查找某人在某微博裏留下的所有留言

#coding=utf-8
__author__ = 'user'
import requests
import sys
import re
import time

def getcomment(url,cook,commentid):
urlre=requests.get(url,cookies=cook)
html=urlre.text
cook2=urlre.cookies
print(html.encode('utf-8'))
print('')

mystate2=re.findall('</a> <a href="http://weibo.cn/comment/(.*?)&rl=0#cmtfrm(.*?)</a>',html,re.S)
k=0

f=open('1.txt','r')
a=f.read()
f.close()
f=open('1.txt','w+')
f.write(a)

for i in mystate2:
k=k+1
meow=re.findall('\[(.*?)\]',i[1],re.S)
if meow[0]!='0':
ans=re.search(commentid,i[0])
if ans:
commentlink='http://weibo.cn/comment/'+i[0]+'&rl=0#cmtfrm'
#print (k)
#print (commentlink)
f.write(commentlink+'\n')

f.close()

print (k)
if k<1:
time.sleep(2)
getcomment(url,cook,commentid)

if __name__=='__main__':
cook={"Cookie":""}

for i in range(1,76+1):
print('start%d'%i)
url='http://weibo.cn/u/111111?page=%d'%i
commentid='111111'
getcomment(url,cook,commentid)

</pre><pre name="code" class="python"><pre name="code" class="python">#coding=utf-8
__author__ = 'user'
import requests
import sys
import re
import time

#<meta http-equiv="refresh"

def readtxt():
k=0
ff=open('1.txt','r')
a=ff.readline()
while a:
k=k+1
print(k)
if k>=1:
print(a)
test(a,a)
a=ff.readline()
ff.close()

def test(url0,url):
cook={"Cookie":""}

urlre=requests.get(url,cookies=cook)
html=urlre.text
print('read')
if re.search('comment',html,re.S):
zy=re.search('123456',html,re.S)
if zy:
f=open('2.txt','r')
text=f.read()
f.close()
f=open('2.txt','w+')
f.write(text)
f.write(url0+'\n')
f.close()
else:
nexturl=re.search('method="post"><div><a href="(.*?)">',html,re.S)
if nexturl:
nexturl=nexturl.group(1)
nexturl='http://weibo.cn'+nexturl
nexturl=re.sub('&','&',nexturl)
test(url0,nexturl)
else:
print(html.encode('utf-8'))
else:
time.sleep(1)
test(url0,url)

if __name__=='__main__':
readtxt()