├── .gitattributes ├── 11-10评论结果 ├── 11-10 │ ├── lianjie.csv │ ├── pictureName.csv │ ├── pinglun.csv │ ├── 口碑评论.xlsx │ ├── 抓取评论详情结果.xlsx │ └── 评论详情.xlsx ├── 2019-11-10 │ ├── 2019-11-10-21_20_19.png │ ├── 2019-11-10-21_20_34.png │ ├── 2019-11-10-21_20_49.png │ ├── 2019-11-10-21_21_04.png │ ├── 2019-11-10-21_21_19.png │ ├── 2019-11-10-21_21_49.png │ ├── 2019-11-10-21_22_27.png │ ├── 2019-11-10-21_22_42.png │ ├── 2019-11-10-21_22_59.png │ ├── 2019-11-10-21_23_14.png │ ├── 2019-11-10-21_23_28.png │ ├── 2019-11-10-21_23_43.png │ ├── 2019-11-10-21_24_09.png │ ├── 2019-11-10-21_24_24.png │ ├── 2019-11-10-21_24_39.png │ ├── 2019-11-10-21_24_54.png │ ├── 2019-11-10-21_25_20.png │ ├── 2019-11-10-21_26_09.png │ ├── 2019-11-10-21_26_36.png │ ├── 2019-11-10-21_26_50.png │ ├── 2019-11-10-21_27_17.png │ ├── 2019-11-10-21_27_43.png │ ├── 2019-11-10-21_27_58.png │ ├── 2019-11-10-21_28_26.png │ ├── 2019-11-10-21_28_41.png │ ├── 2019-11-10-21_29_07.png │ ├── 2019-11-10-21_29_21.png │ ├── 2019-11-10-21_29_36.png │ ├── 2019-11-10-21_29_51.png │ ├── 2019-11-10-21_30_30.png │ ├── 2019-11-10-21_30_57.png │ ├── 2019-11-10-21_31_12.png │ ├── 2019-11-10-21_31_39.png │ ├── 2019-11-10-21_31_54.png │ ├── 2019-11-10-21_32_08.png │ ├── 2019-11-10-21_32_24.png │ ├── 2019-11-10-21_32_50.png │ ├── 2019-11-10-21_33_28.png │ ├── 2019-11-10-21_33_43.png │ ├── 2019-11-10-21_33_57.png │ ├── 2019-11-10-21_34_34.png │ ├── 2019-11-10-21_35_00.png │ ├── 2019-11-10-21_35_13.png │ ├── 2019-11-10-21_35_27.png │ ├── 2019-11-10-21_35_41.png │ ├── 2019-11-10-21_36_07.png │ ├── 2019-11-10-21_36_21.png │ ├── 2019-11-10-21_36_34.png │ ├── 2019-11-10-21_36_48.png │ ├── 2019-11-10-21_37_02.png │ ├── 2019-11-10-21_37_16.png │ ├── 2019-11-10-21_37_30.png │ ├── 2019-11-10-21_38_32.png │ ├── 2019-11-10-21_38_58.png │ ├── 2019-11-10-21_39_12.png │ ├── 2019-11-10-21_39_26.png │ ├── 2019-11-10-21_39_39.png │ ├── 2019-11-10-21_39_54.png │ ├── 2019-11-10-21_40_08.png │ ├── 2019-11-10-21_40_22.png │ ├── 2019-11-10-21_40_37.png │ ├── 2019-11-10-21_40_51.png │ ├── 2019-11-10-21_41_41.png │ ├── 2019-11-10-21_41_56.png │ ├── 2019-11-10-21_42_10.png │ ├── 2019-11-10-21_42_25.png │ ├── 2019-11-10-21_43_27.png │ ├── 2019-11-10-21_43_54.png │ ├── 2019-11-10-21_44_44.png │ ├── 2019-11-10-21_45_10.png │ ├── 2019-11-10-21_45_25.png │ ├── 2019-11-10-21_45_52.png │ ├── 2019-11-10-21_46_07.png │ ├── 2019-11-10-21_46_33.png │ ├── 2019-11-10-21_46_48.png │ ├── 2019-11-10-21_47_03.png │ ├── 2019-11-10-21_47_17.png │ ├── 2019-11-10-21_47_32.png │ ├── 2019-11-10-21_47_47.png │ ├── 2019-11-10-21_48_02.png │ ├── 2019-11-10-21_48_17.png │ ├── 2019-11-10-21_48_32.png │ ├── 2019-11-10-21_48_46.png │ ├── 2019-11-10-21_49_01.png │ ├── 2019-11-10-21_49_40.png │ ├── 2019-11-10-21_49_54.png │ ├── 2019-11-10-21_50_20.png │ ├── 2019-11-10-21_50_37.png │ ├── 2019-11-10-21_50_52.png │ ├── 2019-11-10-21_51_07.png │ ├── 2019-11-10-21_51_47.png │ ├── 2019-11-10-21_52_01.png │ ├── 2019-11-10-21_52_53.png │ ├── 2019-11-10-21_53_19.png │ ├── 2019-11-10-21_53_45.png │ ├── 2019-11-10-21_54_10.png │ ├── 2019-11-10-21_54_24.png │ ├── 2019-11-10-21_54_38.png │ ├── 2019-11-10-21_55_03.png │ ├── 2019-11-10-21_55_40.png │ ├── 2019-11-10-21_56_06.png │ ├── 2019-11-10-21_56_32.png │ ├── 2019-11-10-21_56_46.png │ ├── 2019-11-10-21_56_59.png │ ├── 2019-11-10-21_57_13.png │ ├── 2019-11-10-21_58_14.png │ ├── 2019-11-10-21_58_29.png │ └── 2019-11-10-21_58_56.png ├── Tableprocess.py ├── koubeipinlun.py ├── pictureName.csv ├── pictureandlink.csv ├── pinglun.csv ├── 口碑评论.xlsx ├── 抓取评论详情结果.xlsx └── 评论详情.xlsx ├── 5K壁纸爬虫.py ├── NBA ├── NBA Player.py └── 球员信息.csv ├── README.md ├── 多线程爬取表情包.py ├── 大学排名爬虫.py ├── 安居客二手房.py ├── 王者荣耀英雄信息爬取.py ├── 美桌网图片爬虫.py ├── 表情包爬虫.py ├── 豆瓣电影排名爬虫.py ├── 豆瓣电影爬虫（GUI界面） ├── DoubanMovie.py ├── Movie.py └── main.py └── 链家爬虫（含二手房、新房、租房、小区等爬虫） ├── .idea ├── inspectionProfiles │ └── profiles_settings.xml ├── misc.xml ├── modules.xml ├── workspace.xml └── 链家爬虫.iml ├── 20191030爬取链家上海小区信息 ├── 嘉定 │ ├── jiading_anting.csv │ ├── jiading_fengzhuang.csv │ ├── jiading_huating.csv │ ├── jiading_jiadinglaocheng.csv │ ├── jiading_jiadingxincheng.csv │ ├── jiading_jiangqiao.csv │ ├── jiading_juyuanxinqu.csv │ ├── jiading_malu.csv │ ├── jiading_nanxiang.csv │ ├── jiading_shangda.csv │ ├── jiading_waigang.csv │ ├── jiading_xinchenglu1.csv │ └── jiading_xuxing.csv ├── 奉贤 │ ├── fengxian_fengcheng.csv │ ├── fengxian_fengxianjinhui.csv │ ├── fengxian_haiwan.csv │ ├── fengxian_nanqiao.csv │ ├── fengxian_qingcun.csv │ ├── fengxian_situan.csv │ ├── fengxian_xidu.csv │ ├── fengxian_zhelin.csv │ └── fengxian_zhuanghang.csv ├── 宝山 │ ├── baoshan_dachangzhen.csv │ ├── baoshan_dahua.csv │ ├── baoshan_gongfu.csv │ ├── baoshan_gongkang.csv │ ├── baoshan_gucun.csv │ ├── baoshan_luodian.csv │ ├── baoshan_luojing.csv │ ├── baoshan_songbao.csv │ ├── baoshan_songnan.csv │ ├── baoshan_tonghe.csv │ ├── baoshan_yanghang.csv │ ├── baoshan_yuepu.csv │ └── baoshan_zhangmiao.csv ├── 小区信息 │ ├── 上海各区小区信息汇总.xlsx │ ├── 嘉定小区信息.xlsx │ ├── 奉贤小区信息.xlsx │ ├── 宝山小区信息.xlsx │ ├── 崇明小区信息.xlsx │ ├── 徐家汇小区信息.xlsx │ ├── 普陀小区信息.xlsx │ ├── 杨浦小区信息.xlsx │ ├── 松江小区信息.xlsx │ ├── 浦东小区信息.xlsx │ ├── 虹口小区信息.xlsx │ ├── 金山小区信息.xlsx │ ├── 长宁区小区信息.xlsx │ ├── 闵行小区信息.xlsx │ ├── 青浦小区信息.xlsx │ ├── 静安小区信息.xlsx │ └── 黄埔小区信息.xlsx ├── 崇明 │ ├── chongming_baozhen.csv │ ├── chongming_changxingdao21211.csv │ ├── chongming_chenjiazhen.csv │ ├── chongming_chongmingqita.csv │ ├── chongming_chongmingxincheng.csv │ └── chongming_hengshadao.csv ├── 徐家汇 │ ├── xuhui_caohejing.csv │ ├── xuhui_changqiao.csv │ ├── xuhui_hengshanlu.csv │ ├── xuhui_huadongligong.csv │ ├── xuhui_huajing.csv │ ├── xuhui_jianguoxilu.csv │ ├── xuhui_kangjian.csv │ ├── xuhui_longhua.csv │ ├── xuhui_shanghainanzhan.csv │ ├── xuhui_tianlin.csv │ ├── xuhui_wantiguan.csv │ ├── xuhui_xietulu.csv │ ├── xuhui_xuhuibinjiang.csv │ ├── xuhui_xujiahui.csv │ └── xuhui_zhiwuyuan.csv ├── 普陀 │ ├── putuo_caoyang.csv │ ├── putuo_changfeng1.csv │ ├── putuo_changshoulu.csv │ ├── putuo_changzheng.csv │ ├── putuo_ganquanyichuan.csv │ ├── putuo_guangxin.csv │ ├── putuo_taopu.csv │ ├── putuo_wanli.csv │ ├── putuo_wuning.csv │ ├── putuo_zhenguang.csv │ ├── putuo_zhenru.csv │ └── putuo_zhongyuanliangwancheng.csv ├── 杨浦 │ ├── yangpu_anshan.csv │ ├── yangpu_dongwaitan.csv │ ├── yangpu_gaojing.csv │ ├── yangpu_huangxinggongyuan.csv │ ├── yangpu_kongjianglu.csv │ ├── yangpu_wujiaochang.csv │ ├── yangpu_xinjiangwancheng.csv │ ├── yangpu_zhongyuan1.csv │ └── yangpu_zhoujiazuilu.csv ├── 松江 │ ├── songjiang_chedun.csv │ ├── songjiang_jiuting.csv │ ├── songjiang_maogang.csv │ ├── songjiang_shenminbieshu.csv │ ├── songjiang_sheshan.csv │ ├── songjiang_shihudang.csv │ ├── songjiang_sijing.csv │ ├── songjiang_songjiangdaxuecheng.csv │ ├── songjiang_songjianglaocheng.csv │ ├── songjiang_songjiangxincheng.csv │ ├── songjiang_xiaokunshan.csv │ ├── songjiang_xinbang.csv │ ├── songjiang_xinqiao.csv │ └── songjiang_yexie.csv ├── 浦东 │ ├── pudong_beicai.csv │ ├── pudong_biyun.csv │ ├── pudong_caolu.csv │ ├── pudong_chuansha.csv │ ├── pudong_datuanzhen.csv │ ├── pudong_gaodong.csv │ ├── pudong_gaohang.csv │ ├── pudong_geqing.csv │ ├── pudong_hangtou.csv │ ├── pudong_huamu.csv │ ├── pudong_huinan.csv │ ├── pudong_jinqiao.csv │ ├── pudong_jinyang.csv │ ├── pudong_kangqiao.csv │ ├── pudong_laogangzhen.csv │ ├── pudong_lianyang.csv │ ├── pudong_lingangxincheng.csv │ ├── pudong_lujiazui.csv │ ├── pudong_nanmatou.csv │ ├── pudong_nichengzhen.csv │ ├── pudong_sanlin.csv │ ├── pudong_shibo.csv │ ├── pudong_shuyuanzhen.csv │ ├── pudong_tangqiao.csv │ ├── pudong_tangzhen.csv │ ├── pudong_waigaoqiao.csv │ ├── pudong_wanxiangzhen.csv │ ├── pudong_weifang.csv │ ├── pudong_xinchang.csv │ ├── pudong_xuanqiao.csv │ ├── pudong_yangdong.csv │ ├── pudong_yangjing.csv │ ├── pudong_yuanshen.csv │ ├── pudong_yuqiao1.csv │ ├── pudong_zhangjiang.csv │ ├── pudong_zhoupu.csv │ └── pudong_zhuqiao.csv ├── 虹口 │ ├── hongkou_beiwaitan.csv │ ├── hongkou_jiangwanzhen.csv │ ├── hongkou_liangcheng.csv │ ├── hongkou_linpinglu.csv │ ├── hongkou_luxungongyuan.csv │ ├── hongkou_quyang.csv │ └── hongkou_sichuanbeilu.csv ├── 金山 │ ├── jinshan_caojing.csv │ ├── jinshan_fengjing.csv │ ├── jinshan_jinshan1.csv │ ├── jinshan_langxia.csv │ ├── jinshan_luxiang.csv │ ├── jinshan_shanyang.csv │ ├── jinshan_shihua.csv │ ├── jinshan_tinglin.csv │ ├── jinshan_zhangyan.csv │ └── jinshan_zhujing.csv ├── 长宁 │ ├── changning_beixinjing.csv │ ├── changning_gubei.csv │ ├── changning_hongqiao1.csv │ ├── changning_tianshan.csv │ ├── changning_xianxia.csv │ ├── changning_xijiao.csv │ ├── changning_xinhualu.csv │ ├── changning_zhenninglu.csv │ └── changning_zhongshangongyuan.csv ├── 闵行 │ ├── minhang_chunshen.csv │ ├── minhang_gumei.csv │ ├── minhang_hanghua.csv │ ├── minhang_huacao.csv │ ├── minhang_jinganxincheng.csv │ ├── minhang_jinhongqiao.csv │ ├── minhang_jinhui.csv │ ├── minhang_laominhang.csv │ ├── minhang_longbai.csv │ ├── minhang_maqiao.csv │ ├── minhang_meilong.csv │ ├── minhang_pujiang1.csv │ ├── minhang_qibao.csv │ ├── minhang_wujing.csv │ ├── minhang_xinzhuang5.csv │ └── minhang_zhuanqiao.csv ├── 青浦 │ ├── qingpu_baihe.csv │ ├── qingpu_chonggu.csv │ ├── qingpu_huaxin.csv │ ├── qingpu_jinze.csv │ ├── qingpu_liantang1.csv │ ├── qingpu_xianghuaqiao.csv │ ├── qingpu_xiayang.csv │ ├── qingpu_xujing.csv │ ├── qingpu_yingpu.csv │ ├── qingpu_zhaoxiang.csv │ └── qingpu_zhujiajiao.csv ├── 静安 │ ├── jingan_buyecheng.csv │ ├── jingan_caojiadu.csv │ ├── jingan_daning.csv │ ├── jingan_jiangninglu.csv │ ├── jingan_jingansi.csv │ ├── jingan_nanjingxilu.csv │ ├── jingan_pengpu.csv │ ├── jingan_xizangbeilu.csv │ ├── jingan_yangcheng.csv │ ├── jingan_yonghe.csv │ └── jingan_zhabeigongyuan.csv └── 黄埔 │ ├── huangpu_dapuqiao.csv │ ├── huangpu_dongjiadu.csv │ ├── huangpu_huaihaizhonglu.csv │ ├── huangpu_huangpubinjiang.csv │ ├── huangpu_laoximen.csv │ ├── huangpu_nanjingdonglu.csv │ ├── huangpu_penglaigongyuan.csv │ ├── huangpu_renminguangchang.csv │ ├── huangpu_shibobinjiang.csv │ ├── huangpu_wuliqiao.csv │ ├── huangpu_xintiandi.csv │ └── huangpu_yuyuan.csv ├── LJNTxiaoqu.py ├── LJNew_bouse.py ├── LJershoufang.xlsx ├── LJershoufang ├── LJershoufang.ipynb ├── LJershoufang.md ├── output_5_0.png ├── output_5_2.png ├── output_5_3.png ├── output_5_4.png ├── output_5_5.png ├── output_5_6.png ├── output_5_7.png └── 链家二手房数据分析.pdf ├── LJsecond_house ├── LJershoufang.ipynb ├── LJershoufang.md ├── output_5_0.png ├── output_5_2.png ├── output_5_3.png ├── output_5_4.png ├── output_5_5.png ├── output_5_6.png ├── output_5_7.png └── 链家二手房数据分析.pdf ├── LJzufang.csv ├── LJzufang.py ├── lianjiasecond_house.py ├── 上海小区爬虫最终版 ├── .gitignore ├── README.md ├── lib │ ├── __init__.py │ ├── const │ │ ├── __init__.py │ │ └── xpath.py │ ├── item │ │ ├── __init__.py │ │ └── xiaoqu.py │ ├── request │ │ ├── __init__.py │ │ ├── headers.py │ │ └── proxy.py │ ├── spider │ │ ├── __init__.py │ │ ├── base_spider.py │ │ └── xiaoqu_spider.py │ ├── utility │ │ ├── __init__.py │ │ ├── date.py │ │ ├── log.py │ │ ├── path.py │ │ ├── version.py │ │ └── writer.py │ └── zone │ │ ├── __init__.py │ │ ├── area.py │ │ ├── city.py │ │ └── district.py ├── log │ └── __init__.py ├── pic │ ├── district_top.png │ └── xiaoqu_top.png ├── requirements.txt ├── test │ └── date_test.py ├── tool │ ├── clean.py │ ├── ershou_image_with_coroutine.py │ ├── ershou_image_with_threads.py │ ├── ershou_number.py │ └── lianjia_xiaoqu.sql ├── xiaoqu.py ├── xiaoqu_to_chart.py └── xiaoqu_to_db.py ├── 小区 ├── LJxiaoqu.py ├── LJxiaoquHB.py ├── 上海链家小区信息（第1线程）.csv ├── 上海链家小区信息（第1线程）.xlsx └── 上海链家小区信息（第2线程）.xlsx ├── 链家二手房.xlsx ├── 链家二手房数据整理.xlsx ├── 链家新房.csv ├── 链家新房.xlsx └── 链家租房.xlsx /.gitattributes: -------------------------------------------------------------------------------- 1 | *.js linguist-language=python 2 | *.css linguist-language=python 3 | *.html linguist-language=python 4 | -------------------------------------------------------------------------------- /11-10评论结果/11-10/pinglun.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/11-10/pinglun.csv -------------------------------------------------------------------------------- /11-10评论结果/11-10/口碑评论.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/11-10/口碑评论.xlsx -------------------------------------------------------------------------------- /11-10评论结果/11-10/抓取评论详情结果.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/11-10/抓取评论详情结果.xlsx -------------------------------------------------------------------------------- /11-10评论结果/11-10/评论详情.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/11-10/评论详情.xlsx -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_20_19.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_20_19.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_20_34.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_20_34.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_20_49.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_20_49.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_21_04.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_21_04.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_21_19.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_21_19.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_21_49.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_21_49.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_22_27.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_22_27.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_22_42.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_22_42.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_22_59.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_22_59.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_23_14.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_23_14.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_23_28.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_23_28.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_23_43.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_23_43.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_24_09.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_24_09.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_24_24.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_24_24.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_24_39.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_24_39.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_24_54.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_24_54.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_25_20.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_25_20.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_26_09.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_26_09.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_26_36.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_26_36.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_26_50.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_26_50.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_27_17.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_27_17.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_27_43.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_27_43.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_27_58.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_27_58.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_28_26.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_28_26.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_28_41.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_28_41.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_29_07.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_29_07.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_29_21.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_29_21.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_29_36.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_29_36.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_29_51.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_29_51.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_30_30.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_30_30.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_30_57.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_30_57.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_31_12.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_31_12.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_31_39.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_31_39.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_31_54.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_31_54.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_32_08.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_32_08.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_32_24.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_32_24.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_32_50.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_32_50.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_33_28.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_33_28.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_33_43.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_33_43.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_33_57.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_33_57.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_34_34.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_34_34.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_35_00.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_35_00.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_35_13.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_35_13.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_35_27.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_35_27.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_35_41.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_35_41.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_36_07.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_36_07.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_36_21.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_36_21.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_36_34.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_36_34.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_36_48.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_36_48.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_37_02.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_37_02.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_37_16.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_37_16.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_37_30.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_37_30.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_38_32.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_38_32.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_38_58.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_38_58.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_39_12.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_39_12.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_39_26.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_39_26.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_39_39.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_39_39.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_39_54.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_39_54.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_40_08.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_40_08.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_40_22.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_40_22.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_40_37.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_40_37.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_40_51.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_40_51.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_41_41.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_41_41.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_41_56.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_41_56.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_42_10.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_42_10.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_42_25.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_42_25.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_43_27.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_43_27.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_43_54.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_43_54.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_44_44.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_44_44.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_45_10.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_45_10.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_45_25.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_45_25.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_45_52.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_45_52.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_46_07.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_46_07.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_46_33.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_46_33.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_46_48.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_46_48.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_47_03.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_47_03.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_47_17.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_47_17.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_47_32.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_47_32.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_47_47.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_47_47.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_48_02.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_48_02.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_48_17.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_48_17.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_48_32.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_48_32.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_48_46.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_48_46.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_49_01.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_49_01.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_49_40.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_49_40.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_49_54.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_49_54.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_50_20.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_50_20.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_50_37.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_50_37.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_50_52.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_50_52.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_51_07.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_51_07.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_51_47.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_51_47.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_52_01.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_52_01.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_52_53.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_52_53.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_53_19.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_53_19.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_53_45.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_53_45.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_54_10.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_54_10.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_54_24.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_54_24.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_54_38.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_54_38.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_55_03.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_55_03.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_55_40.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_55_40.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_56_06.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_56_06.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_56_32.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_56_32.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_56_46.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_56_46.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_56_59.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_56_59.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_57_13.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_57_13.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_58_14.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_58_14.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_58_29.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_58_29.png -------------------------------------------------------------------------------- /11-10评论结果/2019-11-10/2019-11-10-21_58_56.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/2019-11-10/2019-11-10-21_58_56.png -------------------------------------------------------------------------------- /11-10评论结果/Tableprocess.py: -------------------------------------------------------------------------------- 1 | import pandas as pd 2 | df1 = pd.read_excel(r'C:\Users\xiaoLiu\Desktop\口碑评论.xlsx', header=0, index_col=None) 3 | df2 = pd.read_excel(r'C:\Users\xiaoLiu\Desktop\评论详情.xlsx', header=0, index_col=None) 4 | df3 = pd.merge(df1, df2, how='outer', on='字段4_link', left_on=None, right_on=None, 5 | left_index=False, right_index=False, sort=False, 6 | suffixes=('_x', '_y'), copy=True, indicator=False) 7 | df3.to_csv('./lianjiepinglun.csv') -------------------------------------------------------------------------------- /11-10评论结果/koubeipinlun.py: -------------------------------------------------------------------------------- 1 | from aip import AipOcr 2 | import pandas as pd 3 | from sqlalchemy import create_engine 4 | import os 5 | import csv 6 | 7 | def getsceenshot(search_url,list): 8 | from selenium import webdriver 9 | import os 10 | import time 11 | from selenium.webdriver.common.by import By 12 | from selenium.webdriver.support.ui import WebDriverWait 13 | from selenium.webdriver.support import expected_conditions as EC 14 | from selenium import webdriver 15 | 16 | picture_time = time.strftime("%Y-%m-%d-%H_%M_%S", time.localtime(time.time())) 17 | directory_time = time.strftime("%Y-%m-%d", time.localtime(time.time())) 18 | 19 | try: 20 | File_Path = os.getcwd() + '\\' + directory_time + '\\' 21 | if not os.path.exists(File_Path): 22 | os.makedirs(File_Path) 23 | print("存入文件%s" % File_Path) 24 | else: 25 | print("写入新文件") 26 | except BaseException as msg: 27 | print("异常：%s" % msg) 28 | try: 29 | options = webdriver.ChromeOptions() 30 | options.add_argument('--headless') 31 | options.add_argument('--disable-gpu') 32 | driver = webdriver.Chrome(options=options) 33 | driver.maximize_window() 34 | 35 | js_height = "return document.body.clientHeight" 36 | 37 | # driver = webdriver.Chrome() 38 | driver.get(search_url) 39 | driver.execute_script(""" 40 | (function () { 41 | $('.subnav-title').hide(); 42 | $('.video-iframe').hide(); 43 | $('.mouth-remak').hide(); 44 | $('.contmain').hide(); 45 | $('.footer_auto').hide(); 46 | $('.mouth-title-end over-hid').hide(); 47 | $('.user-cont').hide(); 48 | $('.mouth-title-end').hide(); 49 | $('.nav-typebar-g12').hide(); 50 | $('.breadnav').hide(); 51 | $('.minitop').hide(); 52 | $('.topbar-header').hide(); 53 | $('.gotop02').hide(); 54 | $('.image-div').hide(); 55 | $('.video-container').hide(); 56 | $('.advbox1').hide(); 57 | $('.mouthcon-cont-left').hide(); 58 | $('.mouthcon-cont-right').attr('width','800'); 59 | $('.text-con').attr('font-size','18'); 60 | $('.img-list').hide(); 61 | })(); 62 | """) 63 | 64 | k = 1 65 | height = driver.execute_script(js_height) 66 | while True: 67 | if k * 500 < height: 68 | js_move = "window.scrollTo(0,{})".format(k * 500) 69 | print(js_move) 70 | driver.execute_script(js_move) 71 | time.sleep(0.2) 72 | height = driver.execute_script(js_height) 73 | k += 1 74 | else: 75 | break 76 | scroll_width = driver.execute_script('return document.body.parentNode.scrollWidth') 77 | scroll_height = driver.execute_script('return document.body.parentNode.scrollHeight') 78 | driver.set_window_size(scroll_width, scroll_height) 79 | driver.get_screenshot_as_file( 80 | '.\\' + directory_time + '\\' + picture_time + '.png') 81 | print("Process {} get one pic !!!".format(os.getpid())) 82 | list.append(search_url) 83 | print(list) 84 | 85 | 86 | except Exception as e: 87 | print(e) 88 | 89 | 90 | finally: 91 | driver.quit() 92 | print('爬取完成') 93 | return ('.\\' + directory_time + '\\' + picture_time + '.png') 94 | 95 | def getlinks(links): 96 | list=[] 97 | for link in links: 98 | getsceenshot(link,list) 99 | df=pd.Series(list) 100 | df.to_csv('./lianjie.csv',index=False) 101 | 102 | def getfile(rootdir): 103 | list = os.listdir(rootdir)#列出文件夹下所有的目录与文件 104 | lujing=[] 105 | for i in range(0,len(list)): 106 | rootdir = r'C:\Users\xiaoLiu\Desktop\11-10评论结果\2019-11-14' 107 | path = os.path.join(rootdir,list[i]) 108 | lujing.append(path) 109 | df=pd.Series(lujing) 110 | df.to_csv('./pictureName.csv',index=False) 111 | 112 | def get_file_content(filePath): 113 | """ 读取图片 """ 114 | with open(filePath, 'rb') as fp: 115 | return fp.read() 116 | 117 | def change_to_words(imgpath): 118 | APP_ID = '17523158' 119 | API_KEY = '9wyiqfr4Ob0llopVzzigi5T3' 120 | SECRET_KEY = 'Mo6Ctv7d6HstNesgPfiCOwxgeSw7nKyG' 121 | aipOcr = AipOcr(APP_ID, API_KEY, SECRET_KEY) 122 | for column in imgpath: 123 | options = {'detect_direction': 'true','language_type': 'CHN_ENG'} 124 | result = aipOcr.basicGeneral(get_file_content(column), options) 125 | words_result=result['words_result'] 126 | list_result=str() 127 | for i in range(len(words_result)): 128 | list_result += words_result[i]['words'] 129 | df=pd.Series(list_result) 130 | engine = create_engine("mysql+pymysql://root:960614abcd@localhost:3306/xiaoliu") 131 | df.to_sql(name = 'pinglun',con = engine,if_exists = 'append',index = False,index_label = False) 132 | 133 | if __name__ == '__main__': 134 | df = pd.read_excel(r'C:\Users\xiaoLiu\Desktop\未处理链接.xlsx', header=0, index_col=None) 135 | links = df['字段4_link'] 136 | getlinks(links) 137 | rootdir = r'C:\Users\xiaoLiu\Desktop\11-10评论结果\2019-11-14' 138 | getfile(rootdir) 139 | with open('./pictureName.csv','r',encoding='utf-8') as csvfile: 140 | reader = csv.reader(csvfile) 141 | imgpath = [row[0]for row in reader] 142 | change_to_words(imgpath) -------------------------------------------------------------------------------- /11-10评论结果/pinglun.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/pinglun.csv -------------------------------------------------------------------------------- /11-10评论结果/口碑评论.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/口碑评论.xlsx -------------------------------------------------------------------------------- /11-10评论结果/抓取评论详情结果.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/抓取评论详情结果.xlsx -------------------------------------------------------------------------------- /11-10评论结果/评论详情.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/11-10评论结果/评论详情.xlsx -------------------------------------------------------------------------------- /5K壁纸爬虫.py: -------------------------------------------------------------------------------- 1 | from requests import get 2 | from filetype import guess 3 | from os import rename 4 | from os import makedirs 5 | from os.path import exists 6 | from json import loads 7 | from contextlib import closing 8 | 9 | 10 | # 文件下载器 11 | def Down_load(file_url, file_full_name, now_photo_count, all_photo_count): 12 | headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36"} 13 | 14 | # 开始下载图片 15 | with closing(get(file_url, headers=headers, stream=True)) as response: 16 | chunk_size = 1024 # 单次请求最大值 17 | content_size = int(response.headers['content-length']) # 文件总大小 18 | data_count = 0 # 当前已传输的大小 19 | with open(file_full_name, "wb") as file: 20 | for data in response.iter_content(chunk_size=chunk_size): 21 | file.write(data) 22 | done_block = int((data_count / content_size) * 50) 23 | data_count = data_count + len(data) 24 | now_jd = (data_count / content_size) * 100 25 | print("\r %s：[%s%s] %d%% %d/%d" % (file_full_name, done_block * '█', ' ' * (50 - 1 - done_block), now_jd, now_photo_count, all_photo_count), end=" ") 26 | 27 | # 下载完图片后获取图片扩展名，并为其增加扩展名 28 | file_type = guess(file_full_name) 29 | rename(file_full_name, file_full_name + '.' + file_type.extension) 30 | 31 | 32 | 33 | # 爬取不同类型图片 34 | def crawler_photo(type_id, photo_count): 35 | 36 | # 最新 1, 最热 2, 女生 3, 星空 4 37 | if(type_id == 1): 38 | url = 'https://service.paper.meiyuan.in/api/v2/columns/flow/5c68ffb9463b7fbfe72b0db0?page=1&per_page=' + str(photo_count) 39 | elif(type_id == 2): 40 | url = 'https://service.paper.meiyuan.in/api/v2/columns/flow/5c69251c9b1c011c41bb97be?page=1&per_page=' + str(photo_count) 41 | elif(type_id == 3): 42 | url = 'https://service.paper.meiyuan.in/api/v2/columns/flow/5c81087e6aee28c541eefc26?page=1&per_page=' + str(photo_count) 43 | elif(type_id == 4): 44 | url = 'https://service.paper.meiyuan.in/api/v2/columns/flow/5c81f64c96fad8fe211f5367?page=1&per_page=' + str(photo_count) 45 | 46 | # 获取图片列表数据 47 | headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36"} 48 | respond = get(url, headers=headers) 49 | photo_data = loads(respond.content) 50 | 51 | # 已经下载的图片张数 52 | now_photo_count = 1 53 | 54 | # 所有图片张数 55 | all_photo_count = len(photo_data) 56 | 57 | # 开始下载并保存5K分辨率壁纸 58 | for photo in photo_data: 59 | 60 | # 创建一个文件夹存放我们下载的图片 61 | if not exists('./' + str(type_id)): 62 | makedirs('./' + str(type_id)) 63 | 64 | # 准备下载的图片链接 65 | file_url = photo['urls']['raw'] 66 | 67 | # 准备下载的图片名称,不包含扩展名 68 | file_name_only = file_url.split('/') 69 | file_name_only = file_name_only[len(file_name_only) -1] 70 | 71 | # 准备保存到本地的完整路径 72 | file_full_name = './' + str(type_id) + '/' + file_name_only 73 | 74 | # 开始下载图片 75 | Down_load(file_url, file_full_name, now_photo_count, all_photo_count) 76 | now_photo_count = now_photo_count + 1 77 | 78 | 79 | 80 | if __name__ == '__main__': 81 | 82 | # 最新 1, 最热 2, 女生 3, 星空 4 83 | # 爬取类型为3的图片(女生),一共准备爬取20000张 84 | wall_paper_id = 1 85 | wall_paper_count = 10 86 | while(True): 87 | 88 | # 换行符 89 | print('\n\n') 90 | 91 | # 选择壁纸类型 92 | wall_paper_id = input("壁纸类型：最新壁纸 1, 最热壁纸 2, 女生壁纸 3, 星空壁纸 4\n请输入编号以便选择5K超清壁纸类型：") 93 | # 判断输入是否正确 94 | while(wall_paper_id != str(1) and wall_paper_id != str(2) and wall_paper_id != str(3) and wall_paper_id != str(4)): 95 | wall_paper_id = input("壁纸类型：最新壁纸 1, 最热壁纸 2, 女生壁纸 3, 星空壁纸 4\n请输入编号以便选择5K超清壁纸类型：") 96 | 97 | 98 | # 选择要下载的壁纸数量 99 | wall_paper_count = input("请输入要下载的5K超清壁纸的数量：") 100 | # 判断输入是否正确 101 | while(int(wall_paper_count) <= 0): 102 | wall_paper_count = input("请输入要下载的5K超清壁纸的数量：") 103 | 104 | 105 | # 开始爬取5K高清壁纸 106 | print("正在下载5K超清壁纸，请稍等……") 107 | crawler_photo(int(wall_paper_id), int(wall_paper_count)) 108 | print('\n下载5K高清壁纸成功!') -------------------------------------------------------------------------------- /NBA/NBA Player.py: -------------------------------------------------------------------------------- 1 | import pandas as pd 2 | import numpy as n 3 | 4 | # 读取网页中的数据表 5 | table = [] 6 | for i in range(1,7): 7 | table.append(pd.read_html('https://nba.hupu.com/stats/players/pts/%d' %i)[0]) 8 | 9 | # 所有数据纵向合并为数据框 10 | players = pd.concat(table) 11 | # 变量重命名 12 | columns=['排名','球员','球队','得分','命中-出手','命中率','命中-三分','三分命中率','命中-罚球','罚球命中率','场次','上场时间'] 13 | players.columns=columns 14 | 15 | 16 | players.drop(0,inplace=True) 17 | players.to_csv(r"C:\Users\MI\Desktop\球员信息.csv",encoding='utf_8_sig') 18 | 19 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # PythonSpyder_100_examples 2 | 自学Python爬虫路上的实战笔记，由浅到深逐步深入学习Python 爬虫 3 | -------------------------------------------------------------------------------- /多线程爬取表情包.py: -------------------------------------------------------------------------------- 1 | import requests 2 | import random 3 | import os 4 | from bs4 import BeautifulSoup 5 | import threading 6 | 7 | class crawler_pic(threading.Thread): 8 | begin_index = 0 # 起始页面 9 | end_index = 0 # 终止页 10 | grads = 20 # 爬取梯度：每个线程爬虫需要执行的爬取页数 11 | # 链接 12 | base_url = "http://www.win4000.com/wallpaper_big_154{}.html" 13 | # 图片保存根目录 14 | file_root = "D://pics_multi//" 15 | # 伪装浏览器 16 | UA = [ 17 | "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50", 18 | "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50", 19 | "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1", 20 | "Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1" 21 | ] 22 | # 随机构造头部信息 23 | headers = { 24 | "User-Agent": random.choice(UA) 25 | } 26 | def __init__(self, name, begin): 27 | threading.Thread.__init__(self) 28 | self.name = name 29 | self.begin_index = begin 30 | self.end_index = begin + self.grads 31 | # 获取 32 | def get_html(self, url): 33 | try: 34 | HTML = requests.get(url,headers=self.headers) 35 | HTML.raise_for_status() 36 | HTML.encoding = HTML.apparent_encoding 37 | return HTML.text 38 | except: 39 | print("In "+self.name+":ERROR Load "+url) 40 | return "NULL" 41 | # 将获取的图片存储至根目录下 42 | def store_pics(self,pic_urls): 43 | fileName = pic_urls[0]+"//" 44 | for picurl in pic_urls[1:]: 45 | # 构造图片存储地址 46 | path = self.file_root + fileName + picurl.split('/')[-1] 47 | print(path) 48 | 49 | try: 50 | # 需要逐层创建目录 51 | if not os.path.exists(self.file_root): 52 | os.mkdir(self.file_root) 53 | # 如无该目录，先行构建 54 | if not os.path.exists(self.file_root+fileName): 55 | os.mkdir(self.file_root+fileName) 56 | # 图片存在，不重复保存 57 | # 不存在，创建 58 | if not os.path.exists(path): 59 | # request获取图片内容 60 | pic = requests.get(picurl) 61 | with open(path, 'wb') as f: 62 | f.write(pic.content) 63 | f.close() 64 | print("图片:" + picurl + " 成功下载") 65 | else: 66 | print("图片已存在") 67 | except: 68 | print("爬取失败") 69 | return 1 70 | 71 | # 在html页面中获取图片链接，返回链接列表 72 | def get_pic_urls(self, HTML): 73 | 74 | pic_urls = ["filename"] 75 | soup = BeautifulSoup(HTML, "html.parser") 76 | """ 77 | 页面分析： 78 | 图片链接位于标签
--
  • -- [href:pic_url] 79 | 获取最上层:div 全部子孙标签 选取a 获取a的属性信息 80 | """ 81 | for tag in soup.find("div", attrs={"id": "picBox", "class": "picBox"}).descendants: 82 | if tag.name == 'img': 83 | pic_urls.append(tag.attrs['src']) 84 | pic_urls[0] = tag.attrs['title'] 85 | """ 86 | for a_tag in soup.find("div", attrs={"id": "picBox", "class": "picBox"}).findAll("a"): 87 | pic_urls.append(a_tag.attrs['href']) 88 | """ 89 | # 全局，记录图片数量 90 | global pic_num 91 | pic_num += len(pic_urls) - 1 92 | return pic_urls 93 | 94 | # 线程方法 95 | def run(self): 96 | # 爬取一遍分配的页面 97 | for i in range(self.begin_index,self.end_index): 98 | html = self.get_html(self.base_url.format(i)) 99 | # 页面爬取成功的情况下获取图片链接 100 | if html != "NULL": 101 | pic_urls = self.get_pic_urls(html) 102 | self.store_pics(pic_urls) 103 | """ 104 | for pic in pic_urls: 105 | print("in "+self.name+":"+pic) 106 | """ 107 | 108 | 109 | if __name__ == '__main__': 110 | 111 | threads = [] 112 | count = 0 113 | pic_num = 0 114 | # 构造爬虫 115 | for begin in range(700,900,20): 116 | threads.append(crawler_pic("Thread-begin:"+str(begin),begin)) 117 | 118 | # 开始爬取 119 | for thread in threads: 120 | thread.start() 121 | 122 | for thread in threads: 123 | thread.join() 124 | 125 | 126 | print(pic_num) -------------------------------------------------------------------------------- /大学排名爬虫.py: -------------------------------------------------------------------------------- 1 | import requests 2 | from bs4 import BeautifulSoup 3 | import bs4 4 | 5 | def getHTMLText(url): 6 | try: 7 | r = requests.get(url,timeout = 30) 8 | r.raise_for_status() 9 | r.encoding = r.apparent_encoding 10 | return r.text 11 | except: 12 | print("getError") 13 | return "" 14 | return "" 15 | 16 | def fillUnivList(ulist,html): 17 | soup = BeautifulSoup(html,"html.parser") 18 | """ 19 | 结构分析 20 | 排名位于tbody标签下 21 | 每个tr标签是一个学校的信息 22 | tr标签下有多个td标签，保存有该学校的各类指标 23 | """ 24 | # 遍历tr标签 tr标签是tbody标签的孩子 25 | for tr in soup.find('tbody').children: 26 | print(tr) 27 | if isinstance(tr,bs4.element.Tag): 28 | # 获取tr标签下的td标签 29 | tds = tr('td') 30 | # 获取相关指标 只需要第 0 1 3 个相关td标签，分别是学校名称，排名，分数 31 | ulist.append([tds[0].string,tds[1].string,tds[3].string]) 32 | 33 | # 打印前20的榜单 34 | def printUnivList(ulist,num): 35 | """ 36 | print("{:^10}\t{:^6}\t{:^10}".format("排名","学校名称","分数")) 37 | for i in range(num): 38 | u = ulist[i] 39 | print("{:^10}\t{:^6}\t{:^10}".format(u[0],u[1],u[2])) 40 | """ 41 | 42 | # 优化，解决中文不对齐问题 43 | #^num num代表占位 44 | tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}" 45 | # chr(12288)是中文空白符 46 | print(tplt.format("排名","学校名称","分数",chr(12288))) 47 | for i in range(num): 48 | u = ulist[i] 49 | print(tplt.format(u[0],u[1],u[2],chr(12288))) 50 | def main(): 51 | unifo = [] 52 | url = "http://www.zuihaodaxue.cn/zuihaodaxuepaiming2019.html" 53 | html = getHTMLText(url) 54 | fillUnivList(unifo,html) 55 | printUnivList(unifo,100) 56 | 57 | main() -------------------------------------------------------------------------------- /安居客二手房.py: -------------------------------------------------------------------------------- 1 | import requests 2 | import time 3 | import csv 4 | import random 5 | from bs4 import BeautifulSoup 6 | 7 | headers = { 8 | 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:69.0) Gecko/20100101 Firefox/69.0', 9 | 'Cookie':'sessid=F3A0D86E-9D3F-82F9-1BBA-D4A22CE6440F; aQQ_ajkguid=35DAB075-3352-357E-F3D9-D46F6E3E210A; lps=http%3A%2F%2Fwww.anjuke.com%2F%3Fpi%3DPZ-baidu-pc-all-biaoti%7Chttps%3A%2F%2Fsp0.baidu.com%2F9q9JcDHa2gU2pMbgoY3K%2Fadrc.php%3Ft%3D06KL00c00f7Hj1f0q3V-00PpAsK8poKI00000FYEi7C00000I5matL.THvs_oeHEtY0UWdVUv4_py4-g1PxuAT0T1d9PyPhPymLPW0sn1N-mW790ZRqwRuKfYFAPRwDfbRdrRPjfWKanWfsnYmsPYu7n1wKrHc0mHdL5iuVmv-b5HnzrHDvnH61njchTZFEuA-b5HDv0ARqpZwYTZnlQzqLILT8my4JIyV-QhPEUitOTAbqR7CVmh7GuZRVTAnVmyk_QyFGmyqYpfKWThnqPHRvP10%26tpl%3Dtpl_11534_19968_16032%26l%3D1514680221%26attach%3Dlocation%253D%2526linkName%253D%2525E6%2525A0%252587%2525E5%252587%252586%2525E5%2525A4%2525B4%2525E9%252583%2525A8-%2525E6%2525A0%252587%2525E9%2525A2%252598-%2525E4%2525B8%2525BB%2525E6%2525A0%252587%2525E9%2525A2%252598%2526linkText%253D%2525E5%2525AE%252589%2525E5%2525B1%252585%2525E5%2525AE%2525A2-%2525E5%252585%2525A8%2525E6%252588%2525BF%2525E6%2525BA%252590%2525E7%2525BD%252591%2525EF%2525BC%25258C%2525E6%252596%2525B0%2525E6%252588%2525BF%252520%2525E4%2525BA%25258C%2525E6%252589%25258B%2525E6%252588%2525BF%252520%2525E6%25258C%252591%2525E5%2525A5%2525BD%2525E6%252588%2525BF%2525E4%2525B8%25258A%2525E5%2525AE%252589%2525E5%2525B1%252585%2525E5%2525AE%2525A2%2525EF%2525BC%252581%2526xp%253Did%28%252522m3291618302_canvas%252522%29%25252FDIV%25255B1%25255D%25252FDIV%25255B1%25255D%25252FDIV%25255B1%25255D%25252FDIV%25255B1%25255D%25252FDIV%25255B1%25255D%25252FH2%25255B1%25255D%25252FA%25255B1%25255D%2526linkType%253D%2526checksum%253D129%26ie%3Dutf-8%26f%3D8%26tn%3Dmonline_3_dg%26wd%3D%25E5%25AE%2589%25E5%25B1%2585%25E5%25AE%25A2%26oq%3D%25E5%25AE%2589%25E5%25B1%2585%25E5%25AE%25A2%26rqlang%3Dcn; ctid=11; twe=2; _stat_guid=3050B320-8AA3-6F6A-9549-5BF2054466BB; _stat_rfpn=Ershou_Web_Property_List_FilterPage_tracklog; _prev_stat_guid=35DAB075-3352-357E-F3D9-D46F6E3E210A; 58tj_uuid=37c162b8-8162-4b45-aedf-dfa05080a10a; new_session=0; init_refer=https%253A%252F%252Fsp0.baidu.com%252F9q9JcDHa2gU2pMbgoY3K%252Fadrc.php%253Ft%253D06KL00c00f7Hj1f0q3V-00PpAsK8poKI00000FYEi7C00000I5matL.THvs_oeHEtY0UWdVUv4_py4-g1PxuAT0T1d9PyPhPymLPW0sn1N-mW790ZRqwRuKfYFAPRwDfbRdrRPjfWKanWfsnYmsPYu7n1wKrHc0mHdL5iuVmv-b5HnzrHDvnH61njchTZFEuA-b5HDv0ARqpZwYTZnlQzqLILT8my4JIyV-QhPEUitOTAbqR7CVmh7GuZRVTAnVmyk_QyFGmyqYpfKWThnqPHRvP10%2526tpl%253Dtpl_11534_19968_16032%2526l%253D1514680221%2526attach%253Dlocation%25253D%252526linkName%25253D%252525E6%252525A0%25252587%252525E5%25252587%25252586%252525E5%252525A4%252525B4%252525E9%25252583%252525A8-%252525E6%252525A0%25252587%252525E9%252525A2%25252598-%252525E4%252525B8%252525BB%252525E6%252525A0%25252587%252525E9%252525A2%25252598%252526linkText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xp%25253Did%28%25252522m3291618302_canvas%25252522%29%2525252FDIV%2525255B1%2525255D%2525252FDIV%2525255B1%2525255D%2525252FDIV%2525255B1%2525255D%2525252FDIV%2525255B1%2525255D%2525252FDIV%2525255B1%2525255D%2525252FH2%2525255B1%2525255D%2525252FA%2525255B1%2525255D%252526linkType%25253D%252526checksum%25253D129%2526ie%253Dutf-8%2526f%253D8%2526tn%253Dmonline_3_dg%2526wd%253D%2525E5%2525AE%252589%2525E5%2525B1%252585%2525E5%2525AE%2525A2%2526oq%253D%2525E5%2525AE%252589%2525E5%2525B1%252585%2525E5%2525AE%2525A2%2526rqlang%253Dcn; new_uv=1; _ga=GA1.2.371539118.1571842678; _gid=GA1.2.389870108.1571842678; als=0; __xsptplus8=8.1.1571842677.1571846354.37%232%7Csp0.baidu.com%7C%7C%7C%25E5%25AE%2589%25E5%25B1%2585%25E5%25AE%25A2%7C%23%23A8ZibGF0HQquvvworKFYDClvSKK6Plsf%23; isp=true; Hm_lvt_c5899c8768ebee272710c9c5f365a6d8=1571842689; Hm_lpvt_c5899c8768ebee272710c9c5f365a6d8=1571844621; __xsptplusUT_8=1; _gat=1' 10 | } 11 | 12 | 13 | def parse_pages(url, num): 14 | response = requests.get(url=url, headers=headers) 15 | soup = BeautifulSoup(response.text, 'lxml') 16 | result_list = soup.find_all('li', class_='list-item') 17 | # print(len(result_list)) 18 | for result in result_list: 19 | # 标题 20 | title = result.find('a', class_='houseListTitle').text.strip() 21 | # print(title) 22 | # 户型 23 | layout = result.select('.details-item > span')[0].text 24 | # print(layout) 25 | # 面积 26 | cover = result.select('.details-item > span')[1].text 27 | # print(cover) 28 | # 楼层 29 | floor = result.select('.details-item > span')[2].text 30 | # print(floor) 31 | # 建造年份 32 | year = result.select('.details-item > span')[3].text 33 | # print(year) 34 | # 单价 35 | unit_price = result.find('span', class_='unit-price').text.strip() 36 | # print(unit_price) 37 | # 总价 38 | total_price = result.find('span', class_='price-det').text.strip() 39 | # print(total_price) 40 | # 关键字 41 | keyword = result.find('div', class_='tags-bottom').text.strip() 42 | # print(keyword) 43 | # 地址 44 | address = result.find('span', class_='comm-address').text.replace(' ', '').replace('\n', '') 45 | # print(address) 46 | # 详情页url 47 | details_url = result.find('a', class_='houseListTitle')['href'] 48 | # print(details_url) 49 | results = [title, layout, cover, floor, year, unit_price, total_price, keyword, address, details_url] 50 | with open('anjuke.csv', 'a', newline='', encoding='utf-8-sig') as f: 51 | w = csv.writer(f) 52 | w.writerow(results) 53 | 54 | # 判断是否还有下一页 55 | next_url = soup.find_all('a', class_='aNxt') 56 | if len(next_url) != 0: 57 | num += 1 58 | print('第' + str(num) + '页数据爬取完毕！') 59 | # 3-60秒之间随机暂停 60 | time.sleep(random.randint(3, 60)) 61 | parse_pages(next_url[0].attrs['href'], num) 62 | else: 63 | print('所有数据爬取完毕！') 64 | 65 | 66 | if __name__ == '__main__': 67 | with open('anjuke.csv', 'a', newline='', encoding='utf-8-sig') as fp: 68 | writer = csv.writer(fp) 69 | writer.writerow(['标题', '户型', '面积', '楼层', '建造年份', '单价', '总价', '关键字', '地址', '详情页地址']) 70 | start_num = 0 71 | start_url = 'https://shanghai.anjuke.com/sale/' 72 | parse_pages(start_url, start_num) 73 | 74 | -------------------------------------------------------------------------------- /王者荣耀英雄信息爬取.py: -------------------------------------------------------------------------------- 1 | #-*- coding: UTF-8 -*- 2 | from urllib.request import urlretrieve 3 | import requests 4 | import os 5 | 6 | 7 | def hero_imgs_download(url, header): 8 | req = requests.get(url = url, headers = header).json() 9 | hero_num = len(req['list']) 10 | print('一共有%d个英雄' % hero_num) 11 | hero_images_path = 'hero_images' 12 | for each_hero in req['list']: 13 | hero_photo_url = each_hero['cover'] 14 | hero_name = each_hero['name'] + '.jpg' 15 | filename = hero_images_path + '/' + hero_name 16 | if hero_images_path not in os.listdir(): 17 | os.makedirs(hero_images_path) 18 | urlretrieve(url = hero_photo_url, filename = filename) 19 | 20 | 21 | def hero_list(url, header): 22 | print('*' * 100) 23 | print('\t\t\t\t欢迎使用《王者荣耀》出装下助手！') 24 | print('*' * 100) 25 | req = requests.get(url = url, headers = header).json() 26 | flag = 0 27 | for each_hero in req['list']: 28 | flag += 1 29 | print('%s的ID为:%-7s' % (each_hero['name'], each_hero['hero_id']), end = '\t\t') 30 | if flag == 3: 31 | print('\n', end = '') 32 | flag = 0 33 | 34 | 35 | def seek_weapon(equip_id, weapon_info): 36 | for each_weapon in weapon_info: 37 | if each_weapon['equip_id'] == str(equip_id): 38 | weapon_name = each_weapon['name'] 39 | weapon_price = each_weapon['price'] 40 | return weapon_name, weapon_price 41 | 42 | 43 | def hero_info(url, header, weapon_info): 44 | req = requests.get(url = url, headers = header).json() 45 | print('\n历史上的%s:\n %s' % (req['info']['name'], req['info']['history_intro'])) 46 | for each_equip_choice in req['info']['equip_choice']: 47 | print('\n%s:\n %s' % (each_equip_choice['title'], each_equip_choice['description'])) 48 | total_price = 0 49 | flag = 0 50 | for each_weapon in each_equip_choice['list']: 51 | flag += 1 52 | weapon_name, weapon_price = seek_weapon(each_weapon['equip_id'], weapon_info) 53 | print('%s:%s' % (weapon_name, weapon_price), end = '\t') 54 | if flag == 3: 55 | print('\n', end = '') 56 | flag = 0 57 | total_price += int(weapon_price) 58 | print('神装套件价格共计:%d' % total_price) 59 | 60 | def hero_weapon(url, header): 61 | req = requests.get(url = url, headers = header).json() 62 | weapon_info_dict = req['list'] 63 | return weapon_info_dict 64 | 65 | 66 | if __name__ == '__main__': 67 | headers = {'Accept-Charset': 'UTF-8', 68 | 'Accept-Encoding': 'gzip,deflate', 69 | 'User-Agent': 'Dalvik/2.1.0 (Linux; U; Android 6.0.1; MI 5 MIUI/V8.1.6.0.MAACNDI)', 70 | 'X-Requested-With': 'XMLHttpRequest', 71 | 'Content-type': 'application/x-www-form-urlencoded', 72 | 'Connection': 'Keep-Alive', 73 | 'Host': 'gamehelper.gm825.com'} 74 | weapon_url = "http://gamehelper.gm825.com/wzry/equip/list?channel_id=90009a&app_id=h9044j&game_id=7622&game_name=%E7%8E%8B%E8%80%85%E8%8D%A3%E8%80%80&vcode=12.0.3&version_code=1203&cuid=2654CC14D2D3894DBF5808264AE2DAD7&ovr=6.0.1&device=Xiaomi_MI+5&net_type=1&client_id=1Yfyt44QSqu7PcVdDduBYQ%3D%3D&info_ms=fBzJ%2BCu4ZDAtl4CyHuZ%2FJQ%3D%3D&info_ma=XshbgIgi0V1HxXTqixI%2BKbgXtNtOP0%2Fn1WZtMWRWj5o%3D&mno=0&info_la=9AChHTMC3uW%2BfY8%2BCFhcFw%3D%3D&info_ci=9AChHTMC3uW%2BfY8%2BCFhcFw%3D%3D&mcc=0&clientversion=&bssid=VY%2BeiuZRJ%2FwaXmoLLVUrMODX1ZTf%2F2dzsWn2AOEM0I4%3D&os_level=23&os_id=dc451556fc0eeadb&resolution=1080_1920&dpi=480&client_ip=192.168.0.198&pdunid=a83d20d8" 75 | heros_url = "http://gamehelper.gm825.com/wzry/hero/list?channel_id=90009a&app_id=h9044j&game_id=7622&game_name=%E7%8E%8B%E8%80%85%E8%8D%A3%E8%80%80&vcode=12.0.3&version_code=1203&cuid=2654CC14D2D3894DBF5808264AE2DAD7&ovr=6.0.1&device=Xiaomi_MI+5&net_type=1&client_id=1Yfyt44QSqu7PcVdDduBYQ%3D%3D&info_ms=fBzJ%2BCu4ZDAtl4CyHuZ%2FJQ%3D%3D&info_ma=XshbgIgi0V1HxXTqixI%2BKbgXtNtOP0%2Fn1WZtMWRWj5o%3D&mno=0&info_la=9AChHTMC3uW%2BfY8%2BCFhcFw%3D%3D&info_ci=9AChHTMC3uW%2BfY8%2BCFhcFw%3D%3D&mcc=0&clientversion=&bssid=VY%2BeiuZRJ%2FwaXmoLLVUrMODX1ZTf%2F2dzsWn2AOEM0I4%3D&os_level=23&os_id=dc451556fc0eeadb&resolution=1080_1920&dpi=480&client_ip=192.168.0.198&pdunid=a83d20d8" 76 | hero_list(heros_url, headers) 77 | hero_id = input("请输入要查询的英雄ID:") 78 | hero_url = "http://gamehelper.gm825.com/wzry/hero/detail?hero_id={}&channel_id=90009a&app_id=h9044j&game_id=7622&game_name=%E7%8E%8B%E8%80%85%E8%8D%A3%E8%80%80&vcode=12.0.3&version_code=1203&cuid=2654CC14D2D3894DBF5808264AE2DAD7&ovr=6.0.1&device=Xiaomi_MI+5&net_type=1&client_id=1Yfyt44QSqu7PcVdDduBYQ%3D%3D&info_ms=fBzJ%2BCu4ZDAtl4CyHuZ%2FJQ%3D%3D&info_ma=XshbgIgi0V1HxXTqixI%2BKbgXtNtOP0%2Fn1WZtMWRWj5o%3D&mno=0&info_la=9AChHTMC3uW%2BfY8%2BCFhcFw%3D%3D&info_ci=9AChHTMC3uW%2BfY8%2BCFhcFw%3D%3D&mcc=0&clientversion=&bssid=VY%2BeiuZRJ%2FwaXmoLLVUrMODX1ZTf%2F2dzsWn2AOEM0I4%3D&os_level=23&os_id=dc451556fc0eeadb&resolution=1080_1920&dpi=480&client_ip=192.168.0.198&pdunid=a83d20d8".format(hero_id) 79 | weapon_info_dict = hero_weapon(weapon_url, headers) 80 | hero_info(hero_url, headers, weapon_info_dict) -------------------------------------------------------------------------------- /美桌网图片爬虫.py: -------------------------------------------------------------------------------- 1 | import requests 2 | import re 3 | import os 4 | import time 5 | url_root = 'http://www.win4000.com/wallpaper_big_154' 6 | # http://www.win4000.com/wallpaper_big_154(3bits).html 7 | user = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36"} 8 | pattern = re.compile(r'http://pic1.win4000.com/wallpaper/[\w|-]+/[\w]+.jpg') 9 | 10 | def get_picture_url(suffix): 11 | try: 12 | url = url_root + str(suffix) + ".html" 13 | print(url) 14 | r = requests.get(url,headers = user) 15 | r.raise_for_status() 16 | validpart = r.text.split('当前位置')[-1] 17 | validpart = validpart.split('listBox')[0] 18 | picurl_list = pattern.findall(validpart) 19 | return picurl_list 20 | except: 21 | print("ERROR") 22 | return ["NULL"] 23 | 24 | def store_pic(picurl_list): 25 | 26 | if "NULL" in picurl_list: 27 | return 0 28 | file_root = "D://pics//" 29 | 30 | for picurl in picurl_list: 31 | path = file_root + picurl.split('/')[-1] 32 | try: 33 | if not os.path.exists(file_root): 34 | os.mkdir(file_root) 35 | if not os.path.exists(path): 36 | pic = requests.get(picurl) 37 | with open(path,'wb') as f: 38 | f.write(pic.content) 39 | f.close() 40 | print("图片:"+picurl+" 成功下载") 41 | else: 42 | print("图片已存在") 43 | except: 44 | print("爬取失败") 45 | return 1 46 | 47 | if __name__ == '__main__': 48 | for suffix in range(800,900): 49 | store_pic(get_picture_url(suffix)) 50 | time.sleep(5) -------------------------------------------------------------------------------- /表情包爬虫.py: -------------------------------------------------------------------------------- 1 | import os 2 | from time import time 3 | 4 | import requests 5 | from bs4 import BeautifulSoup 6 | from queue import Queue 7 | from threading import Thread 8 | 9 | 10 | class DownloadBiaoqingbao(Thread): 11 | 12 | def __init__(self, queue, path): 13 | Thread.__init__(self) 14 | self.queue = queue 15 | self.path = '/home/wistbean/biaoqingbao/' 16 | if not os.path.exists(path): 17 | os.makedirs(path) 18 | 19 | def run(self): 20 | while True: 21 | url = self.queue.get() 22 | try: 23 | # print(url) 24 | download_biaoqingbaos(url, self.path) 25 | finally: 26 | self.queue.task_done() 27 | 28 | 29 | def download_biaoqingbaos(url, path): 30 | 31 | response = requests.get(url) 32 | soup = BeautifulSoup(response.content, 'lxml') 33 | img_list = soup.find_all('img', class_='ui image lazy') 34 | 35 | for img in img_list: 36 | image = img.get('data-original') 37 | title = img.get('title') 38 | print('下载图片： ', title) 39 | 40 | try: 41 | with open(path + title + os.path.splitext(image)[-1], 'wb') as f: 42 | img = requests.get(image).content 43 | f.write(img) 44 | except OSError: 45 | print('length failed') 46 | break 47 | 48 | 49 | if __name__ == '__main__': 50 | 51 | start = time() 52 | 53 | # 构建所有的链接 54 | _url = 'https://fabiaoqing.com/biaoqing/lists/page/{page}.html' 55 | urls = [_url.format(page=page) for page in range(1, 4328+1)] 56 | 57 | queue = Queue() 58 | path = '/home/wistbean/biaoqingbao/' 59 | 60 | # 创建线程 61 | for x in range(10): 62 | worker = DownloadBiaoqingbao(queue, path) 63 | worker.daemon = True 64 | worker.start() 65 | 66 | # 加入队列 67 | for url in urls: 68 | queue.put(url) 69 | 70 | queue.join() 71 | 72 | print('下载完毕耗时： ', time()-start) -------------------------------------------------------------------------------- /豆瓣电影排名爬虫.py: -------------------------------------------------------------------------------- 1 | import requests 2 | from bs4 import BeautifulSoup 3 | import xlwt 4 | 5 | 6 | def request_douban(url): 7 | try: 8 | response = requests.get(url) 9 | if response.status_code == 200: 10 | return response.text 11 | except requests.RequestException: 12 | return None 13 | 14 | 15 | book = xlwt.Workbook(encoding='utf-8', style_compression=0) 16 | 17 | sheet = book.add_sheet('豆瓣电影Top250', cell_overwrite_ok=True) 18 | sheet.write(0, 0, '名称') 19 | sheet.write(0, 1, '图片') 20 | sheet.write(0, 2, '排名') 21 | sheet.write(0, 3, '评分') 22 | sheet.write(0, 4, '作者') 23 | sheet.write(0, 5, '简介') 24 | 25 | n = 1 26 | 27 | 28 | def save_to_excel(soup): 29 | list = soup.find(class_='grid_view').find_all('li') 30 | 31 | for item in list: 32 | item_name = item.find(class_='title').string 33 | item_img = item.find('a').find('img').get('src') 34 | item_index = item.find(class_='').string 35 | item_score = item.find(class_='rating_num').string 36 | item_author = item.find('p').text 37 | if (item.find(class_='inq') != None): 38 | item_intr = item.find(class_='inq').string 39 | 40 | # print('爬取电影：' + item_index + ' | ' + item_name +' | ' + item_img +' | ' + item_score +' | ' + item_author +' | ' + item_intr ) 41 | print('爬取电影：' + item_index + ' | ' + item_name + ' | ' + item_score + ' | ' + item_intr) 42 | 43 | global n 44 | 45 | sheet.write(n, 0, item_name) 46 | sheet.write(n, 1, item_img) 47 | sheet.write(n, 2, item_index) 48 | sheet.write(n, 3, item_score) 49 | sheet.write(n, 4, item_author) 50 | sheet.write(n, 5, item_intr) 51 | 52 | n = n + 1 53 | 54 | 55 | def main(page): 56 | url = 'https://movie.douban.com/top250?start=' + str(page * 25) + '&filter=' 57 | html = request_douban(url) 58 | soup = BeautifulSoup(html, 'lxml') 59 | save_to_excel(soup) 60 | 61 | 62 | if __name__ == '__main__': 63 | 64 | for i in range(0, 10): 65 | main(i) 66 | 67 | book.save(u'豆瓣最受欢迎的250部电影.csv') -------------------------------------------------------------------------------- /豆瓣电影爬虫（GUI界面）/main.py: -------------------------------------------------------------------------------- 1 | from DoubanMovie import uiObject 2 | 3 | # main入口 4 | if __name__ == '__main__': 5 | 6 | ui = uiObject() 7 | ui.ui_process() -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/.idea/inspectionProfiles/profiles_settings.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 6 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/.idea/misc.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/.idea/modules.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/.idea/workspace.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/.idea/链家爬虫.iml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_anting.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_anting.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_fengzhuang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_fengzhuang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_huating.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_huating.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_jiadinglaocheng.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_jiadinglaocheng.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_jiadingxincheng.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_jiadingxincheng.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_jiangqiao.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_jiangqiao.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_juyuanxinqu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_juyuanxinqu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_malu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_malu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_nanxiang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_nanxiang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_shangda.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_shangda.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_waigang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_waigang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_xinchenglu1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_xinchenglu1.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_xuxing.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/嘉定/jiading_xuxing.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/奉贤/fengxian_fengcheng.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/奉贤/fengxian_fengcheng.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/奉贤/fengxian_fengxianjinhui.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/奉贤/fengxian_fengxianjinhui.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/奉贤/fengxian_haiwan.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/奉贤/fengxian_haiwan.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/奉贤/fengxian_nanqiao.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/奉贤/fengxian_nanqiao.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/奉贤/fengxian_qingcun.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/奉贤/fengxian_qingcun.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/奉贤/fengxian_situan.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/奉贤/fengxian_situan.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/奉贤/fengxian_xidu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/奉贤/fengxian_xidu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/奉贤/fengxian_zhelin.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/奉贤/fengxian_zhelin.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/奉贤/fengxian_zhuanghang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/奉贤/fengxian_zhuanghang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_dachangzhen.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_dachangzhen.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_dahua.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_dahua.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_gongfu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_gongfu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_gongkang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_gongkang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_gucun.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_gucun.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_luodian.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_luodian.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_luojing.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_luojing.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_songbao.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_songbao.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_songnan.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_songnan.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_tonghe.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_tonghe.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_yanghang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_yanghang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_yuepu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_yuepu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_zhangmiao.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/宝山/baoshan_zhangmiao.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/上海各区小区信息汇总.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/上海各区小区信息汇总.xlsx -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/嘉定小区信息.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/嘉定小区信息.xlsx -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/奉贤小区信息.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/奉贤小区信息.xlsx -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/宝山小区信息.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/宝山小区信息.xlsx -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/崇明小区信息.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/崇明小区信息.xlsx -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/徐家汇小区信息.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/徐家汇小区信息.xlsx -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/普陀小区信息.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/普陀小区信息.xlsx -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/杨浦小区信息.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/杨浦小区信息.xlsx -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/松江小区信息.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/松江小区信息.xlsx -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/浦东小区信息.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/浦东小区信息.xlsx -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/虹口小区信息.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/虹口小区信息.xlsx -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/金山小区信息.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/金山小区信息.xlsx -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/长宁区小区信息.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/长宁区小区信息.xlsx -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/闵行小区信息.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/闵行小区信息.xlsx -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/青浦小区信息.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/青浦小区信息.xlsx -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/静安小区信息.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/静安小区信息.xlsx -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/黄埔小区信息.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/小区信息/黄埔小区信息.xlsx -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/崇明/chongming_baozhen.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/崇明/chongming_baozhen.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/崇明/chongming_changxingdao21211.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/崇明/chongming_changxingdao21211.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/崇明/chongming_chenjiazhen.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/崇明/chongming_chenjiazhen.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/崇明/chongming_chongmingqita.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/崇明/chongming_chongmingqita.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/崇明/chongming_chongmingxincheng.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/崇明/chongming_chongmingxincheng.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/崇明/chongming_hengshadao.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/崇明/chongming_hengshadao.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_caohejing.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_caohejing.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_changqiao.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_changqiao.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_hengshanlu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_hengshanlu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_huadongligong.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_huadongligong.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_huajing.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_huajing.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_jianguoxilu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_jianguoxilu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_kangjian.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_kangjian.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_longhua.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_longhua.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_shanghainanzhan.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_shanghainanzhan.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_tianlin.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_tianlin.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_wantiguan.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_wantiguan.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_xietulu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_xietulu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_xuhuibinjiang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_xuhuibinjiang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_xujiahui.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_xujiahui.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_zhiwuyuan.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/徐家汇/xuhui_zhiwuyuan.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_caoyang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_caoyang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_changfeng1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_changfeng1.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_changshoulu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_changshoulu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_changzheng.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_changzheng.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_ganquanyichuan.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_ganquanyichuan.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_guangxin.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_guangxin.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_taopu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_taopu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_wanli.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_wanli.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_wuning.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_wuning.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_zhenguang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_zhenguang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_zhenru.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_zhenru.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_zhongyuanliangwancheng.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/普陀/putuo_zhongyuanliangwancheng.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/杨浦/yangpu_anshan.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/杨浦/yangpu_anshan.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/杨浦/yangpu_dongwaitan.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/杨浦/yangpu_dongwaitan.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/杨浦/yangpu_gaojing.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/杨浦/yangpu_gaojing.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/杨浦/yangpu_huangxinggongyuan.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/杨浦/yangpu_huangxinggongyuan.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/杨浦/yangpu_kongjianglu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/杨浦/yangpu_kongjianglu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/杨浦/yangpu_wujiaochang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/杨浦/yangpu_wujiaochang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/杨浦/yangpu_xinjiangwancheng.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/杨浦/yangpu_xinjiangwancheng.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/杨浦/yangpu_zhongyuan1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/杨浦/yangpu_zhongyuan1.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/杨浦/yangpu_zhoujiazuilu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/杨浦/yangpu_zhoujiazuilu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_chedun.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_chedun.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_jiuting.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_jiuting.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_maogang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_maogang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_shenminbieshu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_shenminbieshu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_sheshan.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_sheshan.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_shihudang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_shihudang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_sijing.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_sijing.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_songjiangdaxuecheng.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_songjiangdaxuecheng.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_songjianglaocheng.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_songjianglaocheng.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_songjiangxincheng.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_songjiangxincheng.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_xiaokunshan.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_xiaokunshan.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_xinbang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_xinbang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_xinqiao.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_xinqiao.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_yexie.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/松江/songjiang_yexie.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_beicai.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_beicai.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_biyun.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_biyun.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_caolu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_caolu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_chuansha.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_chuansha.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_datuanzhen.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_datuanzhen.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_gaodong.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_gaodong.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_gaohang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_gaohang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_geqing.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_geqing.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_hangtou.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_hangtou.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_huamu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_huamu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_huinan.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_huinan.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_jinqiao.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_jinqiao.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_jinyang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_jinyang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_kangqiao.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_kangqiao.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_laogangzhen.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_laogangzhen.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_lianyang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_lianyang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_lingangxincheng.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_lingangxincheng.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_lujiazui.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_lujiazui.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_nanmatou.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_nanmatou.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_nichengzhen.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_nichengzhen.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_sanlin.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_sanlin.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_shibo.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_shibo.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_shuyuanzhen.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_shuyuanzhen.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_tangqiao.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_tangqiao.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_tangzhen.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_tangzhen.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_waigaoqiao.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_waigaoqiao.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_wanxiangzhen.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_wanxiangzhen.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_weifang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_weifang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_xinchang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_xinchang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_xuanqiao.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_xuanqiao.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_yangdong.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_yangdong.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_yangjing.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_yangjing.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_yuanshen.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_yuanshen.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_yuqiao1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_yuqiao1.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_zhangjiang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_zhangjiang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_zhoupu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_zhoupu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_zhuqiao.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/浦东/pudong_zhuqiao.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/虹口/hongkou_beiwaitan.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/虹口/hongkou_beiwaitan.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/虹口/hongkou_jiangwanzhen.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/虹口/hongkou_jiangwanzhen.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/虹口/hongkou_liangcheng.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/虹口/hongkou_liangcheng.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/虹口/hongkou_linpinglu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/虹口/hongkou_linpinglu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/虹口/hongkou_luxungongyuan.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/虹口/hongkou_luxungongyuan.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/虹口/hongkou_quyang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/虹口/hongkou_quyang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/虹口/hongkou_sichuanbeilu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/虹口/hongkou_sichuanbeilu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/金山/jinshan_caojing.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/金山/jinshan_caojing.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/金山/jinshan_fengjing.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/金山/jinshan_fengjing.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/金山/jinshan_jinshan1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/金山/jinshan_jinshan1.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/金山/jinshan_langxia.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/金山/jinshan_langxia.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/金山/jinshan_luxiang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/金山/jinshan_luxiang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/金山/jinshan_shanyang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/金山/jinshan_shanyang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/金山/jinshan_shihua.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/金山/jinshan_shihua.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/金山/jinshan_tinglin.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/金山/jinshan_tinglin.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/金山/jinshan_zhangyan.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/金山/jinshan_zhangyan.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/金山/jinshan_zhujing.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/金山/jinshan_zhujing.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/长宁/changning_beixinjing.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/长宁/changning_beixinjing.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/长宁/changning_gubei.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/长宁/changning_gubei.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/长宁/changning_hongqiao1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/长宁/changning_hongqiao1.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/长宁/changning_tianshan.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/长宁/changning_tianshan.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/长宁/changning_xianxia.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/长宁/changning_xianxia.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/长宁/changning_xijiao.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/长宁/changning_xijiao.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/长宁/changning_xinhualu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/长宁/changning_xinhualu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/长宁/changning_zhenninglu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/长宁/changning_zhenninglu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/长宁/changning_zhongshangongyuan.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/长宁/changning_zhongshangongyuan.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_chunshen.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_chunshen.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_gumei.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_gumei.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_hanghua.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_hanghua.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_huacao.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_huacao.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_jinganxincheng.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_jinganxincheng.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_jinhongqiao.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_jinhongqiao.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_jinhui.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_jinhui.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_laominhang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_laominhang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_longbai.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_longbai.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_maqiao.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_maqiao.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_meilong.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_meilong.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_pujiang1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_pujiang1.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_qibao.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_qibao.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_wujing.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_wujing.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_xinzhuang5.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_xinzhuang5.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_zhuanqiao.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/闵行/minhang_zhuanqiao.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/青浦/qingpu_baihe.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/青浦/qingpu_baihe.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/青浦/qingpu_chonggu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/青浦/qingpu_chonggu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/青浦/qingpu_huaxin.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/青浦/qingpu_huaxin.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/青浦/qingpu_jinze.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/青浦/qingpu_jinze.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/青浦/qingpu_liantang1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/青浦/qingpu_liantang1.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/青浦/qingpu_xianghuaqiao.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/青浦/qingpu_xianghuaqiao.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/青浦/qingpu_xiayang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/青浦/qingpu_xiayang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/青浦/qingpu_xujing.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/青浦/qingpu_xujing.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/青浦/qingpu_yingpu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/青浦/qingpu_yingpu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/青浦/qingpu_zhaoxiang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/青浦/qingpu_zhaoxiang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/青浦/qingpu_zhujiajiao.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/青浦/qingpu_zhujiajiao.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/静安/jingan_buyecheng.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/静安/jingan_buyecheng.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/静安/jingan_caojiadu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/静安/jingan_caojiadu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/静安/jingan_daning.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/静安/jingan_daning.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/静安/jingan_jiangninglu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/静安/jingan_jiangninglu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/静安/jingan_jingansi.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/静安/jingan_jingansi.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/静安/jingan_nanjingxilu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/静安/jingan_nanjingxilu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/静安/jingan_pengpu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/静安/jingan_pengpu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/静安/jingan_xizangbeilu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/静安/jingan_xizangbeilu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/静安/jingan_yangcheng.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/静安/jingan_yangcheng.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/静安/jingan_yonghe.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/静安/jingan_yonghe.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/静安/jingan_zhabeigongyuan.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/静安/jingan_zhabeigongyuan.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_dapuqiao.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_dapuqiao.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_dongjiadu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_dongjiadu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_huaihaizhonglu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_huaihaizhonglu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_huangpubinjiang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_huangpubinjiang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_laoximen.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_laoximen.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_nanjingdonglu.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_nanjingdonglu.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_penglaigongyuan.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_penglaigongyuan.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_renminguangchang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_renminguangchang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_shibobinjiang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_shibobinjiang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_wuliqiao.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_wuliqiao.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_xintiandi.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_xintiandi.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_yuyuan.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/20191030爬取链家上海小区信息/黄埔/huangpu_yuyuan.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/LJNew_bouse.py: -------------------------------------------------------------------------------- 1 | from bs4 import BeautifulSoup 2 | import requests 3 | import time 4 | import pandas as pd 5 | 6 | url = 'https://m.lianjia.com/nt/xiaoqu/' 7 | headers = {'Referer': url, 8 | 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:69.0) Gecko/20100101 Firefox/69.0', 9 | 'Cookie': 'lianjia_uuid=443bb6e3-b556-47ea-967d-5444ea915dc6; Hm_lvt_9152f8221cb6243a53c83b956842be8a=1571809948,1572075513,1572091757,1572092040; _smt_uid=5dafea9d.5470d44f; UM_distinctid=16df72c7718be-086f464eb904c-4c312373-144000-16df72c7719794; _jzqa=1.3017324979856383500.1571809949.1572094819.1572175751.7; _jzqy=1.1571809949.1572091757.1.jzqsr=baidu|jzqct=%E9%93%BE%E5%AE%B6.-; sensorsdata2015jssdkcross=%7B%22distinct_id%22%3A%2216df72c7a34233-04d3d7bf7d75b18-4c312373-1327104-16df72c7a35214%22%2C%22%24device_id%22%3A%2216df72c7a34233-04d3d7bf7d75b18-4c312373-1327104-16df72c7a35214%22%2C%22props%22%3A%7B%22%24latest_traffic_source_type%22%3A%22%E7%9B%B4%E6%8E%A5%E6%B5%81%E9%87%8F%22%2C%22%24latest_referrer%22%3A%22%22%2C%22%24latest_referrer_host%22%3A%22%22%2C%22%24latest_search_keyword%22%3A%22%E6%9C%AA%E5%8F%96%E5%88%B0%E5%80%BC_%E7%9B%B4%E6%8E%A5%E6%89%93%E5%BC%80%22%2C%22%24latest_utm_source%22%3A%22baidu%22%2C%22%24latest_utm_medium%22%3A%22pinzhuan%22%2C%22%24latest_utm_campaign%22%3A%22sousuo%22%2C%22%24latest_utm_content%22%3A%22biaotimiaoshu%22%2C%22%24latest_utm_term%22%3A%22biaoti%22%7D%7D; _ga=GA1.2.1379447899.1571809952; _jzqx=1.1571814886.1572175751.4.jzqsr=sh%2Elianjia%2Ecom|jzqct=/ershoufang/pg100/.jzqsr=nt%2Elianjia%2Ecom|jzqct=/xiaoqu/8745128002049017/; select_city=320600; Hm_lpvt_9152f8221cb6243a53c83b956842be8a=1572177857; _jzqc=1; _gid=GA1.2.487758797.1572075516; srcid=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; CNZZDATA1254525948=1706170696-1572075705-%7C1572172951; CNZZDATA1253491255=1450175482-1572074448-%7C1572172565; lianjia_ssid=91c55eb0-d2cf-7ad8-de18-58a73ecf6aab; _jzqckmp=1'} 10 | page = ('pg') 11 | 12 | # return demjson.encode(res) 13 | 14 | 15 | 16 | 17 | def areainfo(url): 18 | page = ('pg') 19 | for i in range(1, 31): # 获取1-100页的数据 20 | if i == 1: 21 | i = str(i) 22 | a = (url + page + i + '/') 23 | r = requests.get(url=a, headers=headers) 24 | print(a) 25 | htmlinfo = r.content 26 | else: 27 | i = str(i) 28 | a = (url + page + i + '/') 29 | print(a) 30 | r = requests.get(url=a, headers=headers) 31 | html2 = r.content 32 | htmlinfo = htmlinfo + html2 33 | time.sleep(0.5) 34 | return htmlinfo 35 | 36 | 37 | hlist = [] 38 | 39 | 40 | def listinfo(listhtml): 41 | areasoup = BeautifulSoup(listhtml, 'html.parser') 42 | ljhouse = areasoup.find_all('a', attrs={'class': 'pictext'}) 43 | 44 | for house in ljhouse: 45 | loupantitle = house.find("div", attrs={"class": "xiaoqu_head_title lazyload_ulog"}) 46 | loupanname = loupantitle.a.get_text() 47 | # loupantag = loupantitle.find_all("span") 48 | # wuye = loupantag[0].get_text() 49 | # xiaoshouzhuangtai = loupantag[1].get_text() 50 | location = house.find("div", attrs={"class": "xiaoqu_head_address"}).get_text() 51 | a = house.find("div", attrs={"class": "mod_box jichuxinxi"}) 52 | niandai=a.find("div", attrs={"class": "mod_cont"})[0].get_text() 53 | leixing=a.find("div", attrs={"class": "mod_cont"})[1].get_text() 54 | loudongshu=a.find("div", attrs={"class": "mod_cont"})[2].get_text() 55 | fangwushu=a.find("div", attrs={"class": "mod_cont"})[1].get_text() 56 | # price = house.find("div", attrs={"class": "main-price"}).get_text() 57 | # total = jiage.find("div", attrs={"class": "second"}) 58 | # totalprice = "暂无" 59 | # if total is not None: 60 | # totalprice = total.get_text() 61 | h = {'title': loupanname, 'location': location.replace("\n", ""), 62 | 'niandai': niandai.replace("\n", ""), 'leixing': leixing, 'loudongshu': loudongshu, 'fangwushu': fangwushu}; 63 | hlist.append(h) 64 | 65 | 66 | if __name__ == '__main__': 67 | url = url 68 | hlist.append( 69 | {'title': "楼盘名称", 'location': "位置", 70 | 'niandai': "建筑年代", 'leixing': "房屋类型", 'loudongshu': "楼栋数", 71 | 'fangwushu': "房屋数"}) 72 | areahtml = areainfo(url) 73 | listinfo(areahtml) 74 | # houseinfo = houseinfo.append(hlist) 75 | houseinfo = pd.DataFrame(hlist) 76 | houseinfo.to_csv('链家新房.csv', index=False, encoding="utf_8_sig") 77 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/LJershoufang.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/LJershoufang.xlsx -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/LJershoufang/output_5_0.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/LJershoufang/output_5_0.png -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/LJershoufang/output_5_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/LJershoufang/output_5_2.png -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/LJershoufang/output_5_3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/LJershoufang/output_5_3.png -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/LJershoufang/output_5_4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/LJershoufang/output_5_4.png -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/LJershoufang/output_5_5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/LJershoufang/output_5_5.png -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/LJershoufang/output_5_6.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/LJershoufang/output_5_6.png -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/LJershoufang/output_5_7.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/LJershoufang/output_5_7.png -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/LJershoufang/链家二手房数据分析.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/LJershoufang/链家二手房数据分析.pdf -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/LJsecond_house/output_5_0.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/LJsecond_house/output_5_0.png -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/LJsecond_house/output_5_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/LJsecond_house/output_5_2.png -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/LJsecond_house/output_5_3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/LJsecond_house/output_5_3.png -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/LJsecond_house/output_5_4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/LJsecond_house/output_5_4.png -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/LJsecond_house/output_5_5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/LJsecond_house/output_5_5.png -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/LJsecond_house/output_5_6.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/LJsecond_house/output_5_6.png -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/LJsecond_house/output_5_7.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/LJsecond_house/output_5_7.png -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/LJsecond_house/链家二手房数据分析.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/LJsecond_house/链家二手房数据分析.pdf -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/LJzufang.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/LJzufang.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/LJzufang.py: -------------------------------------------------------------------------------- 1 | import requests 2 | import csv 3 | import random 4 | import time 5 | import socket 6 | import http.client 7 | from bs4 import BeautifulSoup 8 | import re 9 | 10 | 11 | def get_content(url, data=None): 12 | header = { 13 | 'Accept': 'application/json, text/javascript, */*; q=0.01', 14 | 'Accept-Encoding': 'gzip, deflate, br', 15 | 'Accept-Language': 'zh-CN,zh;q=0.9', 16 | 'Connection': 'keep-alive', 17 | 'Cookie': 'lianjia_uuid=8290c333-59db-490c-8808-8b2645f848c6; lianjia_ssid=55ca6233-79ad-4e5a-b366-831c546fe02e; srcid=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', 18 | 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36' 19 | } 20 | timeout = random.choice(range(80, 180)) 21 | while True: 22 | try: 23 | req = requests.get(url, headers=header, timeout=timeout) 24 | req.encoding = 'utf-8' 25 | break 26 | 27 | except socket.timeout as e: 28 | print('3:', e) 29 | time.sleep(random.choice(range(8, 15))) 30 | 31 | except socket.error as e: 32 | print('4:', e) 33 | time.sleep(random.choice(range(20, 60))) 34 | 35 | except http.client.BadStatusLine as e: 36 | print('5:', e) 37 | time.sleep(random.choice(range(30, 80))) 38 | 39 | except http.client.IncompleteRead as e: 40 | print('6:', e) 41 | time.sleep(random.choice(range(5, 15))) 42 | return req.text 43 | 44 | 45 | def get_data(html_text): 46 | final = [] 47 | bs = BeautifulSoup(html_text, "html.parser") 48 | body = bs.body 49 | data = body.find('div', {'id': 'content'}).find('div', {'class': 'content__article'}) 50 | total = data.find('p', {'class': 'content__title'}).find('span', {'class': 'content__title--hl'}).string 51 | items = data.find('div', {'class': 'content__list'}).find_all('div', {'class': 'content__list--item'}) 52 | 53 | for item in items: 54 | temp = [] 55 | title = item.find('p', {'class': 'twoline'}).find('a').string 56 | price = str(item.find('span', {'class': 'content__list--item-price'}).text) 57 | infostr = str(item.find('p', {'class': 'content__list--item--des'}).text) 58 | try: 59 | type = str(item.find('p', {'class': 'content__list--item--brand'}).text) 60 | except: 61 | type = '' 62 | time = str(item.find('p', {'class': 'content__list--item--time'}).text) 63 | tag = str(item.find('p', {'class': 'content__list--item--bottom'}).text) 64 | title = re.sub(r'[\[\]\s]', '', title) 65 | infostr = re.sub(r'\s', '', infostr) 66 | info = infostr.split('/') 67 | type = re.sub(r'\s', '', type) 68 | tag = re.sub(r'\s', '', tag) 69 | address = info[0] 70 | size = info[1] 71 | fangxiang = info[2] 72 | format = info[3] 73 | # floor = info[4] 74 | temp.append(title) 75 | temp.append(price) 76 | temp.append(address) 77 | temp.append(size) 78 | temp.append(fangxiang) 79 | temp.append(format) 80 | # temp.append(floor) 81 | temp.append(type) 82 | temp.append(time) 83 | temp.append(tag) 84 | final.append(temp) 85 | return final 86 | 87 | 88 | def write_data(data, name): 89 | file_name = name 90 | 91 | with open(file_name, 'a', errors='ignore', newline='') as f: 92 | f_csv = csv.writer(f) 93 | f_csv.writerows([['title', 'price', 'address', 'size', 'fangxiang', 'format', 'type', 'time', 'tag']]) 94 | f_csv.writerows(data) 95 | 96 | 97 | if __name__ == '__main__': 98 | url = 'https://sh.lianjia.com/zufang/' 99 | # https://sh.lianjia.com/zufang/pujiang1/pg2rt200600000001l0/ 100 | result = [] 101 | for i in range(0, 99): 102 | html = get_content(url) 103 | d = get_data(html) 104 | result.extend(d) 105 | url = 'https://sh.lianjia.com/zufang/pg' + str(i+1) + '/#contentList' 106 | 107 | write_data(result, 'LJzufang.csv') -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/lianjiasecond_house.py: -------------------------------------------------------------------------------- 1 | import os 2 | import pandas as pd 3 | from selenium import webdriver 4 | from pyquery import PyQuery as pq 5 | driver = webdriver.Chrome() 6 | 7 | 8 | ''' 9 | 步骤： 10 | 1. 下载页面 11 | 2. 解析页面 12 | 3. 保存数据 13 | ''' 14 | 15 | 16 | def cached_url(url): 17 | """ 18 | 缓存网页, 避免重复下载浪费时间 19 | """ 20 | folder = 'cached' 21 | filename = url.split('/')[-2][2:] + '.html' # 以页面数命名 html 页面 22 | path = os.path.join(folder, filename) 23 | if os.path.exists(path): 24 | with open(path, 'rb') as f: 25 | s = f.read() 26 | return s 27 | else: 28 | if not os.path.exists(folder): 29 | # 建立 cached 文件夹 30 | os.makedirs(folder) 31 | 32 | driver.get(url) # 使用 Selenium 爬取页面 33 | with open(path, 'wb') as f: 34 | f.write(driver.page_source.encode()) 35 | return driver.page_source 36 | 37 | 38 | def house_from_div(div): 39 | """ 40 | 从一个 div 里面获取到一个二手房信息 41 | """ 42 | e = pq(div) 43 | 44 | # 小作用域变量用单字符 45 | m = {} 46 | m['name'] = e('.houseInfo').text() # 二手房名字 47 | m['price'] = e('.totalPrice').text() # 二手房总价 48 | m['unitprice'] = e('.unitPrice').text() # 二手房每平米单价 49 | m['position'] = e('.positionInfo').text() # 二手房位置 50 | m['follow'] = e('.followInfo').text() # 二手房关注信息 51 | m['url'] = e('a').attr('href') # 二手房页面链接 52 | 53 | return m 54 | 55 | 56 | def houses_from_url(url): 57 | """ 58 | 从 url 中下载网页并解析出页面内所有的房源 59 | """ 60 | # 页面只需要下载一次 61 | page = cached_url(url) 62 | e = pq(page) 63 | items = e('.info.clear') # 解析的class为info clear, 中间有空格, 使用“.info.clear” 64 | # 调用 house_from_div 65 | houses = [house_from_div(i) for i in items] 66 | return houses 67 | 68 | 69 | def append_to_csv(data): 70 | ''' 71 | 保存数据 72 | ''' 73 | file_name = './新房数据.csv' 74 | df = pd.DataFrame(data) 75 | df.to_csv(file_name, mode='a', encoding='gbk', header=False, index=False) 76 | 77 | 78 | def main(): 79 | for i in range(1, 101): 80 | # 一共 100 页房源信息 81 | url = 'https://sh.fang.lianjia.com/loupan/pg{}/'.format(i) 82 | houses = houses_from_url(url) 83 | print(houses) 84 | append_to_csv(houses) 85 | 86 | 87 | if __name__ == '__main__': 88 | main() -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/.gitignore: -------------------------------------------------------------------------------- 1 | *.pyc 2 | .idea/ 3 | data/ 4 | *.html 5 | *.csv 6 | log/log.txt 7 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/README.md: -------------------------------------------------------------------------------- 1 | # 链家网(lianjia.com)和贝壳网(ke.com)爬虫 2 | - 爬取链家网、贝壳网的各类房价数据（小区数据，挂牌二手房, 出租房，新房）。 3 | - **如果好用，请点星支持 ！** 4 | - 支持北京上海广州深圳等国内21个主要城市；支持Python2和Python3; 基于页面的数据爬取，稳定可靠; 丰富的代码注释，帮助理解代码并且方便扩展功能。 5 | - 数据含义：城市-city, 区县-district, 板块-area, 小区-xiaoqu, 二手房-ershou, 租房-zufang， 新房-loupan。 6 | - 每个版块存储为一个csv文件，该文件可以作为原始数据进行进一步的处理和分析。 7 | - 支持图表展示。 8 | ![alt text](https://github.com/jumper2014/lianjia-spider/blob/master/pic/xiaoqu_top.png) 9 | ![alt text](https://github.com/jumper2014/lianjia-spider/blob/master/pic/district_top.png) 10 | - 如果链家和贝壳页面结构有调整，欢迎反馈，我将尽力保持更新。 11 | - 此代码仅供学习与交流，请勿用于商业用途，后果自负。 12 | 13 | ## 安装依赖 14 | - pip install -r requirements.txt 15 | - 运行前，请将当前目录加入到系统环境变量PYTHONPATH中。 16 | - 运行前，请指定要爬取的网站，见lib/spider/base_spider.py里面的SPIDER_NAME变量。 17 | - 清理数据，运行 python tool/clean.py 18 | 19 | ## 快速问答 20 | - Q: 如何降低爬取速度，避免被封IP？A:见base_spider.py里面的RANDOM_DELAY 21 | - Q: 如何减少并发的爬虫数？ A: 见见base_spider.py的thread_pool_size 22 | - Q: 为何无法使用xiaoqu_to_chart.py? A: 该脚本现仅支持mac系统 23 | - Q: 有其他问题反馈途径么？ A: 问题反馈QQ群号635276285。 24 | 25 | ## 小区房价数据爬取 26 | - 内容格式：采集日期,所属区县,板块名,小区名,挂牌均价,挂牌数 27 | - 内容如下：20180221,浦东,川沙,恒纬家苑,32176元/m2,3套在售二手房 28 | - 数据可以存入MySQL/MongoDB数据库，用于进一步数据分析，比如排序，计算区县和版块均价。 29 | - MySQL数据库结构可以通过导入tool/lianjia_xiaoqu.sql建立。 30 | - MySQL数据格式: 城市 日期 所属区县 版块名 小区名 挂牌均价 挂牌数 31 | - MySQL数据内容：上海 20180331 徐汇 衡山路 永嘉路621号 333333 0 32 | - MongoDB数据内容: { "_id" : ObjectId("5ac0309332e3885598b3b751"), "city" : "上海", "district" : "黄浦", "area" : "五里桥", "date" : "20180331", "price" : 81805, "sale" : 11, "xiaoqu" : "桥一小区" } 33 | - Excel数据内容：上海 20180331 徐汇 衡山路 永嘉路621号 333333 0 34 | - 运行, python xiaoqu.py 根据提示输入城市代码，回车确认，开始采集数据到csv文件 35 | - 运行, python xiaoqu.py city, 自动开始采集数据到csv文件 36 | ``` 37 | hz: 杭州, sz: 深圳, dl: 大连, fs: 佛山 38 | xm: 厦门, dg: 东莞, gz: 广州, bj: 北京 39 | cd: 成都, sy: 沈阳, jn: 济南, sh: 上海 40 | tj: 天津, qd: 青岛, cs: 长沙, su: 苏州 41 | cq: 重庆, wh: 武汉, hf: 合肥, yt: 烟台 42 | nj: 南京, 43 | ``` 44 | - 修改 xiaoqu_to_db.py 中的database变量，设置数据最终存入mysql/mongodb/Excel/json 45 | - python xiaoqu_to_db.py 根据提示将今天采集到的csv数据存入数据库。(默认导出为单一csv文件) 46 | - python xiaoqu_to_chart.py 将单一csv文件数据通过图表展示。 47 | 48 | ## 挂牌二手房数据爬取 49 | - 获取链家网挂牌二手房价数据，数据格式如下： 50 | - 20180405,浦东,万祥镇,祥安菊苑 3室2厅 258万,258万,祥安菊苑 | 3室2厅 | 126.58平米 | 南 | 毛坯 51 | - 运行，python ershou.py 根据提示输入城市代码，回车确认，开始采集数据到csv文件 52 | - 运行，python ershou.py city，自动开始采集数据到csv文件 53 | 54 | 55 | ## 出租房数据爬取 56 | - 获取链家网挂牌出租房数据，数据格式如下： 57 | - 20180407,浦东,御桥,仁和都市花园  ,3室2厅,100平米,8000 58 | - 运行，python zufang.py 根据提示输入城市代码，回车确认，开始采集数据到csv文件 59 | - 运行，python zufang.py city，自动开始采集数据到csv文件 60 | 61 | ## 新房数据爬取 62 | - 获取链家网新房数据，数据格式如下： 63 | - 20180407,上海星河湾,76000,1672万 64 | - 运行，python loupan.py 根据提示输入城市代码，回车确认，开始采集数据到csv文件 65 | - 运行，python loupan.py city，自动开始采集数据到csv文件 66 | 67 | ## 结果存储 68 | - 根目录下建立data目录存放结果数据文件 69 | - 小区房价数据存储目录为 data/site/xiaoqu/city/date 70 | - 二手房房价数据存储目录为 data/site/ershou/city/date 71 | - 出租房房价数据存储目录为 data/site/zufang/city/date 72 | - 新房房价数据存储目录为 data/site/loupan/city/date 73 | 74 | ## 性能 75 | - 300秒爬取上海市207个版块的2.7万条小区数据，平均每秒90条数据。 76 | ``` 77 | Total crawl 207 areas. 78 | Total cost 294.048109055 second to crawl 27256 data items. 79 | ``` 80 | - 1000秒爬取上海215个版块的7.5万条挂牌二手房数据，平均每秒75条数据。 81 | ``` 82 | Total crawl 215 areas. 83 | Total cost 1028.3090899 second to crawl 75448 data items. 84 | ``` 85 | - 300秒爬取上海215个版块的3.2万条出租房数据, 平均每秒150条数据。 86 | ``` 87 | Total crawl 215 areas. 88 | Total cost 299.7534770965576 second to crawl 32735 data items. 89 | ``` 90 | - 30秒爬取上海400个新盘数据。 91 | ``` 92 | Total crawl 400 loupan. 93 | Total cost 29.757128953933716 second 94 | ``` 95 | 96 | 97 | 98 | ### 更新记录 99 | - 2019/06/21 去除requirements.txt中的webbrower 100 | - 2018/11/05 增加工具下载二手房缩略图tool/download_ershou_image.py 101 | - 2018/11/01 增加二手房缩略图地址 102 | - 2018/10/28 xiaoqu_to_db.py改造成支持命令行参数自动运行。 103 | - 2018/10/25 将主要爬取代码抽取到spider类中。 104 | - 2018/10/22 文件名，目录，代码重构。 105 | - 2018/10/20 增加中间文件清理功能，能够爬取贝壳网的小区，新房，二手房和租房数据。 106 | - 2018/10/19 支持贝壳网小区数据爬取 107 | - 2018/10/15 增加Spider类，优化异常处理，功能无变动 108 | - 2018/10/14 允许用户通过命令行指定要爬取的城市，而不仅仅通过交互模式选择，用于支持自动爬取。 109 | - 2018/10/11 增加初步log功能。 110 | - 2018/10/09 图表展示区县均价排名。 111 | - 2018/10/07 小区房价导出到json文件, csv文件。图表展示最贵的小区。 112 | - 2018/10/05 增加Referer。增加透明代理服务器获取(未使用) 113 | - 2018/06/01 支持User-Agent 114 | - 2018/04/07 支持采集新房的基本房价信息 115 | - 2018/04/07 支持采集出租房的相关信息 116 | - 2018/04/05 支持采集挂牌二手房信息 117 | - 2018/04/02 支持将采集到的csv数据导入Excel 118 | - 2018/04/01 同时支持Python2和Python3 119 | - 2018/04/01 支持将采集到的csv数据导入MongoDB数据库 120 | - 2018/03/31 支持将采集到的csv数据导入MySQL数据库 121 | - 2018/03/27 修复bug: 版块下只有一页小区数据时未能正确爬取 122 | - 2018/03/27 增加5个城市，现在支持21个城市的小区数据爬取 123 | - 2018/03/10 自动获取城市的区县列表，现在支持16个城市小区数据爬取 124 | - 2018/03/06 支持北京二手房小区数据采集 125 | - 2018/02/21 应对链家前端页面更新，使用内置urllib2代替第三方requests库,提升性能，减少依赖 126 | - 2018/02/01 支持上海二手房小区数据采集 -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/lib/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/lib/__init__.py -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/lib/const/__init__.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | # -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/lib/const/xpath.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: zengyuetian 4 | # 此代码仅供学习与交流，请勿用于商业用途。 5 | # 页面元素的XPATH 6 | 7 | from lib.spider.base_spider import SPIDER_NAME, LIANJIA_SPIDER, BEIKE_SPIDER 8 | 9 | if SPIDER_NAME == LIANJIA_SPIDER: 10 | ERSHOUFANG_QU_XPATH = '//*[@id="filter-options"]/dl[1]/dd/div/a' 11 | ERSHOUFANG_BANKUAI_XPATH = '//*[@id="filter-options"]/dl[1]/dd/div[2]/a' 12 | XIAOQU_QU_XPATH = '//*[@id="filter-options"]/dl[1]/dd/div/a' 13 | XIAOQU_BANKUAI_XPATH = '//*[@id="filter-options"]/dl[1]/dd/div[2]/a' 14 | DISTRICT_AREA_XPATH = '//div[3]/div[1]/dl[2]/dd/div/div[2]/a' 15 | CITY_DISTRICT_XPATH = '///div[3]/div[1]/dl[2]/dd/div/div/a' 16 | elif SPIDER_NAME == BEIKE_SPIDER: 17 | ERSHOUFANG_QU_XPATH = '//*[@id="filter-options"]/dl[1]/dd/div/a' 18 | ERSHOUFANG_BANKUAI_XPATH = '//*[@id="filter-options"]/dl[1]/dd/div[2]/a' 19 | XIAOQU_QU_XPATH = '//*[@id="filter-options"]/dl[1]/dd/div/a' 20 | XIAOQU_BANKUAI_XPATH = '//*[@id="filter-options"]/dl[1]/dd/div[2]/a' 21 | DISTRICT_AREA_XPATH = '//div[3]/div[1]/dl[2]/dd/div/div[2]/a' 22 | CITY_DISTRICT_XPATH = '///div[3]/div[1]/dl[2]/dd/div/div/a' 23 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/lib/item/__init__.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: zengyuetian 4 | 5 | 6 | if __name__ == '__main__': 7 | pass -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/lib/item/xiaoqu.py: -------------------------------------------------------------------------------- 1 | 2 | 3 | class XiaoQu(object): 4 | def __init__(self, district, area, name, price, on_sale, link,niandai,leixing,wuyefei,wuyegs,kaifashang,loushu,wushu): 5 | self.district = district 6 | self.area = area 7 | self.price = price 8 | self.name = name 9 | self.on_sale = on_sale 10 | self.link=link 11 | self.niandai=niandai 12 | self.leixing=leixing 13 | self.wuyefei=wuyefei 14 | self.loushu=loushu 15 | self.wushu=wushu 16 | 17 | def text(self): 18 | return self.district + "," + \ 19 | self.area + "," + \ 20 | self.name + "," + \ 21 | self.price + "," + \ 22 | self.on_sale + "," + \ 23 | self.link + "," + \ 24 | self.niandai + "," + \ 25 | self.leixing + "," + \ 26 | self.wuyefei + "," + \ 27 | self.loushu + "," + \ 28 | self.wushu -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/lib/request/__init__.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: zengyuetian 4 | 5 | 6 | if __name__ == '__main__': 7 | pass -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/lib/request/headers.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: zengyuetian 4 | # 此代码仅供学习与交流，请勿用于商业用途。 5 | # USER AGENTS 可以自己添加 6 | 7 | import random 8 | from lib.spider.base_spider import SPIDER_NAME 9 | 10 | USER_AGENTS = [ 11 | "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)", 12 | "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)", 13 | "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)", 14 | "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)", 15 | "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)", 16 | "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)", 17 | "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)", 18 | "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)", 19 | "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6", 20 | "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1", 21 | "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0", 22 | "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5", 23 | "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6", 24 | "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11", 25 | "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20", 26 | "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52", 27 | ] 28 | 29 | 30 | def create_headers(): 31 | headers = dict() 32 | headers["User-Agent"] = random.choice(USER_AGENTS) 33 | headers["Referer"] = "http://www.{0}.com".format(SPIDER_NAME) 34 | return headers 35 | 36 | 37 | if __name__ == '__main__': 38 | pass 39 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/lib/request/proxy.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: zengyuetian 4 | # 此代码仅供学习与交流，请勿用于商业用途。 5 | # 用于获取代理 6 | 7 | from bs4 import BeautifulSoup 8 | import requests 9 | from lib.request.headers import create_headers 10 | 11 | proxys_src = [] 12 | proxys = [] 13 | 14 | 15 | def spider_proxyip(num=10): 16 | try: 17 | url = 'http://www.xicidaili.com/nt/1' 18 | req = requests.get(url, headers=create_headers()) 19 | source_code = req.content 20 | print(source_code) 21 | soup = BeautifulSoup(source_code, 'lxml') 22 | ips = soup.findAll('tr') 23 | 24 | for x in range(1, len(ips)): 25 | ip = ips[x] 26 | tds = ip.findAll("td") 27 | proxy_host = "{0}://".format(tds[5].contents[0]) + tds[1].contents[0] + ":" + tds[2].contents[0] 28 | proxy_temp = {tds[5].contents[0]: proxy_host} 29 | proxys_src.append(proxy_temp) 30 | if x >= num: 31 | break 32 | except Exception as e: 33 | print("spider_proxyip exception:") 34 | print(e) 35 | 36 | 37 | if __name__ == '__main__': 38 | spider_proxyip(10) 39 | print(proxys_src) 40 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/lib/spider/__init__.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | # -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/lib/spider/base_spider.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: zengyuetian 4 | # 此代码仅供学习与交流，请勿用于商业用途。 5 | # 爬虫基类 6 | # 爬虫名常量，用来设置爬取哪个站点 7 | 8 | import threading 9 | from lib.zone.city import lianjia_cities, beike_cities 10 | from lib.utility.date import * 11 | import lib.utility.version 12 | import random 13 | 14 | thread_pool_size = 50 15 | 16 | # 防止爬虫被禁，随机延迟设定 17 | # 如果不想delay，就设定False， 18 | # 具体时间可以修改random_delay()，由于多线程，建议数值大于10 19 | RANDOM_DELAY = False 20 | LIANJIA_SPIDER = "lianjia" 21 | BEIKE_SPIDER = "lianjia" 22 | SPIDER_NAME = LIANJIA_SPIDER 23 | #SPIDER_NAME = BEIKE_SPIDER 24 | 25 | 26 | class BaseSpider(object): 27 | @staticmethod 28 | def random_delay(): 29 | if RANDOM_DELAY: 30 | time.sleep(random.randint(0, 16)) 31 | 32 | def __init__(self, name): 33 | self.name = name 34 | if self.name == LIANJIA_SPIDER: 35 | self.cities = lianjia_cities 36 | elif self.name == BEIKE_SPIDER: 37 | self.cities = beike_cities 38 | else: 39 | self.cities = None 40 | # 准备日期信息，爬到的数据存放到日期相关文件夹下 41 | self.date_string = get_date_string() 42 | print('Today date is: %s' % self.date_string) 43 | 44 | self.total_num = 0 # 总的小区个数，用于统计 45 | print("Target site is {0}.com".format(SPIDER_NAME)) 46 | self.mutex = threading.Lock() # 创建锁 47 | 48 | def create_prompt_text(self): 49 | """ 50 | 根据已有城市中英文对照表拼接选择提示信息 51 | :return: 拼接好的字串 52 | """ 53 | city_info = list() 54 | count = 0 55 | for en_name, ch_name in self.cities.items(): 56 | count += 1 57 | city_info.append(en_name) 58 | city_info.append(": ") 59 | city_info.append(ch_name) 60 | # if count % 4 == 0: 61 | # city_info.append("\n") 62 | # else: 63 | # city_info.append(", ") 64 | return 'Which city do you want to crawl?\n' + ''.join(city_info) 65 | 66 | def get_chinese_city(self, en): 67 | """ 68 | 拼音拼音名转中文城市名 69 | :param en: 拼音 70 | :return: 中文 71 | """ 72 | return self.cities.get(en, None) 73 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/lib/utility/__init__.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | # -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/lib/utility/date.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: zengyuetian 4 | # 此代码仅供学习与交流，请勿用于商业用途。 5 | # 日期和时间的字符串辅助函数 6 | 7 | import time 8 | 9 | 10 | def get_time_string(): 11 | """ 12 | 获得形如20161010120000这样的年月日时分秒字符串 13 | :return: 14 | """ 15 | current = time.localtime() 16 | return time.strftime("%Y%m%d%H%M%S", current) 17 | 18 | 19 | def get_date_string(): 20 | """ 21 | 获得形如20161010这样的年月日字符串 22 | :return: 23 | """ 24 | current = time.localtime() 25 | return time.strftime("%Y%m%d", current) 26 | 27 | 28 | def get_year_month_string(): 29 | """ 30 | 获得形如201610这样的年月字符串 31 | :return: 32 | """ 33 | current = time.localtime() 34 | return time.strftime("%Y%m", current) 35 | 36 | 37 | if __name__ == "__main__": 38 | print(get_date_string()) 39 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/lib/utility/log.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: zengyuetian 4 | # 此代码仅供学习与交流，请勿用于商业用途。 5 | 6 | import logging 7 | from lib.utility.path import LOG_PATH 8 | 9 | logger = logging.getLogger(__name__) 10 | logger.setLevel(level=logging.INFO) 11 | handler = logging.FileHandler(LOG_PATH + "/log.txt") 12 | handler.setLevel(logging.INFO) 13 | formatter = logging.Formatter('%(asctime)s - %(levelname)s - %(message)s') 14 | handler.setFormatter(formatter) 15 | logger.addHandler(handler) 16 | 17 | if __name__ == '__main__': 18 | pass -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/lib/utility/path.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: zengyuetian 4 | # 此代码仅供学习与交流，请勿用于商业用途。 5 | # 获得当前目录结构,创建目录结构 6 | 7 | 8 | import inspect 9 | import os 10 | import sys 11 | 12 | 13 | def get_root_path(): 14 | file_path = os.path.abspath(inspect.getfile(sys.modules[__name__])) 15 | parent_path = os.path.dirname(file_path) 16 | lib_path = os.path.dirname(parent_path) 17 | root_path = os.path.dirname(lib_path) 18 | return root_path 19 | 20 | 21 | def create_data_path(): 22 | root_path = get_root_path() 23 | data_path = root_path + "/data" 24 | if not os.path.exists(data_path): 25 | os.makedirs(data_path) 26 | return data_path 27 | 28 | 29 | def create_site_path(site): 30 | data_path = create_data_path() 31 | site_path = data_path + "/" + site 32 | if not os.path.exists(site_path): 33 | os.makedirs(site_path) 34 | return site_path 35 | 36 | 37 | def create_city_path(site, city): 38 | site_path = create_site_path(site) 39 | city_path = site_path + "/" + city 40 | if not os.path.exists(city_path): 41 | os.makedirs(city_path) 42 | return city_path 43 | 44 | 45 | def create_date_path(site, city, date): 46 | city_path = create_city_path(site, city) 47 | date_path = city_path + "/" + date 48 | if not os.path.exists(date_path): 49 | os.makedirs(date_path) 50 | return date_path 51 | 52 | 53 | # const for path 54 | ROOT_PATH = get_root_path() 55 | DATA_PATH = ROOT_PATH + "/data" 56 | SAMPLE_PATH = ROOT_PATH + "/sample" 57 | LOG_PATH = ROOT_PATH + "/log" 58 | 59 | if __name__ == "__main__": 60 | create_date_path() 61 | create_date_path() 62 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/lib/utility/version.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: zengyuetian 4 | # 此代码仅供学习与交流，请勿用于商业用途。 5 | # 判断Python版本环境 6 | 7 | 8 | import sys 9 | 10 | if sys.version_info < (3, 0): # 如果小于Python3 11 | PYTHON_3 = False 12 | else: 13 | PYTHON_3 = True 14 | 15 | if not PYTHON_3: # 如果小于Python3 16 | reload(sys) 17 | sys.setdefaultencoding("utf-8") 18 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/lib/utility/writer.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: zengyuetian 4 | # 此代码仅供学习与交流，请勿用于商业用途。 5 | # 保存结果到文件 6 | 7 | from lib.utility.path import * 8 | 9 | 10 | def write_urls_to_file(file_name, urls): 11 | file_name = DATA_PATH + "/" + file_name 12 | txt_file = open(file_name, 'w') 13 | for url in urls: 14 | txt_file.write(url+"\n") 15 | txt_file.close() 16 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/lib/zone/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/lib/zone/__init__.py -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/lib/zone/area.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: zengyuetian 4 | # 此代码仅供学习与交流，请勿用于商业用途。 5 | # 板块信息相关函数 6 | 7 | from lib.zone.district import * 8 | from lib.const.xpath import * 9 | from lib.request.headers import * 10 | from lib.spider.base_spider import SPIDER_NAME 11 | 12 | 13 | def get_district_url(city, district): 14 | """ 15 | 拼接指定城市的区县url 16 | :param city: 城市 17 | :param district: 区县 18 | :return: 19 | """ 20 | return "http://{0}.{1}.com/xiaoqu/{2}".format(city, SPIDER_NAME, district) 21 | 22 | 23 | def get_areas(city, district): 24 | """ 25 | 通过城市和区县名获得下级板块名 26 | :param city: 城市 27 | :param district: 区县 28 | :return: 区县列表 29 | """ 30 | page = get_district_url(city, district) 31 | areas = list() 32 | try: 33 | headers = create_headers() 34 | response = requests.get(page, timeout=10, headers=headers) 35 | html = response.content 36 | root = etree.HTML(html) 37 | links = root.xpath(DISTRICT_AREA_XPATH) 38 | 39 | # 针对a标签的list进行处理 40 | for link in links: 41 | relative_link = link.attrib['href'] 42 | # 去掉最后的"/" 43 | relative_link = relative_link[:-1] 44 | # 获取最后一节 45 | area = relative_link.split("/")[-1] 46 | # 去掉区县名,防止重复 47 | if area != district: 48 | chinese_area = link.text 49 | chinese_area_dict[area] = chinese_area 50 | # print(chinese_area) 51 | areas.append(area) 52 | return areas 53 | except Exception as e: 54 | print(e) 55 | 56 | 57 | if __name__ == "__main__": 58 | print(get_areas("sh", "huangpu")) 59 | 60 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/lib/zone/city.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: zengyuetian 4 | # 此代码仅供学习与交流，请勿用于商业用途。 5 | # 城市缩写和城市名的映射 6 | # 想抓取其他已有城市的话，需要把相关城市信息放入下面的字典中 7 | # 不过暂时只有下面这些城市在链家上是统一样式 8 | 9 | import sys 10 | from lib.utility.version import PYTHON_3 11 | from lib.utility.log import * 12 | 13 | cities = { 14 | 'bj': '北京', 15 | 'cd': '成都', 16 | 'cq': '重庆', 17 | 'cs': '长沙', 18 | 'dg': '东莞', 19 | 'dl': '大连', 20 | 'fs': '佛山', 21 | 'gz': '广州', 22 | 'hz': '杭州', 23 | 'hf': '合肥', 24 | 'jn': '济南', 25 | 'nj': '南京', 26 | 'qd': '青岛', 27 | 'sh': '上海', 28 | 'sz': '深圳', 29 | 'su': '苏州', 30 | 'sy': '沈阳', 31 | 'tj': '天津', 32 | 'wh': '武汉', 33 | 'xm': '厦门', 34 | 'yt': '烟台', 35 | } 36 | 37 | 38 | lianjia_cities = cities 39 | beike_cities = cities 40 | 41 | 42 | def create_prompt_text(): 43 | """ 44 | 根据已有城市中英文对照表拼接选择提示信息 45 | :return: 拼接好的字串 46 | """ 47 | city_info = list() 48 | count = 0 49 | for en_name, ch_name in cities.items(): 50 | count += 1 51 | city_info.append(en_name) 52 | city_info.append(": ") 53 | city_info.append(ch_name) 54 | if count % 4 == 0: 55 | city_info.append("\n") 56 | else: 57 | city_info.append(", ") 58 | return 'Which city do you want to crawl?\n' + ''.join(city_info) 59 | 60 | 61 | def get_chinese_city(en): 62 | """ 63 | 拼音拼音名转中文城市名 64 | :param en: 拼音 65 | :return: 中文 66 | """ 67 | return cities.get(en, None) 68 | 69 | 70 | def get_city(): 71 | city = None 72 | # 允许用户通过命令直接指定 73 | if len(sys.argv) < 2: 74 | print("Wait for your choice.") 75 | # 让用户选择爬取哪个城市的二手房小区价格数据 76 | prompt = create_prompt_text() 77 | # 判断Python版本 78 | if not PYTHON_3: # 如果小于Python3 79 | city = raw_input(prompt) 80 | else: 81 | city = input(prompt) 82 | elif len(sys.argv) == 2: 83 | city = str(sys.argv[1]) 84 | print("City is: {0}".format(city)) 85 | else: 86 | print("At most accept one parameter.") 87 | exit(1) 88 | 89 | chinese_city = get_chinese_city(city) 90 | if chinese_city is not None: 91 | message = 'OK, start to crawl ' + get_chinese_city(city) 92 | print(message) 93 | logger.info(message) 94 | else: 95 | print("No such city, please check your input.") 96 | exit(1) 97 | return city 98 | 99 | 100 | if __name__ == '__main__': 101 | print(get_chinese_city("sh")) 102 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/lib/zone/district.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: zengyuetian 4 | # 此代码仅供学习与交流，请勿用于商业用途。 5 | # 获得各城市的区县相关信息 6 | 7 | import requests 8 | from lxml import etree 9 | from lib.zone.city import cities 10 | from lib.const.xpath import * 11 | from lib.request.headers import * 12 | from lib.spider.base_spider import SPIDER_NAME 13 | 14 | chinese_city_district_dict = dict() # 城市代码和中文名映射 15 | chinese_area_dict = dict() # 版块代码和中文名映射 16 | area_dict = dict() 17 | 18 | 19 | def get_chinese_district(en): 20 | """ 21 | 拼音区县名转中文区县名 22 | :param en: 英文 23 | :return: 中文 24 | """ 25 | return chinese_city_district_dict.get(en, None) 26 | 27 | 28 | def get_districts(city): 29 | """ 30 | 获取各城市的区县中英文对照信息 31 | :param city: 城市 32 | :return: 英文区县名列表 33 | """ 34 | url = 'https://{0}.{1}.com/xiaoqu/'.format(city, SPIDER_NAME) 35 | headers = create_headers() 36 | response = requests.get(url, timeout=10, headers=headers) 37 | html = response.content 38 | root = etree.HTML(html) 39 | elements = root.xpath(CITY_DISTRICT_XPATH) 40 | en_names = list() 41 | ch_names = list() 42 | for element in elements: 43 | link = element.attrib['href'] 44 | en_names.append(link.split('/')[-2]) 45 | ch_names.append(element.text) 46 | 47 | # 打印区县英文和中文名列表 48 | for index, name in enumerate(en_names): 49 | chinese_city_district_dict[name] = ch_names[index] 50 | # print(name + ' -> ' + ch_names[index]) 51 | return en_names 52 | 53 | 54 | if __name__ == '__main__': 55 | for key in cities.keys(): 56 | # 寻找那些网页格式不合规的城市 57 | chinese_city_district_dict = dict() 58 | get_districts(key) 59 | if len(chinese_city_district_dict.items()) == 0: 60 | print(key) 61 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/log/__init__.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: zengyuetian 4 | # 此代码仅供学习与交流，请勿用于商业用途。 5 | 6 | 7 | if __name__ == '__main__': 8 | pass -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/pic/district_top.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/pic/district_top.png -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/pic/xiaoqu_top.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/pic/xiaoqu_top.png -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/requirements.txt: -------------------------------------------------------------------------------- 1 | threadpool 2 | bs4 3 | pymysql 4 | requests 5 | lxml 6 | records 7 | pymongo 8 | xlsxwriter 9 | numpy 10 | pandas 11 | pyecharts 12 | pyecharts-snapshot -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/test/date_test.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: zengyuetian 4 | # 此代码仅供学习与交流，请勿用于商业用途。 5 | 6 | import unittest 7 | from lib.utility.date import * 8 | 9 | 10 | class DateTest(unittest.TestCase): 11 | def setUp(self): 12 | pass 13 | 14 | def tearDown(self): 15 | pass 16 | 17 | def test_time_string(self): 18 | self.assertEqual(len(get_time_string()), 14) 19 | 20 | def test_date_string(self): 21 | self.assertEqual(len(get_date_string()), 8) 22 | 23 | def test_year_string(self): 24 | self.assertEqual(len(get_year_month_string()), 6) 25 | 26 | 27 | if __name__ == '__main__': 28 | unittest.main() 29 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/tool/clean.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: zengyuetian 4 | # 此代码仅供学习与交流，请勿用于商业用途。 5 | # 清理结果文件 6 | 7 | from lib.utility.path import * 8 | 9 | if __name__ == '__main__': 10 | # 删除日志 11 | os.system("rm -rf {0}/*.txt".format(LOG_PATH)) 12 | 13 | # 删除爬取的数据 14 | os.system("rm -rf {0}/*".format(DATA_PATH)) 15 | 16 | # 删除HTML 17 | os.system("rm -rf {0}/*.html".format(ROOT_PATH)) 18 | 19 | # 删除csv 20 | os.system("rm -rf {0}/*.csv".format(ROOT_PATH)) 21 | 22 | # 删除json 23 | os.system("rm -rf {0}/*.json".format(ROOT_PATH)) -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/tool/ershou_image_with_coroutine.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: zengyuetian 4 | # 此代码仅供学习与交流，请勿用于商业用途。 5 | # 协程下载图片，仅支持Python 3.6.1 6 | 7 | 8 | 9 | import aiohttp 10 | import aiofiles 11 | import asyncio 12 | import os 13 | import time 14 | from lib.zone.city import get_chinese_city 15 | from lib.request.headers import create_headers 16 | from lib.utility.date import get_date_string 17 | from lib.spider.base_spider import SPIDER_NAME 18 | from lib.utility.path import DATA_PATH 19 | 20 | 21 | def get_ershou_img_urls(city): 22 | urls = list() 23 | date = get_date_string() 24 | # 获得 csv 文件路径 25 | # date = "20180331" # 指定采集数据的日期 26 | # city = "sh" # 指定采集数据的城市 27 | csv_dir = "{0}/{1}/ershou/{2}/{3}".format(DATA_PATH, SPIDER_NAME, city, date) 28 | 29 | files = list() 30 | if not os.path.exists(csv_dir): 31 | print("{0} does not exist.".format(csv_dir)) 32 | print("Please run 'python ershou.py' firstly.") 33 | print("Bye.") 34 | exit(0) 35 | else: 36 | print('OK, start to process ' + get_chinese_city(city)) 37 | for csv in os.listdir(csv_dir): 38 | if csv[-3:] != "csv": 39 | continue 40 | data_csv = csv_dir + "/" + csv 41 | # print(data_csv) 42 | files.append(data_csv) 43 | 44 | # 清理数据 45 | count = 0 46 | for csv in files: 47 | with open(csv, 'r') as f: 48 | for line in f: 49 | count += 1 50 | text = line.strip() 51 | try: 52 | results = text.split("https://") 53 | except Exception as e: 54 | print(text) 55 | print(e) 56 | continue 57 | # 确保之前的步骤采集到了图片的url 58 | if len(results) > 1: 59 | url = results[-1] 60 | urls.append("https://"+url) 61 | print("https://"+url) 62 | print(len(urls)) 63 | return urls 64 | 65 | 66 | async def download_images(save_path: str, image_url: str): 67 | """ 68 | :param save_path: 保存图片的路径 69 | :param image_url: 图片的下载的url地址 70 | :return: 71 | """ 72 | async with aiohttp.ClientSession() as session: 73 | async with session.get(image_url, headers=create_headers()) as req: 74 | image = await req.read() 75 | fp = await aiofiles.open(save_path, 'wb') 76 | await fp.write(image) 77 | 78 | if __name__ == '__main__': 79 | # urls = ["https://img.ljcdn.com/370600-inspection/test-9925c97c-fc99-4d1a-97fa-2fd6d3209027.png!m_fill,w_280,h_210,f_jpg?from=ke.com", 80 | # "https://img.ljcdn.com/370600-inspection/df98f65c-427e-4d7d-91a7-425a5d682af5.jpg!m_fill,w_280,h_210,f_jpg?from=ke.com", 81 | # "https://img.ljcdn.com/370600-inspection/test-9925c97c-fc99-4d1a-97fa-2fd6d3209027.png!m_fill,w_280,h_210,f_jpg?from=ke.com", 82 | # "https://img.ljcdn.com/370600-inspection/df98f65c-427e-4d7d-91a7-425a5d682af5.jpg!m_fill,w_280,h_210,f_jpg?from=ke.com"] 83 | # 指定城市 84 | start = time.time() 85 | city = "yt" 86 | urls = get_ershou_img_urls(city) 87 | loop = asyncio.get_event_loop() 88 | date = get_date_string() 89 | csv_dir = "{0}/{1}/ershou/{2}/{3}".format(DATA_PATH, SPIDER_NAME, city, date) 90 | to_do = [download_images("{0}/{1}.jpg".format(csv_dir, i), urls[i]) for i in range(len(urls))] 91 | print("Start to download, please wait.") 92 | wait_future = asyncio.wait(to_do) 93 | resp = loop.run_until_complete(wait_future) 94 | loop.close() 95 | print("Download {0} images, cost {1} seconds.".format(len(urls), time.time() - start)) 96 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/tool/ershou_image_with_threads.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: zengyuetian 4 | # 此代码仅供学习与交流，请勿用于商业用途。 5 | # 多线程下载图片，Python 3.6.1 6 | 7 | 8 | import os 9 | import time 10 | from lib.zone.city import get_chinese_city 11 | from lib.request.headers import create_headers 12 | from lib.utility.date import get_date_string 13 | from lib.spider.base_spider import SPIDER_NAME 14 | from lib.utility.path import DATA_PATH 15 | from tomorrow import threads 16 | import requests 17 | 18 | 19 | def get_ershou_img_urls(city): 20 | urls = list() 21 | date = get_date_string() 22 | # 获得 csv 文件路径 23 | # date = "20180331" # 指定采集数据的日期 24 | # city = "sh" # 指定采集数据的城市 25 | csv_dir = "{0}/{1}/ershou/{2}/{3}".format(DATA_PATH, SPIDER_NAME, city, date) 26 | 27 | files = list() 28 | if not os.path.exists(csv_dir): 29 | print("{0} does not exist.".format(csv_dir)) 30 | print("Please run 'python ershou.py' firstly.") 31 | print("Bye.") 32 | exit(0) 33 | else: 34 | print('OK, start to process ' + get_chinese_city(city)) 35 | for csv in os.listdir(csv_dir): 36 | if csv[-3:] != "csv": 37 | continue 38 | data_csv = csv_dir + "/" + csv 39 | # print(data_csv) 40 | files.append(data_csv) 41 | 42 | # 清理数据 43 | count = 0 44 | for csv in files: 45 | with open(csv, 'r') as f: 46 | for line in f: 47 | count += 1 48 | text = line.strip() 49 | try: 50 | results = text.split("https://") 51 | except Exception as e: 52 | print(text) 53 | print(e) 54 | continue 55 | # 确保之前的步骤采集到了图片的url 56 | if len(results) > 1: 57 | url = results[-1] 58 | urls.append("https://"+url) 59 | print("https://"+url) 60 | print(len(urls)) 61 | return urls 62 | 63 | 64 | @threads(50) 65 | def download_images(save_path: str, image_url: str): 66 | """ 67 | :param save_path: 保存图片的路径 68 | :param image_url: 图片的下载的url地址 69 | :return: 70 | """ 71 | resp = requests.get(image_url) 72 | fp = open(save_path, 'wb') 73 | fp.write(resp.content) 74 | fp.close() 75 | 76 | if __name__ == '__main__': 77 | # urls = ["https://img.ljcdn.com/370600-inspection/test-9925c97c-fc99-4d1a-97fa-2fd6d3209027.png!m_fill,w_280,h_210,f_jpg?from=ke.com", 78 | # "https://img.ljcdn.com/370600-inspection/df98f65c-427e-4d7d-91a7-425a5d682af5.jpg!m_fill,w_280,h_210,f_jpg?from=ke.com", 79 | # "https://img.ljcdn.com/370600-inspection/test-9925c97c-fc99-4d1a-97fa-2fd6d3209027.png!m_fill,w_280,h_210,f_jpg?from=ke.com", 80 | # "https://img.ljcdn.com/370600-inspection/df98f65c-427e-4d7d-91a7-425a5d682af5.jpg!m_fill,w_280,h_210,f_jpg?from=ke.com"] 81 | # 指定城市 82 | start = time.time() 83 | city = "yt" 84 | urls = get_ershou_img_urls(city) 85 | 86 | date = get_date_string() 87 | csv_dir = "{0}/{1}/ershou/{2}/{3}".format(DATA_PATH, SPIDER_NAME, city, date) 88 | to_do = [download_images("{0}/{1}.jpg".format(csv_dir, i), urls[i]) for i in range(len(urls))] 89 | print("Start to download, please wait...") 90 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/tool/ershou_number.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: zengyuetian 4 | # 此代码仅供学习与交流，请勿用于商业用途。 5 | # 获取城市挂牌二手房数量 6 | 7 | import time 8 | from lib.spider.base_spider import SPIDER_NAME 9 | from bs4 import BeautifulSoup 10 | from lib.zone.city import cities 11 | import requests 12 | 13 | numbers = dict() 14 | 15 | 16 | def get_ershou_number(city): 17 | url = "https://{0}.{1}.com/ershoufang/".format(city, SPIDER_NAME) 18 | print(url) 19 | response = requests.get(url) 20 | html = response.content 21 | soup = BeautifulSoup(html, "lxml") 22 | element = soup.find('h2', class_='total') 23 | number = int(element.text.split(" ")[1].strip()) 24 | numbers[city] = number 25 | 26 | 27 | if __name__ == '__main__': 28 | start = time.time() 29 | for key, value in cities.items(): 30 | # print(key, value) 31 | get_ershou_number(key) 32 | for k, v in numbers.items(): 33 | print(cities[k], v) 34 | print("cost {0} seconds".format(time.time() - start)) 35 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/tool/lianjia_xiaoqu.sql: -------------------------------------------------------------------------------- 1 | # ************************************************************ 2 | # Sequel Pro SQL dump 3 | # Version 4541 4 | # 5 | # http://www.sequelpro.com/ 6 | # https://github.com/sequelpro/sequelpro 7 | # 8 | # Host: 127.0.0.1 (MySQL 5.7.21) 9 | # Database: lianjia 10 | # Generation Time: 2018-03-31 12:54:33 +0000 11 | # ************************************************************ 12 | 13 | 14 | /*!40101 SET @OLD_CHARACTER_SET_CLIENT=@@CHARACTER_SET_CLIENT */; 15 | /*!40101 SET @OLD_CHARACTER_SET_RESULTS=@@CHARACTER_SET_RESULTS */; 16 | /*!40101 SET @OLD_COLLATION_CONNECTION=@@COLLATION_CONNECTION */; 17 | /*!40101 SET NAMES utf8 */; 18 | /*!40014 SET @OLD_FOREIGN_KEY_CHECKS=@@FOREIGN_KEY_CHECKS, FOREIGN_KEY_CHECKS=0 */; 19 | /*!40101 SET @OLD_SQL_MODE=@@SQL_MODE, SQL_MODE='NO_AUTO_VALUE_ON_ZERO' */; 20 | /*!40111 SET @OLD_SQL_NOTES=@@SQL_NOTES, SQL_NOTES=0 */; 21 | 22 | 23 | # Dump of table xiaoqu 24 | # ------------------------------------------------------------ 25 | 26 | DROP TABLE IF EXISTS `xiaoqu`; 27 | 28 | CREATE TABLE `xiaoqu` ( 29 | `id` int(11) unsigned NOT NULL AUTO_INCREMENT, 30 | `city` varchar(10) DEFAULT NULL, 31 | `date` varchar(8) DEFAULT NULL, 32 | `district` varchar(50) DEFAULT NULL, 33 | `area` varchar(50) DEFAULT NULL, 34 | `xiaoqu` varchar(100) DEFAULT NULL, 35 | `price` int(11) DEFAULT NULL, 36 | `sale` int(11) DEFAULT NULL, 37 | PRIMARY KEY (`id`) 38 | ) ENGINE=InnoDB DEFAULT CHARSET=utf8; 39 | 40 | 41 | 42 | 43 | /*!40111 SET SQL_NOTES=@OLD_SQL_NOTES */; 44 | /*!40101 SET SQL_MODE=@OLD_SQL_MODE */; 45 | /*!40014 SET FOREIGN_KEY_CHECKS=@OLD_FOREIGN_KEY_CHECKS */; 46 | /*!40101 SET CHARACTER_SET_CLIENT=@OLD_CHARACTER_SET_CLIENT */; 47 | /*!40101 SET CHARACTER_SET_RESULTS=@OLD_CHARACTER_SET_RESULTS */; 48 | /*!40101 SET COLLATION_CONNECTION=@OLD_COLLATION_CONNECTION */; 49 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/xiaoqu.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: Zeng YueTian 4 | # 此代码仅供学习与交流，请勿用于商业用途。 5 | # 获得指定城市的小区数据 6 | # 这些数据包括: 7 | # 日期,所属区县,板块名,小区名,挂牌均价,挂牌数 8 | # 20180221,浦东,川沙,恒纬家苑,32176元/m2,3套在售二手房 9 | 10 | from lib.spider.xiaoqu_spider import * 11 | 12 | if __name__ == "__main__": 13 | spider = XiaoQuBaseSpider(SPIDER_NAME) 14 | spider.start() 15 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/上海小区爬虫最终版/xiaoqu_to_chart.py: -------------------------------------------------------------------------------- 1 | 2 | 3 | import pandas as pd 4 | from pyecharts import Bar 5 | 6 | import os 7 | import time 8 | from lib.utility.version import PYTHON_3 9 | 10 | if __name__ == '__main__': 11 | try: 12 | import webbrowser as web 13 | auto_browse = True 14 | except Exception as e: 15 | auto_browse = False 16 | 17 | if auto_browse: 18 | try: 19 | if PYTHON_3: 20 | os.system("ps aux | grep python | grep http.server | grep -v grep | awk '{print $2}' | xargs kill") 21 | os.system("python -m http.server 8080 & > /dev/null 2>&1 ") 22 | else: 23 | os.system("ps aux | grep python | grep SimpleHTTPServer | grep -v grep | awk '{print $2}' | xargs kill") 24 | os.system("python -m SimpleHTTPServer 8080 & > /dev/null 2>&1 ") 25 | except Exception as e: 26 | print(e) 27 | 28 | # 注意，已经将分割符号转换成分号，因为有的小区名中有逗号 29 | df = pd.read_csv("xiaoqu.csv", encoding="utf-8", sep=";") 30 | 31 | # 打印总行数 32 | print("row number is {0}".format(len(df.index))) 33 | 34 | # 过滤房价为0的无效数据 35 | df = df[df.price > 0] 36 | # # 去除重复行 37 | # df = df.drop_duplicates() 38 | print("row number is {0}".format(len(df.index))) 39 | 40 | #################################################### 41 | # 最贵的小区排名 42 | #################################################### 43 | df.sort_values("price", ascending=False, inplace=True) 44 | num = 5 45 | print(df.head(num)) 46 | city = df["city_ch"][0] 47 | xqs = df["xiaoqu"][0:num] 48 | prices = df["price"][0:num] 49 | bar = Bar("{0}小区均价".format(city)) 50 | bar.add("小区均价前{0}名".format(num), xqs, prices, is_stack=True, is_label_show=True, xaxis_interval=0, xaxis_rotate=45) 51 | bar.render(path="xiaoqu.html") 52 | 53 | #################################################### 54 | # 区县均价排名 55 | #################################################### 56 | district_df = df.groupby('district').mean() 57 | district_df = district_df.round(0) 58 | district_df.sort_values("price", ascending=False, inplace=True) 59 | print(district_df) 60 | districts = district_df.index.tolist() 61 | prices = district_df["price"] 62 | bar = Bar("{0}区县均价".format(city)) 63 | bar.add("区县均价排名", districts, prices, is_stack=True, is_label_show=True, xaxis_interval=0, xaxis_rotate=45) 64 | bar.render(path="district.html") 65 | 66 | if auto_browse: 67 | web.open("http://localhost:8080/xiaoqu.html", new=0, autoraise=True) 68 | web.open("http://localhost:8080/district.html", new=0, autoraise=True) 69 | # 确保页面打开 70 | time.sleep(15) 71 | 72 | 73 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/小区/LJxiaoquHB.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # coding: utf-8 3 | import pandas as pd 4 | import numpy as np 5 | data1=pd.read_csv('housedata1.csv',encoding='gbk') 6 | data2=pd.read_csv('housedata2.csv',encoding='gbk') 7 | data=pd.concat([data1,data2],axis=0,ignore_index=False) 8 | data=pd.DataFrame(data) 9 | # data=str(data).encode('gbk') 10 | data=data.sort_values('area') 11 | data=data.reset_index() 12 | data=data.drop(labels='index',axis=1) 13 | # print(data.head()) 14 | print(data.loc[:,'area'].value_counts()) 15 | # for i,data['price'][i] in enumerate(data['price']): 16 | # data['price'][i]=int(data['price'][i].replace('元/平','')) 17 | #print(i,data['price'][i]) 18 | # print('changed_price\n',data['price'].head()) 19 | # print(data.head()) 20 | 21 | # print(type(data['price'][0]) 22 | data.to_csv('cleaned.csv', mode='a', encoding='gbk', header=False, index=False) 23 | 24 | # print(data.loc[:,'area'].value_counts()) 25 | # print(data.describe()) 26 | 27 | # area=data.groupby(by='area')['price'].mean() 28 | 29 | #print(data.loc[:,'price'].mean()) 30 | #area=data.groupby(by='area')['price'] 31 | # print(area) -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/小区/上海链家小区信息（第1线程）.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/小区/上海链家小区信息（第1线程）.csv -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/小区/上海链家小区信息（第1线程）.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/小区/上海链家小区信息（第1线程）.xlsx -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/小区/上海链家小区信息（第2线程）.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/小区/上海链家小区信息（第2线程）.xlsx -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/链家二手房.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/链家二手房.xlsx -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/链家二手房数据整理.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/链家二手房数据整理.xlsx -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/链家新房.csv: -------------------------------------------------------------------------------- 1 | title,location,niandai,leixing,loudongshu,fangwushu 2 | 楼盘名称,位置,建筑年代,房屋类型,楼栋数,房屋数 3 | -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/链家新房.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/链家新房.xlsx -------------------------------------------------------------------------------- /链家爬虫（含二手房、新房、租房、小区等爬虫）/链家租房.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuzuoping/PythonSpyder_100_examples/1e137b396321b2643521582c2a761dc3fb3b025a/链家爬虫（含二手房、新房、租房、小区等爬虫）/链家租房.xlsx --------------------------------------------------------------------------------