爬取微信文章代码

import re
import urllib.request
import time
import urllib.error
def use_proxy(proxy_addr,url):
    try:
      req=urllib.request.Request(url)
      req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:58.0) Gecko/20100101 Firefox/58.0')
      proxy=urllib.request.ProxyHandler({'http':proxy_addr})
      opener=urllib.request.build_opener(proxy,urllib.request.HTTPHandler)
      urllib.request.install_opener(opener)
      data=urllib.request.urlopen(req).read()
      return data
    except urllib.error.URLError as e:
        if(hasattr(e,"code")):
            print(e.code)
        if(hasattr(e,"reason")):
            print(e.reason)
        time.sleep(10)
    except Exception as e:
        print("exception:"+str(e))
        time.sleep(1)

key="Python"
proxy="127.0.0.1:8888"
for i in range(0,10):
    key=urllib.request.quote(key)
    thispageurl="http://weixin.sogou.com/weixin?query="+key+"&_sug_type_=&sut=1777&lkt=7%2C1519106265525%2C1519106267321&s_from=input&_sug_=y&type=2&sst0=1519106267427&page="+str(i)+"&ie=utf8&w=01019900&dr=1"
    thispagedata=use_proxy(proxy,thispageurl)
    print(len(str(thispagedata)))
    pat='<a target="_blank" href="(.*?)"'
    rs=re.compile(pat,re.S).findall(str(thispagedata))
    if(len(rs)==0):
        print("第("+str(i)+")页没成功")
        continue
    for j in range(0,len(rs)):
        thisurl=rs[j]
        thisurl=thisurl.replace("amp;","")
        file="d:/111"+str(i)+str(j)+".html"
        thisdata=use_proxy(proxy,thisurl)
        try:
            fh=open(file,"wb")
            fh.write(thisdata)
            fh.close()
            print("第"+str(i)+str(j)+"篇文章成功")
        except Exception as e:
            print(e)
            print("第"+str(i)+str(j)+"篇文章不成功")

用python3.5对weixin.sogou.com中的微信文章进行文章的爬取，浏览器为火狐浏览器，使用本地代理，代码如上。