恋爱吧爬取

最近竟然被虐，不行~~~
程序员的恋爱，欧耶！！！
网站链接
代码附上

import requests
import re
news={}
def o(what):
    global naws
    news['机会来了，小伙子']=what
    for key in news:
        print(key+':'+news[key])
for page in range(1,12000,50):
    url='https://tieba.baidu.com/f?kw=%C1%B5%B0%AE&fr=ala0&tpl={}'.format(page)
    headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 Safari/537.36 Edg/84.0.522.40'}
    html=requests.get(url=url,headers=headers)
    html.encoding='utf-8'
    info=re.findall('<a rel="noreferrer"  id="thread_top_folder" class="icon_top_folder" href="javascript:;"(.*?)<div class="thread_list_bottom clearfix">',html.text,re.S)
    for all_list in info:
        main=re.findall('<div class="threadlist_abs threadlist_abs_onlyline ">(.*?)</div>',all_list,re.S)
        for content in main:
            if content.find('脱单') != -1 or content.find('分手') != -1:
                o(content)
            else:
                pass


  

效果图

。。。。。程序员的崛起，疯狂繁殖~~~~