Python 微信爬虫完整实例【单线程与多线程】


Posted in Python onJuly 06, 2019

本文实例讲述了Python 实现的微信爬虫。分享给大家供大家参考,具体如下:

单线程版:

import urllib.request
import urllib.parse
import urllib.error
import re,time
headers = ("User-Agent",
      "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3107.4 Safari/537.36")
operner = urllib.request.build_opener()
operner.addheaders = [headers]
urllib.request.install_opener(operner)
list_url = []
###使用代理获取网页url内容
def use_proxy(url):
  try:
    # proxy = urllib.request.ProxyHandler({'http':proxy_addr})
##使用代理版
    # operner = urllib.request.build_opener()
    # urllib.request.install_opener(operner)
    headers = ("User-Agent",
          "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3107.4 Safari/537.36")
    operner = urllib.request.build_opener()
    operner.addheaders = [headers]
    urllib.request.install_opener(operner)
    data = urllib.request.urlopen(url).read().decode('utf-8')
    # print (data)
    return data
  except urllib.error.URLError as e:
    if hasattr(e, "code"):
      print(e.code)
    elif hasattr(e, "reason"):
      print(e.reason)
  except Exception as e:
    print("exception" + str(e))
    time.sleep(1)
##获取要爬取的url
def get_url(key, pagestart, pageend):
  try:
    keycode = urllib.parse.quote(key)
    for page in range(pagestart, pageend + 1):
      url = "http://weixin.sogou.com/weixin?query=%s&_sug_type_=&s_from=input&_sug_=n&type=%d&page=1&ie=utf8" % (
      keycode, page)
      data1 = use_proxy(url)
      #print("data1的内容是", data1)
      listurl_pattern = '<h3>.*?("http://.*?)</h3>'
      result = re.compile(listurl_pattern, re.S).findall(data1)
      for i in range(len(result)):
        res = result[i].replace("amp;", "").split(" ")[0].replace("\"", "")
        list_url.append(res)
    #print(list_url)
    return list_url
  except urllib.error.URLError as e:
    if hasattr(e, "code"):
      print(e.code)
    elif hasattr(e, "reason"):
      print(e.reason)
  except Exception as e:
    print("exception:", e)
##通过获取的url爬行内容数据并处理
def get_url_content(list_url):
  fh1=open("D:\\python-script\\1.html", 'wb')
  html1 = '''<!DOCTYPE html>\n<html xmlns="http://www.w3.org/1999/xhmtl">\n<head>\n<meta http-equiv="Content-Type" content="text/html; charset=utf-8">\n<title>微信文章</title></head>\n<body>'''
  fh1.write(html1.encode("utf-8"))
  fh1.close()
  fh = open("D:\\python-script\\1.html", 'ab')
  for url in list_url:
    data_content = use_proxy(url)
    #print (data_content)
    #sys.exit()
    title_pattern = '<h2.*>.*?</h2>'
    result_title = re.compile(title_pattern, re.S).findall(data_content)
    ##标题(str)
    res_title = result_title[0].replace("<h2 class=\"rich_media_title\" id=\"activity-name\">", "").replace("</h2>",
                                             "").strip()
    content_pattern = 'id="js_content">(.*?)<div class="rich_media_tool" id="js_sg_bar">'
    content = re.compile(content_pattern, re.S).findall(data_content)
    try:
      fh.write(res_title.encode("utf-8"))
      for i in content:
        fh.write(i.strip().encode("utf-8"))
    except UnicodeEncodeError as e:
      continue
  fh.write("</body></html>".encode("utf-8"))
if __name__ == '__main__':
  pagestart = 1
  pageend = 2
  key = "人工智能"
  get_url(key, pagestart, pageend)
  get_url_content(list_url)

多线程版:

import urllib.request
import urllib.parse
import urllib.error
import re,time
import queue
import threading
headers = ("User-Agent","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3107.4 Safari/537.36")
operner = urllib.request.build_opener()
operner.addheaders = [headers]
urllib.request.install_opener(operner)
urlque = queue.Queue()
list_url = []
###使用代理获取网页url内容
def use_proxy(url):
  try:
    # proxy = urllib.request.ProxyHandler({'http':proxy_addr})
    # operner = urllib.request.build_opener()
    # urllib.request.install_opener(operner)
    headers = ("User-Agent",
          "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3107.4 Safari/537.36")
    operner = urllib.request.build_opener()
    operner.addheaders = [headers]
    urllib.request.install_opener(operner)
    data = urllib.request.urlopen(url).read().decode('utf-8')
    #print (data)
    return data
  except urllib.error.URLError as e:
    if hasattr(e,"code"):
      print (e.code)
    elif hasattr(e,"reason"):
      print (e.reason)
  except Exception as e:
    print ("exception"+str(e))
    time.sleep(1)
###获取文章的url连接,并将连接加入到队列
class get_url(threading.Thread):
  def __init__(self,key,pagestart,pageend,urlque):
    threading.Thread.__init__(self)
    self.pagestart = pagestart
    self.pageend = pageend
    self.key = key
    self.urlque = urlque
  def run(self):
    try:
      keycode = urllib.parse.quote(self.key)
      for page in range(self.pagestart,self.pageend+1):
        url = "http://weixin.sogou.com/weixin?query=%s&_sug_type_=&s_from=input&_sug_=n&type=%d&page=1&ie=utf8" % (keycode,page)
        data = use_proxy(url)
        print ("data1的内容是",data)
        listurl_pattern = '<h3>.*?("http://.*?)</h3>'
        result = re.compile(listurl_pattern,re.S).findall(data)
        print (result)
        if len(result) == 0:
          print ("没有可用的url")
          sys.exit()
        for i in range(len(result)):
          res = result[i].replace("amp;","").split(" ")[0].replace("\"" ,"")
          #list_url.append(res)    #加入列表
          self.urlque.put(res)      ##加入队列
          self.urlque.task_done()
      #return list_url
    except urllib.error.URLError as e:
      if hasattr(e, "code"):
        print(e.code)
      elif hasattr(e, "reason"):
        print(e.reason)
    except Exception as e:
      print ("exception:",e)
##根据url获取文章内容
class get_url_content(threading.Thread):
  def __init__(self,urlque):
    threading.Thread.__init__(self)
    self.urlque = urlque
  def run(self):
    fh1 = open("D:\\python-script\\1.html", 'wb')
    html1 = '''<!DOCTYPE html>\n<html xmlns="http://www.w3.org/1999/xhmtl">\n<head>\n<meta http-equiv="Content-Type" content="text/html; charset=utf-8">\n<title>微信文章</title></head>\n<body>'''
    fh1.write(html1.encode("utf-8"))
    fh1.close()
    fh = open("D:\\python-script\\1.html", 'ab')
    while True:
      try:
        url = self.urlque.get()
        data_content = use_proxy(url)
        title_pattern = '<h2.*>.*?</h2>'
        result_title = re.compile(title_pattern, re.S).findall(data_content)
        ##标题
        res_title = result_title[0].replace("<h2 class=\"rich_media_title\" id=\"activity-name\">", "").replace("</h2>","").strip()
        content_pattern = 'id="js_content">(.*?)<div class="rich_media_tool" id="js_sg_bar">'
        content = re.compile(content_pattern, re.S).findall(data_content)
        #c = '<p style="max-width: 100%;box-sizing: border-box;min-height: 1em;text-indent: 2em;word-wrap: break-word !important;">'
        # for i in content:
        #   ##内容
        #   c_content=i.replace(c, "").replace("<br /></p>", "").replace("</p>", "")
        fh.write(res_title.encode("utf-8"))
        for i in content:
          fh.write(i.strip().encode("utf-8"))
      except UnicodeEncodeError as e:
        continue
      fh.close()
class contrl(threading.Thread):
  def __init__(self,urlqueue):
    threading.Thread.__init__(self)
    self.urlqueue = urlqueue
    while True:
      print ("程序正在执行")
      if self.urlqueue.empty():
        time.sleep(3)
        print ("程序执行完毕")
        exit()
if __name__ == '__main__':
  pagestart = 1
  pageend = 2
  key = "人工智能"
  get_url = get_url(key,pagestart,pageend,urlque)
  get_url.start()
  get_content = get_url_content(urlque)
  get_content.start()
  cntrol = contrl(urlque)
  cntrol.start()

更多关于Python相关内容可查看本站专题:《Python Socket编程技巧总结》、《Python正则表达式用法总结》、《Python数据结构与算法教程》、《Python函数使用技巧总结》、《Python字符串操作技巧汇总》、《Python入门与进阶经典教程》及《Python文件与目录操作技巧汇总》

希望本文所述对大家Python程序设计有所帮助。

Python 相关文章推荐
python合并文本文件示例
Feb 07 Python
python基础教程之popen函数操作其它程序的输入和输出示例
Feb 10 Python
Windows下用py2exe将Python程序打包成exe程序的教程
Apr 08 Python
Python中的with...as用法介绍
May 28 Python
python中字典(Dictionary)用法实例详解
May 30 Python
python实现树形打印目录结构
Mar 29 Python
python获取命令行输入参数列表的实例代码
Jun 23 Python
Python使用itertools模块实现排列组合功能示例
Jul 02 Python
使用python Fabric动态修改远程机器hosts的方法
Oct 26 Python
pycharm 关掉syntax检查操作
Jun 09 Python
python从Oracle读取数据生成图表
Oct 14 Python
Python实现中英文全文搜索的示例
Dec 04 Python
python实现爬取百度图片的方法示例
Jul 06 #Python
python实现控制电脑鼠标和键盘,登录QQ的方法示例
Jul 06 #Python
python3 打印输出字典中特定的某个key的方法示例
Jul 06 #Python
python使用 zip 同时迭代多个序列示例
Jul 06 #Python
Python搭建Spark分布式集群环境
Jul 05 #Python
详解python解压压缩包的五种方法
Jul 05 #Python
用python3 返回鼠标位置的实现方法(带界面)
Jul 05 #Python
You might like
多人战的战术与战略
2020/03/04 星际争霸
PHP新手上路(八)
2006/10/09 PHP
php无限遍历目录示例
2014/02/21 PHP
PHP中copy on write写时复制机制介绍
2014/05/13 PHP
PHP实现图片批量打包下载功能
2017/03/01 PHP
js利用div背景,做一个竖线的效果。
2008/11/22 Javascript
jquery trim() 功能源代码
2011/02/14 Javascript
JS实现在线统计一个页面内鼠标点击次数的方法
2015/02/28 Javascript
浅谈JS之tagNaem和nodeName
2016/09/13 Javascript
es7学习教程之fetch解决异步嵌套问题的方法示例
2017/07/21 Javascript
Vue 源码分析之 Observer实现过程
2018/03/29 Javascript
vue单页面在微信下只能分享落地页的解决方案
2019/04/15 Javascript
JS实现获取当前所在周的周六、周日示例分析
2019/05/11 Javascript
通过实例学习React中事件节流防抖
2019/06/17 Javascript
python写的ARP攻击代码实例
2014/06/04 Python
Python中关于使用模块的基础知识
2015/05/24 Python
浅谈Scrapy框架普通反爬虫机制的应对策略
2017/12/28 Python
PyTorch上实现卷积神经网络CNN的方法
2018/04/28 Python
python 模拟贷款卡号生成规则过程解析
2019/08/30 Python
python实现自动化报表功能(Oracle/plsql/Excel/多线程)
2019/12/02 Python
布隆过滤器的概述及Python实现方法
2019/12/08 Python
利用pyecharts读取csv并进行数据统计可视化的实现
2020/04/17 Python
Python3+RIDE+RobotFramework自动化测试框架搭建过程详解
2020/09/23 Python
python中翻译功能translate模块实现方法
2020/12/17 Python
德国购买健身器材:AsVIVA
2017/08/09 全球购物
即兴演讲稿
2014/01/04 职场文书
中专毕业生自我鉴定
2014/02/02 职场文书
机电一体化求职信
2014/03/10 职场文书
生产文员岗位职责
2014/04/05 职场文书
关于读书的演讲稿
2014/05/07 职场文书
乡镇干部个人对照检查材料思想汇报
2014/10/04 职场文书
单位接收证明格式
2015/06/18 职场文书
高质量“欢迎词”
2019/04/03 职场文书
nginx限制并发连接请求数的方法
2021/04/01 Servers
oracle索引总结
2021/09/25 Oracle
python中的3种定义类方法
2021/11/27 Python