Python 爬取开源大赛的附件

本文来源吾爱破解论坛

本帖最后由 E飞翔 于 2018-12-1 16:58 编辑

精易开源大赛的源码还是有很多比较好的东西的。

用Python写一下：

import re
from requests import post,get
import pprint

class JYKY:
    def __init__(self,num):
        """ 初始化  num  为页码 """
        self.urls = 'https://bbs.125.la/forum.php?mod=forumdisplay&fid=98&typeid=585&typeid=585&filter=typeid&t=5459534&page=%d'%num

    def getArticle(self):
        """ 获取帖子链接和标题 """
        header = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'}
        res = get(self.urls,headers=header).text

        Expression = r'<a href="\.(.*?html)" class="s xst">(.*?)</a>' # 优化后的表达式
        re_data = re.findall(Expression,res)

        # pprint.pprint(re_data)          # 格式化输出帖子链接和标题

        if re_data:
            for i in re_data:
                self.getAnnex(i)

    def getAnnex(self,listApp):
        """ 获取附件 """
        # print(listApp)
        url = 'https://bbs.125.la' + listApp[0]
        title = listApp[1]
        header = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36',
            'Cookie':'',                   # 这里添加你的  cookie
            'Host':'bbs.125.la',
            'Referer':self.urls
        }
        res = get(url,headers = header).text
        # print(res)
        re_data = re.findall(r'id=le3600_down:show&aid(.*?)"',res)
        # pprint.pprint(re_data)
        if re_data:
            for i in re_data:
                res_url = 'https://bbs.125.la/plugin.php?id=le3600_down:show&aid%s&infloat=yes&handlekey=le3600_down&inajax=1&ajaxtarget=fwin_content_le3600_down'%i
                res_i = get(res_url,headers=header).text
                rei_url = re.findall(r'a href="(http://att\.125\.la/plugin\.php\?id=le3600_down.*?)"',res_i)
                rei_name = re.findall(r'<td class="css_dashed" colspan="3">(.*?\.)(rar|7z|e|zip)</td>',res_i)#(.+?\.[rar|7z|e|zip])
                # print(res_i)
                # print(len(rei_url),len(rei_name))
                if rei_name :
                    self.saveAnnex(rei_name[0],rei_url[0])
                    print(rei_url[0])



    def saveAnnex(self,Annex_title,Annex_url):
        Annex = get(Annex_url)
        with open(r'C:\Users\Administrator\Desktop\MP3\%s' % Annex_title, 'wb') as f:
            f.write(Annex.content)



if __name__ == '__main__':
    p = JYKY(1) # 这里初始化一个页码
    p.getArticle()