├── lib ├── __init__.py ├── zone │ ├── __init__.py │ ├── area.py │ ├── district.py │ └── city.py ├── const │ ├── __init__.py │ └── xpath.py ├── spider │ ├── __init__.py │ ├── base_spider.py │ ├── loupan_spider.py │ ├── xiaoqu_spider.py │ ├── ershou_spider.py │ └── zufang_spider.py ├── utility │ ├── __init__.py │ ├── version.py │ ├── writer.py │ ├── log.py │ ├── date.py │ └── path.py ├── item │ ├── __init__.py │ ├── loupan.py │ ├── xiaoqu.py │ ├── ershou.py │ └── zufang.py └── request │ ├── __init__.py │ ├── proxy.py │ └── headers.py ├── .gitignore ├── pic ├── xiaoqu_top.png └── district_top.png ├── log └── __init__.py ├── requirements.txt ├── ershou.py ├── loupan.py ├── zufang.py ├── xiaoqu.py ├── tool ├── clean.py ├── ershou_number.py ├── lianjia_xiaoqu.sql ├── ershou_image_with_threads.py └── ershou_image_with_coroutine.py ├── test └── date_test.py ├── xiaoqu_to_chart.py ├── README.md ├── xiaoqu_to_db.py └── LICENSE /lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /lib/zone/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /lib/const/__init__.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | # -------------------------------------------------------------------------------- /lib/spider/__init__.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | # -------------------------------------------------------------------------------- /lib/utility/__init__.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | # -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | *.pyc 2 | .idea/ 3 | data/ 4 | *.html 5 | *.csv 6 | log/log.txt 7 | -------------------------------------------------------------------------------- /pic/xiaoqu_top.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Crush0nyou/beike-lianjia/HEAD/pic/xiaoqu_top.png -------------------------------------------------------------------------------- /pic/district_top.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Crush0nyou/beike-lianjia/HEAD/pic/district_top.png -------------------------------------------------------------------------------- /lib/item/__init__.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: zengyuetian 4 | 5 | 6 | if __name__ == '__main__': 7 | pass -------------------------------------------------------------------------------- /lib/request/__init__.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: zengyuetian 4 | 5 | 6 | if __name__ == '__main__': 7 | pass -------------------------------------------------------------------------------- /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 -------------------------------------------------------------------------------- /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 13 | -------------------------------------------------------------------------------- /ershou.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 | # 获得指定城市的二手房数据 6 | 7 | from lib.spider.ershou_spider import * 8 | 9 | if __name__ == "__main__": 10 | spider = ErShouSpider(SPIDER_NAME) 11 | spider.start() 12 | 13 | -------------------------------------------------------------------------------- /loupan.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 | # 获得指定城市的所有新房楼盘数据 6 | 7 | from lib.spider.loupan_spider import * 8 | 9 | if __name__ == "__main__": 10 | spider = LouPanBaseSpider(SPIDER_NAME) 11 | spider.start() 12 | 13 | -------------------------------------------------------------------------------- /zufang.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 | # 获得指定城市的出租房数据 6 | 7 | 8 | from lib.spider.zufang_spider import * 9 | 10 | if __name__ == "__main__": 11 | spider = ZuFangBaseSpider(SPIDER_NAME) 12 | spider.start() 13 | 14 | -------------------------------------------------------------------------------- /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 | -------------------------------------------------------------------------------- /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 | -------------------------------------------------------------------------------- /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 | -------------------------------------------------------------------------------- /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 -------------------------------------------------------------------------------- /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)) -------------------------------------------------------------------------------- /lib/item/loupan.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 | # 新房楼盘的数据结构 6 | 7 | 8 | class LouPan(object): 9 | def __init__(self, xiaoqu, price, total): 10 | # self.district = district 11 | # self.area = area 12 | self.xiaoqu = xiaoqu 13 | # self.address = address 14 | # self.size = size 15 | self.price = price 16 | self.total = total 17 | 18 | def text(self): 19 | return self.xiaoqu + "," + \ 20 | self.price + "," + \ 21 | self.total 22 | -------------------------------------------------------------------------------- /lib/item/xiaoqu.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 | # 小区信息的数据结构 6 | 7 | 8 | class XiaoQu(object): 9 | def __init__(self, district, area, name, price, on_sale): 10 | self.district = district 11 | self.area = area 12 | self.price = price 13 | self.name = name 14 | self.on_sale = on_sale 15 | 16 | def text(self): 17 | return self.district + "," + \ 18 | self.area + "," + \ 19 | self.name + "," + \ 20 | self.price + "," + \ 21 | self.on_sale 22 | -------------------------------------------------------------------------------- /lib/item/ershou.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 | # 二手房信息的数据结构 6 | 7 | 8 | class ErShou(object): 9 | def __init__(self, district, area, name, price, desc, pic): 10 | self.district = district 11 | self.area = area 12 | self.price = price 13 | self.name = name 14 | self.desc = desc 15 | self.pic = pic 16 | 17 | def text(self): 18 | return self.district + "," + \ 19 | self.area + "," + \ 20 | self.name + "," + \ 21 | self.price + "," + \ 22 | self.desc + "," + \ 23 | self.pic 24 | -------------------------------------------------------------------------------- /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 | -------------------------------------------------------------------------------- /lib/item/zufang.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 | # 二手房信息的数据结构 6 | 7 | 8 | class ZuFang(object): 9 | def __init__(self, district, area, xiaoqu, layout, size, price): 10 | self.district = district 11 | self.area = area 12 | self.xiaoqu = xiaoqu 13 | self.layout = layout 14 | self.size = size 15 | self.price = price 16 | 17 | def text(self): 18 | return self.district + "," + \ 19 | self.area + "," + \ 20 | self.xiaoqu + "," + \ 21 | self.layout + "," + \ 22 | self.size + "," + \ 23 | self.price 24 | -------------------------------------------------------------------------------- /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 | -------------------------------------------------------------------------------- /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 | -------------------------------------------------------------------------------- /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 | -------------------------------------------------------------------------------- /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 | -------------------------------------------------------------------------------- /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 | -------------------------------------------------------------------------------- /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("lianjia", "sh", "20160912") 61 | create_date_path("anjuke", "bj", "20160912") 62 | -------------------------------------------------------------------------------- /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 | -------------------------------------------------------------------------------- /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 | -------------------------------------------------------------------------------- /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 = "ke" 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 | -------------------------------------------------------------------------------- /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 | -------------------------------------------------------------------------------- /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 | -------------------------------------------------------------------------------- /xiaoqu_to_chart.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding=utf-8 3 | # author: zengyuetian 4 | # 展示小区图表信息（仅仅支持MAC） 5 | # 1. 杀死之前启动的http服务器 6 | # 2. 启动一个新的http服务器 7 | # 3. 用浏览器打开生成的数据html文件 8 | 9 | import pandas as pd 10 | from pyecharts import Bar 11 | 12 | import os 13 | import time 14 | from lib.utility.version import PYTHON_3 15 | 16 | if __name__ == '__main__': 17 | try: 18 | import webbrowser as web 19 | auto_browse = True 20 | except Exception as e: 21 | auto_browse = False 22 | 23 | if auto_browse: 24 | try: 25 | if PYTHON_3: 26 | os.system("ps aux | grep python | grep http.server | grep -v grep | awk '{print $2}' | xargs kill") 27 | os.system("python -m http.server 8080 & > /dev/null 2>&1 ") 28 | else: 29 | os.system("ps aux | grep python | grep SimpleHTTPServer | grep -v grep | awk '{print $2}' | xargs kill") 30 | os.system("python -m SimpleHTTPServer 8080 & > /dev/null 2>&1 ") 31 | except Exception as e: 32 | print(e) 33 | 34 | # 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 35 | df = pd.read_csv("xiaoqu.csv", encoding="utf-8", sep=";") 36 | 37 | # 打印总行数 38 | print("row number is {0}".format(len(df.index))) 39 | 40 | # 过滤房价为0的无效数据 41 | df = df[df.price > 0] 42 | # # 去除重复行 43 | # df = df.drop_duplicates() 44 | print("row number is {0}".format(len(df.index))) 45 | 46 | #################################################### 47 | # 最贵的小区排名 48 | #################################################### 49 | df.sort_values("price", ascending=False, inplace=True) 50 | num = 5 51 | print(df.head(num)) 52 | city = df["city_ch"][0] 53 | xqs = df["xiaoqu"][0:num] 54 | prices = df["price"][0:num] 55 | bar = Bar("{0}小区均价".format(city)) 56 | 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) 57 | bar.render(path="xiaoqu.html") 58 | 59 | #################################################### 60 | # 区县均价排名 61 | #################################################### 62 | district_df = df.groupby('district').mean() 63 | district_df = district_df.round(0) 64 | district_df.sort_values("price", ascending=False, inplace=True) 65 | print(district_df) 66 | districts = district_df.index.tolist() 67 | prices = district_df["price"] 68 | bar = Bar("{0}区县均价".format(city)) 69 | bar.add("区县均价排名", districts, prices, is_stack=True, is_label_show=True, xaxis_interval=0, xaxis_rotate=45) 70 | bar.render(path="district.html") 71 | 72 | if auto_browse: 73 | web.open("http://localhost:8080/xiaoqu.html", new=0, autoraise=True) 74 | web.open("http://localhost:8080/district.html", new=0, autoraise=True) 75 | # 确保页面打开 76 | time.sleep(15) 77 | 78 | 79 | -------------------------------------------------------------------------------- /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 | -------------------------------------------------------------------------------- /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 | -------------------------------------------------------------------------------- /lib/spider/loupan_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 | # 爬取楼盘数据的爬虫派生类 6 | 7 | import re 8 | import math 9 | import requests 10 | from bs4 import BeautifulSoup 11 | from lib.item.loupan import * 12 | from lib.spider.base_spider import * 13 | from lib.request.headers import * 14 | from lib.utility.date import * 15 | from lib.utility.path import * 16 | from lib.zone.city import get_city 17 | from lib.utility.log import * 18 | import lib.utility.version 19 | 20 | 21 | class LouPanBaseSpider(BaseSpider): 22 | def collect_city_loupan_data(self, city_name, fmt="csv"): 23 | """ 24 | 将指定城市的新房楼盘数据存储下来，默认存为csv文件 25 | :param city_name: 城市 26 | :param fmt: 保存文件格式 27 | :return: None 28 | """ 29 | csv_file = self.today_path + "/{0}.csv".format(city_name) 30 | with open(csv_file, "w") as f: 31 | # 开始获得需要的板块数据 32 | loupans = self.get_loupan_info(city_name) 33 | self.total_num = len(loupans) 34 | if fmt == "csv": 35 | for loupan in loupans: 36 | f.write(self.date_string + "," + loupan.text() + "\n") 37 | print("Finish crawl: " + city_name + ", save data to : " + csv_file) 38 | 39 | @staticmethod 40 | def get_loupan_info(city_name): 41 | """ 42 | 爬取页面获取城市新房楼盘信息 43 | :param city_name: 城市 44 | :return: 新房楼盘信息列表 45 | """ 46 | total_page = 1 47 | loupan_list = list() 48 | page = 'http://{0}.fang.{1}.com/loupan/'.format(city_name, SPIDER_NAME) 49 | print(page) 50 | headers = create_headers() 51 | response = requests.get(page, timeout=10, headers=headers) 52 | html = response.content 53 | soup = BeautifulSoup(html, "lxml") 54 | 55 | # 获得总的页数 56 | try: 57 | page_box = soup.find_all('div', class_='page-box')[0] 58 | matches = re.search('.*data-total-count="(\d+)".*', str(page_box)) 59 | total_page = int(math.ceil(int(matches.group(1)) / 10)) 60 | except Exception as e: 61 | print("\tWarning: only find one page for {0}".format(city_name)) 62 | print(e) 63 | 64 | print(total_page) 65 | # 从第一页开始,一直遍历到最后一页 66 | headers = create_headers() 67 | for i in range(1, total_page + 1): 68 | page = 'http://{0}.fang.{1}.com/loupan/pg{2}'.format(city_name, SPIDER_NAME, i) 69 | print(page) 70 | BaseSpider.random_delay() 71 | response = requests.get(page, timeout=10, headers=headers) 72 | html = response.content 73 | soup = BeautifulSoup(html, "lxml") 74 | 75 | # 获得有小区信息的panel 76 | house_elements = soup.find_all('li', class_="resblock-list") 77 | for house_elem in house_elements: 78 | price = house_elem.find('span', class_="number") 79 | total = house_elem.find('div', class_="second") 80 | loupan = house_elem.find('a', class_='name') 81 | 82 | # 继续清理数据 83 | try: 84 | price = price.text.strip() 85 | except Exception as e: 86 | price = '0' 87 | 88 | loupan = loupan.text.replace("\n", "") 89 | 90 | try: 91 | total = total.text.strip().replace(u'总价', '') 92 | total = total.replace(u'/套起', '') 93 | except Exception as e: 94 | total = '0' 95 | 96 | print("{0} {1} {2} ".format( 97 | loupan, price, total)) 98 | 99 | # 作为对象保存 100 | loupan = LouPan(loupan, price, total) 101 | loupan_list.append(loupan) 102 | return loupan_list 103 | 104 | def start(self): 105 | city = get_city() 106 | print('Today date is: %s' % self.date_string) 107 | self.today_path = create_date_path("{0}/loupan".format(SPIDER_NAME), city, self.date_string) 108 | 109 | t1 = time.time() # 开始计时 110 | self.collect_city_loupan_data(city) 111 | t2 = time.time() # 计时结束，统计结果 112 | 113 | print("Total crawl {0} loupan.".format(self.total_num)) 114 | print("Total cost {0} second ".format(t2 - t1)) 115 | 116 | 117 | if __name__ == '__main__': 118 | pass 119 | -------------------------------------------------------------------------------- /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 -------------------------------------------------------------------------------- /lib/spider/xiaoqu_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 | # 爬取小区数据的爬虫派生类 6 | 7 | import re 8 | import threadpool 9 | from bs4 import BeautifulSoup 10 | from lib.item.xiaoqu import * 11 | from lib.zone.city import get_city 12 | from lib.spider.base_spider import * 13 | from lib.utility.date import * 14 | from lib.utility.path import * 15 | from lib.zone.area import * 16 | from lib.utility.log import * 17 | import lib.utility.version 18 | 19 | 20 | class XiaoQuBaseSpider(BaseSpider): 21 | def collect_area_xiaoqu_data(self, city_name, area_name, fmt="csv"): 22 | """ 23 | 对于每个板块,获得这个板块下所有小区的信息 24 | 并且将这些信息写入文件保存 25 | :param city_name: 城市 26 | :param area_name: 板块 27 | :param fmt: 保存文件格式 28 | :return: None 29 | """ 30 | district_name = area_dict.get(area_name, "") 31 | csv_file = self.today_path + "/{0}_{1}.csv".format(district_name, area_name) 32 | with open(csv_file, "w") as f: 33 | # 开始获得需要的板块数据 34 | xqs = self.get_xiaoqu_info(city_name, area_name) 35 | # 锁定 36 | if self.mutex.acquire(1): 37 | self.total_num += len(xqs) 38 | # 释放 39 | self.mutex.release() 40 | if fmt == "csv": 41 | for xiaoqu in xqs: 42 | f.write(self.date_string + "," + xiaoqu.text() + "\n") 43 | print("Finish crawl area: " + area_name + ", save data to : " + csv_file) 44 | logger.info("Finish crawl area: " + area_name + ", save data to : " + csv_file) 45 | 46 | @staticmethod 47 | def get_xiaoqu_info(city, area): 48 | total_page = 1 49 | district = area_dict.get(area, "") 50 | chinese_district = get_chinese_district(district) 51 | chinese_area = chinese_area_dict.get(area, "") 52 | xiaoqu_list = list() 53 | page = 'http://{0}.{1}.com/xiaoqu/{2}/'.format(city, SPIDER_NAME, area) 54 | print(page) 55 | logger.info(page) 56 | 57 | headers = create_headers() 58 | response = requests.get(page, timeout=10, headers=headers) 59 | html = response.content 60 | soup = BeautifulSoup(html, "lxml") 61 | 62 | # 获得总的页数 63 | try: 64 | page_box = soup.find_all('div', class_='page-box')[0] 65 | matches = re.search('.*"totalPage":(\d+),.*', str(page_box)) 66 | total_page = int(matches.group(1)) 67 | except Exception as e: 68 | print("\tWarning: only find one page for {0}".format(area)) 69 | print(e) 70 | 71 | # 从第一页开始,一直遍历到最后一页 72 | for i in range(1, total_page + 1): 73 | headers = create_headers() 74 | page = 'http://{0}.{1}.com/xiaoqu/{2}/pg{3}'.format(city, SPIDER_NAME, area, i) 75 | print(page) # 打印版块页面地址 76 | BaseSpider.random_delay() 77 | response = requests.get(page, timeout=10, headers=headers) 78 | html = response.content 79 | soup = BeautifulSoup(html, "lxml") 80 | 81 | # 获得有小区信息的panel 82 | house_elems = soup.find_all('li', class_="xiaoquListItem") 83 | for house_elem in house_elems: 84 | price = house_elem.find('div', class_="totalPrice") 85 | name = house_elem.find('div', class_='title') 86 | on_sale = house_elem.find('div', class_="xiaoquListItemSellCount") 87 | 88 | # 继续清理数据 89 | price = price.text.strip() 90 | name = name.text.replace("\n", "") 91 | on_sale = on_sale.text.replace("\n", "").strip() 92 | 93 | # 作为对象保存 94 | xiaoqu = XiaoQu(chinese_district, chinese_area, name, price, on_sale) 95 | xiaoqu_list.append(xiaoqu) 96 | return xiaoqu_list 97 | 98 | def start(self): 99 | city = get_city() 100 | self.today_path = create_date_path("{0}/xiaoqu".format(SPIDER_NAME), city, self.date_string) 101 | t1 = time.time() # 开始计时 102 | 103 | # 获得城市有多少区列表, district: 区县 104 | districts = get_districts(city) 105 | print('City: {0}'.format(city)) 106 | print('Districts: {0}'.format(districts)) 107 | 108 | # 获得每个区的板块, area: 板块 109 | areas = list() 110 | for district in districts: 111 | areas_of_district = get_areas(city, district) 112 | print('{0}: Area list: {1}'.format(district, areas_of_district)) 113 | # 用list的extend方法,L1.extend(L2)，该方法将参数L2的全部元素添加到L1的尾部 114 | areas.extend(areas_of_district) 115 | # 使用一个字典来存储区县和板块的对应关系, 例如{'beicai': 'pudongxinqu', } 116 | for area in areas_of_district: 117 | area_dict[area] = district 118 | print("Area:", areas) 119 | print("District and areas:", area_dict) 120 | 121 | # 准备线程池用到的参数 122 | nones = [None for i in range(len(areas))] 123 | city_list = [city for i in range(len(areas))] 124 | args = zip(zip(city_list, areas), nones) 125 | # areas = areas[0: 1] 126 | 127 | # 针对每个板块写一个文件,启动一个线程来操作 128 | pool_size = thread_pool_size 129 | pool = threadpool.ThreadPool(pool_size) 130 | my_requests = threadpool.makeRequests(self.collect_area_xiaoqu_data, args) 131 | [pool.putRequest(req) for req in my_requests] 132 | pool.wait() 133 | pool.dismissWorkers(pool_size, do_join=True) # 完成后退出 134 | 135 | # 计时结束，统计结果 136 | t2 = time.time() 137 | print("Total crawl {0} areas.".format(len(areas))) 138 | print("Total cost {0} second to crawl {1} data items.".format(t2 - t1, self.total_num)) 139 | 140 | 141 | if __name__ == "__main__": 142 | # urls = get_xiaoqu_area_urls() 143 | # print urls 144 | # get_xiaoqu_info("sh", "beicai") 145 | spider = XiaoQuBaseSpider("lianjia") 146 | spider.start() 147 | -------------------------------------------------------------------------------- /lib/spider/ershou_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 | # 爬取二手房数据的爬虫派生类 6 | 7 | import re 8 | import threadpool 9 | from bs4 import BeautifulSoup 10 | from lib.item.ershou import * 11 | from lib.zone.city import get_city 12 | from lib.spider.base_spider import * 13 | from lib.utility.date import * 14 | from lib.utility.path import * 15 | from lib.zone.area import * 16 | from lib.utility.log import * 17 | import lib.utility.version 18 | 19 | 20 | class ErShouSpider(BaseSpider): 21 | def collect_area_ershou_data(self, city_name, area_name, fmt="csv"): 22 | """ 23 | 对于每个板块,获得这个板块下所有二手房的信息 24 | 并且将这些信息写入文件保存 25 | :param city_name: 城市 26 | :param area_name: 板块 27 | :param fmt: 保存文件格式 28 | :return: None 29 | """ 30 | district_name = area_dict.get(area_name, "") 31 | csv_file = self.today_path + "/{0}_{1}.csv".format(district_name, area_name) 32 | with open(csv_file, "w") as f: 33 | # 开始获得需要的板块数据 34 | ershous = self.get_area_ershou_info(city_name, area_name) 35 | # 锁定，多线程读写 36 | if self.mutex.acquire(1): 37 | self.total_num += len(ershous) 38 | # 释放 39 | self.mutex.release() 40 | if fmt == "csv": 41 | for ershou in ershous: 42 | # print(date_string + "," + xiaoqu.text()) 43 | f.write(self.date_string + "," + ershou.text() + "\n") 44 | print("Finish crawl area: " + area_name + ", save data to : " + csv_file) 45 | 46 | @staticmethod 47 | def get_area_ershou_info(city_name, area_name): 48 | """ 49 | 通过爬取页面获得城市指定版块的二手房信息 50 | :param city_name: 城市 51 | :param area_name: 版块 52 | :return: 二手房数据列表 53 | """ 54 | total_page = 1 55 | district_name = area_dict.get(area_name, "") 56 | # 中文区县 57 | chinese_district = get_chinese_district(district_name) 58 | # 中文版块 59 | chinese_area = chinese_area_dict.get(area_name, "") 60 | 61 | ershou_list = list() 62 | page = 'http://{0}.{1}.com/ershoufang/{2}/'.format(city_name, SPIDER_NAME, area_name) 63 | print(page) # 打印版块页面地址 64 | headers = create_headers() 65 | response = requests.get(page, timeout=10, headers=headers) 66 | html = response.content 67 | soup = BeautifulSoup(html, "lxml") 68 | 69 | # 获得总的页数，通过查找总页码的元素信息 70 | try: 71 | page_box = soup.find_all('div', class_='page-box')[0] 72 | matches = re.search('.*"totalPage":(\d+),.*', str(page_box)) 73 | total_page = int(matches.group(1)) 74 | except Exception as e: 75 | print("\tWarning: only find one page for {0}".format(area_name)) 76 | print(e) 77 | 78 | # 从第一页开始,一直遍历到最后一页 79 | for num in range(1, total_page + 1): 80 | page = 'http://{0}.{1}.com/ershoufang/{2}/pg{3}'.format(city_name, SPIDER_NAME, area_name, num) 81 | print(page) # 打印每一页的地址 82 | headers = create_headers() 83 | BaseSpider.random_delay() 84 | response = requests.get(page, timeout=10, headers=headers) 85 | html = response.content 86 | soup = BeautifulSoup(html, "lxml") 87 | 88 | # 获得有小区信息的panel 89 | house_elements = soup.find_all('li', class_="clear") 90 | for house_elem in house_elements: 91 | price = house_elem.find('div', class_="totalPrice") 92 | name = house_elem.find('div', class_='title') 93 | desc = house_elem.find('div', class_="houseInfo") 94 | pic = house_elem.find('a', class_="img").find('img', class_="lj-lazy") 95 | 96 | # 继续清理数据 97 | price = price.text.strip() 98 | name = name.text.replace("\n", "") 99 | desc = desc.text.replace("\n", "").strip() 100 | pic = pic.get('data-original').strip() 101 | # print(pic) 102 | 103 | 104 | # 作为对象保存 105 | ershou = ErShou(chinese_district, chinese_area, name, price, desc, pic) 106 | ershou_list.append(ershou) 107 | return ershou_list 108 | 109 | def start(self): 110 | city = get_city() 111 | self.today_path = create_date_path("{0}/ershou".format(SPIDER_NAME), city, self.date_string) 112 | 113 | t1 = time.time() # 开始计时 114 | 115 | # 获得城市有多少区列表, district: 区县 116 | districts = get_districts(city) 117 | print('City: {0}'.format(city)) 118 | print('Districts: {0}'.format(districts)) 119 | 120 | # 获得每个区的板块, area: 板块 121 | areas = list() 122 | for district in districts: 123 | areas_of_district = get_areas(city, district) 124 | print('{0}: Area list: {1}'.format(district, areas_of_district)) 125 | # 用list的extend方法,L1.extend(L2)，该方法将参数L2的全部元素添加到L1的尾部 126 | areas.extend(areas_of_district) 127 | # 使用一个字典来存储区县和板块的对应关系, 例如{'beicai': 'pudongxinqu', } 128 | for area in areas_of_district: 129 | area_dict[area] = district 130 | print("Area:", areas) 131 | print("District and areas:", area_dict) 132 | 133 | # 准备线程池用到的参数 134 | nones = [None for i in range(len(areas))] 135 | city_list = [city for i in range(len(areas))] 136 | args = zip(zip(city_list, areas), nones) 137 | # areas = areas[0: 1] # For debugging 138 | 139 | # 针对每个板块写一个文件,启动一个线程来操作 140 | pool_size = thread_pool_size 141 | pool = threadpool.ThreadPool(pool_size) 142 | my_requests = threadpool.makeRequests(self.collect_area_ershou_data, args) 143 | [pool.putRequest(req) for req in my_requests] 144 | pool.wait() 145 | pool.dismissWorkers(pool_size, do_join=True) # 完成后退出 146 | 147 | # 计时结束，统计结果 148 | t2 = time.time() 149 | print("Total crawl {0} areas.".format(len(areas))) 150 | print("Total cost {0} second to crawl {1} data items.".format(t2 - t1, self.total_num)) 151 | 152 | 153 | if __name__ == '__main__': 154 | pass 155 | -------------------------------------------------------------------------------- /xiaoqu_to_db.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 | # read data from csv, write to database 6 | # database includes: mysql/mongodb/excel/json/csv 7 | 8 | import os 9 | import pymysql 10 | from lib.utility.path import DATA_PATH 11 | from lib.zone.city import * 12 | from lib.utility.date import * 13 | from lib.utility.version import PYTHON_3 14 | from lib.spider.base_spider import SPIDER_NAME 15 | 16 | pymysql.install_as_MySQLdb() 17 | 18 | 19 | def create_prompt_text(): 20 | city_info = list() 21 | num = 0 22 | for en_name, ch_name in cities.items(): 23 | num += 1 24 | city_info.append(en_name) 25 | city_info.append(": ") 26 | city_info.append(ch_name) 27 | if num % 4 == 0: 28 | city_info.append("\n") 29 | else: 30 | city_info.append(", ") 31 | return 'Which city data do you want to save ?\n' + ''.join(city_info) 32 | 33 | 34 | if __name__ == '__main__': 35 | # 设置目标数据库 36 | ################################## 37 | # mysql/mongodb/excel/json/csv 38 | # database = "mysql" 39 | # database = "mongodb" 40 | # database = "excel" 41 | # database = "json" 42 | database = "csv" 43 | ################################## 44 | db = None 45 | collection = None 46 | workbook = None 47 | csv_file = None 48 | datas = list() 49 | 50 | if database == "mysql": 51 | import records 52 | db = records.Database('mysql://root:123456@localhost/lianjia?charset=utf8', encoding='utf-8') 53 | elif database == "mongodb": 54 | from pymongo import MongoClient 55 | conn = MongoClient('localhost', 27017) 56 | db = conn.lianjia # 连接lianjia数据库，没有则自动创建 57 | collection = db.xiaoqu # 使用xiaoqu集合，没有则自动创建 58 | elif database == "excel": 59 | import xlsxwriter 60 | workbook = xlsxwriter.Workbook('xiaoqu.xlsx') 61 | worksheet = workbook.add_worksheet() 62 | elif database == "json": 63 | import json 64 | elif database == "csv": 65 | csv_file = open("xiaoqu.csv", "w") 66 | line = "{0};{1};{2};{3};{4};{5};{6}\n".format('city_ch', 'date', 'district', 'area', 'xiaoqu', 'price', 'sale') 67 | csv_file.write(line) 68 | 69 | city = get_city() 70 | # 准备日期信息，爬到的数据存放到日期相关文件夹下 71 | date = get_date_string() 72 | # 获得 csv 文件路径 73 | # date = "20180331" # 指定采集数据的日期 74 | # city = "sh" # 指定采集数据的城市 75 | city_ch = get_chinese_city(city) 76 | csv_dir = "{0}/{1}/xiaoqu/{2}/{3}".format(DATA_PATH, SPIDER_NAME, city, date) 77 | 78 | files = list() 79 | if not os.path.exists(csv_dir): 80 | print("{0} does not exist.".format(csv_dir)) 81 | print("Please run 'python xiaoqu.py' firstly.") 82 | print("Bye.") 83 | exit(0) 84 | else: 85 | print('OK, start to process ' + get_chinese_city(city)) 86 | for csv in os.listdir(csv_dir): 87 | data_csv = csv_dir + "/" + csv 88 | # print(data_csv) 89 | files.append(data_csv) 90 | 91 | # 清理数据 92 | count = 0 93 | row = 0 94 | col = 0 95 | for csv in files: 96 | with open(csv, 'r') as f: 97 | for line in f: 98 | count += 1 99 | text = line.strip() 100 | try: 101 | # 如果小区名里面没有逗号，那么总共是6项 102 | if text.count(',') == 5: 103 | date, district, area, xiaoqu, price, sale = text.split(',') 104 | elif text.count(',') < 5: 105 | continue 106 | else: 107 | fields = text.split(',') 108 | date = fields[0] 109 | district = fields[1] 110 | area = fields[2] 111 | xiaoqu = ','.join(fields[3:-2]) 112 | price = fields[-2] 113 | sale = fields[-1] 114 | except Exception as e: 115 | print(text) 116 | print(e) 117 | continue 118 | sale = sale.replace(r'套在售二手房', '') 119 | price = price.replace(r'暂无', '0') 120 | price = price.replace(r'元/m2', '') 121 | price = int(price) 122 | sale = int(sale) 123 | print("{0} {1} {2} {3} {4} {5}".format(date, district, area, xiaoqu, price, sale)) 124 | # 写入mysql数据库 125 | if database == "mysql": 126 | db.query('INSERT INTO xiaoqu (city, date, district, area, xiaoqu, price, sale) ' 127 | 'VALUES(:city, :date, :district, :area, :xiaoqu, :price, :sale)', 128 | city=city_ch, date=date, district=district, area=area, xiaoqu=xiaoqu, price=price, 129 | sale=sale) 130 | # 写入mongodb数据库 131 | elif database == "mongodb": 132 | data = dict(city=city_ch, date=date, district=district, area=area, xiaoqu=xiaoqu, price=price, 133 | sale=sale) 134 | collection.insert(data) 135 | elif database == "excel": 136 | if not PYTHON_3: 137 | worksheet.write_string(row, col, unicode(city_ch, 'utf-8')) 138 | worksheet.write_string(row, col + 1, date) 139 | worksheet.write_string(row, col + 2, unicode(district, 'utf-8')) 140 | worksheet.write_string(row, col + 3, unicode(area, 'utf-8')) 141 | worksheet.write_string(row, col + 4, unicode(xiaoqu, 'utf-8')) 142 | worksheet.write_number(row, col + 5, price) 143 | worksheet.write_number(row, col + 6, sale) 144 | else: 145 | worksheet.write_string(row, col, city_ch) 146 | worksheet.write_string(row, col + 1, date) 147 | worksheet.write_string(row, col + 2, district) 148 | worksheet.write_string(row, col + 3, area) 149 | worksheet.write_string(row, col + 4, xiaoqu) 150 | worksheet.write_number(row, col + 5, price) 151 | worksheet.write_number(row, col + 6, sale) 152 | row += 1 153 | elif database == "json": 154 | data = dict(city=city_ch, date=date, district=district, area=area, xiaoqu=xiaoqu, price=price, 155 | sale=sale) 156 | datas.append(data) 157 | elif database == "csv": 158 | line = "{0};{1};{2};{3};{4};{5};{6}\n".format(city_ch, date, district, area, xiaoqu, price, sale) 159 | csv_file.write(line) 160 | 161 | # 写入，并且关闭句柄 162 | if database == "excel": 163 | workbook.close() 164 | elif database == "json": 165 | json.dump(datas, open('xiaoqu.json', 'w'), ensure_ascii=False, indent=2) 166 | elif database == "csv": 167 | csv_file.close() 168 | 169 | print("Total write {0} items to database.".format(count)) 170 | -------------------------------------------------------------------------------- /lib/spider/zufang_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 | # 爬取租房数据的爬虫派生类 6 | 7 | import re 8 | import threadpool 9 | from bs4 import BeautifulSoup 10 | from lib.item.zufang import * 11 | from lib.spider.base_spider import * 12 | from lib.utility.date import * 13 | from lib.utility.path import * 14 | from lib.zone.area import * 15 | from lib.zone.city import get_city 16 | import lib.utility.version 17 | 18 | 19 | class ZuFangBaseSpider(BaseSpider): 20 | def collect_area_zufang_data(self, city_name, area_name, fmt="csv"): 21 | """ 22 | 对于每个板块,获得这个板块下所有出租房的信息 23 | 并且将这些信息写入文件保存 24 | :param city_name: 城市 25 | :param area_name: 板块 26 | :param fmt: 保存文件格式 27 | :return: None 28 | """ 29 | district_name = area_dict.get(area_name, "") 30 | csv_file = self.today_path + "/{0}_{1}.csv".format(district_name, area_name) 31 | with open(csv_file, "w") as f: 32 | # 开始获得需要的板块数据 33 | zufangs = self.get_area_zufang_info(city_name, area_name) 34 | # 锁定 35 | if self.mutex.acquire(1): 36 | self.total_num += len(zufangs) 37 | # 释放 38 | self.mutex.release() 39 | if fmt == "csv": 40 | for zufang in zufangs: 41 | f.write(self.date_string + "," + zufang.text() + "\n") 42 | print("Finish crawl area: " + area_name + ", save data to : " + csv_file) 43 | 44 | @staticmethod 45 | def get_area_zufang_info(city_name, area_name): 46 | matches = None 47 | """ 48 | 通过爬取页面获取城市指定版块的租房信息 49 | :param city_name: 城市 50 | :param area_name: 版块 51 | :return: 出租房信息列表 52 | """ 53 | total_page = 1 54 | district_name = area_dict.get(area_name, "") 55 | chinese_district = get_chinese_district(district_name) 56 | chinese_area = chinese_area_dict.get(area_name, "") 57 | zufang_list = list() 58 | page = 'http://{0}.{1}.com/zufang/{2}/'.format(city_name, SPIDER_NAME, area_name) 59 | print(page) 60 | 61 | headers = create_headers() 62 | response = requests.get(page, timeout=10, headers=headers) 63 | html = response.content 64 | soup = BeautifulSoup(html, "lxml") 65 | 66 | # 获得总的页数 67 | try: 68 | if SPIDER_NAME == "lianjia": 69 | page_box = soup.find_all('div', class_='page-box')[0] 70 | matches = re.search('.*"totalPage":(\d+),.*', str(page_box)) 71 | elif SPIDER_NAME == "ke": 72 | page_box = soup.find_all('div', class_='content__pg')[0] 73 | # print(page_box) 74 | matches = re.search('.*data-totalpage="(\d+)".*', str(page_box)) 75 | total_page = int(matches.group(1)) 76 | # print(total_page) 77 | except Exception as e: 78 | print("\tWarning: only find one page for {0}".format(area_name)) 79 | print(e) 80 | 81 | # 从第一页开始,一直遍历到最后一页 82 | headers = create_headers() 83 | for num in range(1, total_page + 1): 84 | page = 'http://{0}.{1}.com/zufang/{2}/pg{3}'.format(city_name, SPIDER_NAME, area_name, num) 85 | print(page) 86 | BaseSpider.random_delay() 87 | response = requests.get(page, timeout=10, headers=headers) 88 | html = response.content 89 | soup = BeautifulSoup(html, "lxml") 90 | 91 | # 获得有小区信息的panel 92 | if SPIDER_NAME == "lianjia": 93 | ul_element = soup.find('ul', class_="house-lst") 94 | house_elements = ul_element.find_all('li') 95 | else: 96 | ul_element = soup.find('div', class_="content__list") 97 | house_elements = ul_element.find_all('div', class_="content__list--item") 98 | 99 | if len(house_elements) == 0: 100 | continue 101 | # else: 102 | # print(len(house_elements)) 103 | 104 | for house_elem in house_elements: 105 | if SPIDER_NAME == "lianjia": 106 | price = house_elem.find('span', class_="num") 107 | xiaoqu = house_elem.find('span', class_='region') 108 | layout = house_elem.find('span', class_="zone") 109 | size = house_elem.find('span', class_="meters") 110 | else: 111 | price = house_elem.find('span', class_="content__list--item-price") 112 | desc1 = house_elem.find('p', class_="content__list--item--title") 113 | desc2 = house_elem.find('p', class_="content__list--item--des") 114 | 115 | try: 116 | if SPIDER_NAME == "lianjia": 117 | price = price.text.strip() 118 | xiaoqu = xiaoqu.text.strip().replace("\n", "") 119 | layout = layout.text.strip() 120 | size = size.text.strip() 121 | else: 122 | # 继续清理数据 123 | price = price.text.strip().replace(" ", "").replace("元/月", "") 124 | # print(price) 125 | desc1 = desc1.text.strip().replace("\n", "") 126 | desc2 = desc2.text.strip().replace("\n", "").replace(" ", "") 127 | # print(desc1) 128 | 129 | infos = desc1.split(' ') 130 | xiaoqu = infos[0] 131 | layout = infos[1] 132 | descs = desc2.split('/') 133 | # print(descs[1]) 134 | size = descs[1].replace("㎡", "平米") 135 | 136 | # print("{0} {1} {2} {3} {4} {5} {6}".format( 137 | # chinese_district, chinese_area, xiaoqu, layout, size, price)) 138 | 139 | # 作为对象保存 140 | zufang = ZuFang(chinese_district, chinese_area, xiaoqu, layout, size, price) 141 | zufang_list.append(zufang) 142 | except Exception as e: 143 | print("=" * 20 + " page no data") 144 | print(e) 145 | print(page) 146 | print("=" * 20) 147 | return zufang_list 148 | 149 | def start(self): 150 | city = get_city() 151 | self.today_path = create_date_path("{0}/zufang".format(SPIDER_NAME), city, self.date_string) 152 | # collect_area_zufang('sh', 'beicai') # For debugging, keep it here 153 | t1 = time.time() # 开始计时 154 | 155 | # 获得城市有多少区列表, district: 区县 156 | districts = get_districts(city) 157 | print('City: {0}'.format(city)) 158 | print('Districts: {0}'.format(districts)) 159 | 160 | # 获得每个区的板块, area: 板块 161 | areas = list() 162 | for district in districts: 163 | areas_of_district = get_areas(city, district) 164 | print('{0}: Area list: {1}'.format(district, areas_of_district)) 165 | # 用list的extend方法,L1.extend(L2)，该方法将参数L2的全部元素添加到L1的尾部 166 | areas.extend(areas_of_district) 167 | # 使用一个字典来存储区县和板块的对应关系, 例如{'beicai': 'pudongxinqu', } 168 | for area in areas_of_district: 169 | area_dict[area] = district 170 | print("Area:", areas) 171 | print("District and areas:", area_dict) 172 | 173 | # 准备线程池用到的参数 174 | nones = [None for i in range(len(areas))] 175 | city_list = [city for i in range(len(areas))] 176 | args = zip(zip(city_list, areas), nones) 177 | # areas = areas[0: 1] 178 | 179 | # 针对每个板块写一个文件,启动一个线程来操作 180 | pool_size = thread_pool_size 181 | pool = threadpool.ThreadPool(pool_size) 182 | my_requests = threadpool.makeRequests(self.collect_area_zufang_data, args) 183 | [pool.putRequest(req) for req in my_requests] 184 | pool.wait() 185 | pool.dismissWorkers(pool_size, do_join=True) # 完成后退出 186 | 187 | # 计时结束，统计结果 188 | t2 = time.time() 189 | print("Total crawl {0} areas.".format(len(areas))) 190 | print("Total cost {0} second to crawl {1} data items.".format(t2 - t1, self.total_num)) 191 | 192 | 193 | if __name__ == '__main__': 194 | # get_area_zufang_info("yt", "muping") 195 | pass 196 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | --------------------------------------------------------------------------------