抓包分析实战爬取腾讯视频评论

from urllib import request, error
import re
import json


# 使用代理服务器
def use_proxy(url, proxy_addr):
    # https://www.xicidaili.com/nn/
    proxy = request.ProxyHandler({'http': proxy_addr})
    opener = request.build_opener(proxy, request.HTTPHandler)
    # 添加为全局
    request.install_opener(opener)

    data = request.urlopen(url).read().decode('utf-8', 'ignore')
    return data


proxy_addr = '163.204.243.242:9999'

cursor = '6573212673981793805'
_ = 1568989058882
for i in range(0, 10):
    url = 'https://video.coral.qq.com/varticle/4100808418/comment/v2?callback=_varticle4100808418commentv2&orinum=10&oriorder=o&pageflag=1&cursor='+ cursor + '&scorecursor=0&orirepnum=2&reporder=o&reppageflag=1&source=132&_=' + str(_)
    ret = use_proxy(url, proxy_addr)
    pat_cursor = '"last":"(.*?)"'
    cursor = re.compile(pat_cursor).findall(ret)[0]
    _ = _ + 1

    pat_comment = '"content":"(.*?)"'
    list = re.compile(pat_comment).findall(ret)
    print(list)