高性能爬取携程网景区评论数据

昨天花了一天时间写的，改来改去，不断提升性能，终于可以把代码放出来了，如果发现服务域名无效，只需要更改Origin为http形式就行。

 

 

import csv

import requests
from bs4 import BeautifulSoup as bs
from  multiprocessing import Pool
import  gevent,time



class Comment(object):
    #请求头
    headers = {
        "Cookie":"_abtest_userid=dc18ac38-f25f-488b-8535-e709964f2257; gad_city=a4f35f7b1b0a14c597bf3a50fb024f55; MKT_Pagesource=PC; _ga=GA1.2.7662667.1551412569; _gid=GA1.2.815726266.1551412569; _RSG=Wd46GhfGxU6uCJw.ghACmB; _RDG=2808fbf74f24dd23c52c70ca0da70efd1f; _RGUID=67bb429a-d018-49e0-bc0c-2ababee93338; appFloatCnt=25; manualclose=1; TicketSiteID=SiteID=1006; StartCity_Pkg=PkgStartCity=1; Session=smartlinkcode=U130026&smartlinklanguage=zh&SmartLinkKeyWord=&SmartLinkQuary=&SmartLinkHost=; Union=AllianceID=4897&SID=