├── .gitignore ├── .idea ├── .gitignore ├── 1024爬虫.iml ├── inspectionProfiles │ └── Project_Default.xml ├── misc.xml ├── modules.xml └── vcs.xml ├── 1024.py ├── LICENSE ├── README.md └── demo.png /.gitignore: -------------------------------------------------------------------------------- 1 | # Created by .ignore support plugin (hsz.mobi) 2 | -------------------------------------------------------------------------------- /.idea/.gitignore: -------------------------------------------------------------------------------- 1 | # Default ignored files 2 | /workspace.xml -------------------------------------------------------------------------------- /.idea/1024爬虫.iml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | -------------------------------------------------------------------------------- /.idea/inspectionProfiles/Project_Default.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 36 | -------------------------------------------------------------------------------- /.idea/misc.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 6 | -------------------------------------------------------------------------------- /.idea/modules.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | -------------------------------------------------------------------------------- /.idea/vcs.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | -------------------------------------------------------------------------------- /1024.py: -------------------------------------------------------------------------------- 1 | import requests 2 | import re 3 | import os 4 | from lxml import etree 5 | try: 6 | flag=1 7 | while flag<=270: 8 | base_url='https://t66y.com/' 9 | page_url='https://t66y.com/thread0806.php?fid=16&search=&page='+str(flag) 10 | get=requests.get(page_url) 11 | article_url=re.findall(r'

(?!<.*>).*

',str(get.content,'gbk',errors='ignore')) 12 | for url in article_url: 13 | tittle=['default'] 14 | getpage=requests.get(str(base_url)+str(url)) 15 | tittle=re.findall(r'

(.*)

',str(getpage.content,'gbk',errors='ignore')) 16 | file=tittle[0] 17 | if os.path.exists(file)==False: 18 | os.makedirs(file) 19 | tree=etree.HTML(str(getpage.content,'gbk',errors='ignore')) 20 | img_url=tree.xpath('//input/@data-src') 21 | filename=1 22 | for download_url in img_url: 23 | headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36Name','Referer':'https://t66y.com'} 24 | req=requests.get(url=download_url,headers=headers) 25 | file_path='./'+file+"/"+str(filename)+'.jpg' 26 | with open(file_path,'wb') as f: 27 | print('开始下载:'+file+"----第"+str(filename)+"张图片") 28 | f.write(req.content) 29 | filename+=1 30 | print(file+"--下载完成") 31 | except: 32 | print("崩了,兄弟") 33 | 34 | 35 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2019 Liu Y 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # 单线程爬虫,下载的图片文件全部保存在了项目下,下载过的会自动跳 2 | 3 | 请在python 3下运行 4 | 5 | 需要的库: 6 | ```bash 7 | requests 8 | lxml 9 | ``` 10 | 11 | 运行: 12 | ```bash 13 | python 1024.py 14 | ``` 15 | 16 | 停止: 17 | ```bash 18 | ctrl+c 19 | ``` 20 | 如果网络不好,小概率会崩掉,重新运行就OK 21 | 22 | 23 | ![Image text](https://raw.githubusercontent.com/6yi/1024-web-crawler/master/demo.png) 24 | 25 | # 默认爬的是达盖尔的旗帜,可以自己修改想要爬的分区 26 | 27 | ```bash 28 | 把page_url里的pid=16修改成pid=8就可以爬取新时代区了 29 | ``` 30 | 31 | 32 | -------------------------------------------------------------------------------- /demo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/6yi/1024-web-crawler/83f939a53a921c49fbbacb5c5b8000c88b1da858/demo.png --------------------------------------------------------------------------------