python 多线程方法爬取微信公众号文章

本文在上一篇基础上增加多线程处理（https://blog.51cto.com/superleedo/2124494  ）

执行思路：

1，规划好执行流程，建立两个执行线程，一个控制线程

2，线程1用于获取url，并写入urlqueue队列

3，线程2，通过线程1的url获取文章内容，并保存到本地文件中

4，线程3用于控制程序，保证1,2线程都执行完后退出

5，多线程退出程序，在子线程设置daemon为true，保证程序正常退出

6，添加异常处理，添加限时防止屏蔽

闲话不多说，上代码

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import re
import urllib.request
import time
import sys
import urllib.error
import threading
import queue

urlqueue=queue.Queue()
##模拟浏览器安装headers
headers=("User-Agent","Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36")
opener=urllib.request.build_opener()
opener.addheaders=[headers]
urllib.request.install_opener(opener)
##设置列表用于存储链接
listurl=[]

##定义代理服务器函数
#def use_proxy(proxy_addr,url):
#       try:
#               import urllib.request
#               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(url).read().decode('utf-8')
#               data=str(data)
#               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)

##定义获取页面所有文章链接
class getlisturl(threading.Thread):
        def __init__(self,key,pagestart,pageend,urlqueue):
                threading.Thread.__init__(self)
                self.key=key
                self.pagestart=pagestart
                self.pageend=pageend
                self.urlqueue=urlqueue
        def run(self):

                page=self.pagestart
                keycode=urllib.request.quote(key)
        #       pagecode=urllib.request.quote("&page")
                for page in range(self.pagestart,self.pageend+1):
                        url="http://weixin.sogou.com/weixin?type=2&query="+keycode+"&page="+str(page)
                        data1=urllib.request.urlopen(url).read().decode('utf-8')
                        data1=str(data1)
                        listurlpat='
                                
                                
                                 
                                
                                
                                
                                '''
                fh=open("/home/urllib/test/1.html","wb")
                fh.write(html1.encode("utf-8"))
                fh.close()
                #再次以追加写入的方式打开文件，以写入对应文章内容
                fh=open("/home/urllib/test/1.html","ab")
                i=1
                while(True):
                        try:
                                url=self.urlqueue.get()
                                data=urllib.request.urlopen(url).read().decode('utf-8')
                                data=str(data)
                                titlepat='var msg_title = "(.*?)";'
                                contentpat='id="js_content">(.*?)id="js_sg_bar"'
                                title=re.compile(titlepat).findall(data)
                                content=re.compile(contentpat,re.S).findall(data)
                                #初始化标题与内容
                                thistitle = "此次没有获取到"
                                thiscontent= "此次没有获取到"
                                #如果标题列表不为空，说明找到了标题，取列表第0个元素，即此次标题赋给变量thistitle
                                if (title!=[]):
                                        thistitle = title[0]
                                if (content!=[]):
                                        thiscontent = content[0]
                                #将标题与内容汇总赋给变量dataall
                                dataall = "
标题为:"+thistitle+"
内容为："+thiscontent+"
"
                                fh.write(dataall.encode('utf-8'))
                                print("第"+str(i)+"个网页处理")
								time.sleep(1)
                                i+=1
                        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)

                fh.close()
                html2='''
                
                '''
                fh=open("/home/urllib/test/1.html","ab")
                fh.write(html2.encode("utf-8"))
                fh.close()

class contrl(threading.Thread):
        def __init__(self,urlqueue):
                threading.Thread.__init__(self)
                self.urlqueue=urlqueue
        def run(self):
                while(True):
                        print("程序执行中.....")
                        time.sleep(60)
                        if(self.urlqueue.empty()):
                                print("程序执行完毕。。。")
                                exit()

key="科技"
#proxy="122.114.31.177:808"
pagestart=1
pageend=2
#listurl=getlisturl(key,pagestart,pageend)
#getcontent(listurl)
t1=getlisturl(key,pagestart,pageend,urlqueue)
#子进程设置daemon为true，保证程序正常退出
t1.setDaemon(True)
t1.start()
t2=getcontent(urlqueue)
t2.setDaemon(True)
t2.start()
t3=contrl(urlqueue)
t3.start()

执行结果正常：

浏览器打开1.html

已上代码可以直接使用