数据分析训练营-第五周-百度针对xpath反爬策略解决

xpath无法识别出被注释的代码，所以可以用re模块正则表达式解决

import re

with open('meiju1.html','r',encoding='utf-8') as f:
    html = re.sub('\n','',f.read())
    title_pattern = '<div class="threadlist_title pull_left j_th_tit ">.*?<a.*?>(.*?)</a>'#（）表示提取内容
    title_s = re.findall(title_pattern,html)
    for title in title_s:
        print(title)