web crawling(plus2) comment crawling

标签：mini   urlopen   mozilla   web   data   import   tps   dal   cal   

#Author：Mini
#！/usr/bin/env python
import urllib.request
import re
import urllib.error
headers=("User-Agent","Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:56.0) Gecko/20100101 Firefox/56.0")
opener=urllib.request.build_opener()
opener.addheaders=[headers]
urllib.request.install_opener(opener)
comid="6315179284605088209"
for i in range(4,7):
 url="https://coral.qq.com/article/1003390161/comment?commentid="+comid+"&reqnum=20&tag=&callback=jQuery112409214906389806301_1507082215770&_=150708221577"+str(i)

 data=urllib.request.urlopen(url).read().decode("utf-8","ignore")
 patnext=‘"last":"(.*?)"‘
 nextid=re.compile(patnext).findall(data)[0]
 patcom=‘"content":"(.*?)",‘
 comdata=re.compile(patcom).findall(data)
 for j in range(0,len(comdata)):
     print(str(i)+"."+str(j)+"comment:")
     print(eval(‘u"‘+comdata[j]+‘"‘))
 url="https://coral.qq.com/article/1003390161/comment?commentid="+nextid+"&reqnum=20&tag=&callback=jQuery112409214906389806301_1507082215770&_=150708221577"+str(i)
 print(url)

web crawling(plus2) comment crawling

标签：mini   urlopen   mozilla   web   data   import   tps   dal   cal   

原文地址：http://www.cnblogs.com/rabbittail/p/7625447.html