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使用MD5加密字符串示例
Aug 22 Python
python开发之基于thread线程搜索本地文件的方法
Nov 11 Python
python对象及面向对象技术详解
Jul 19 Python
Python读csv文件去掉一列后再写入新的文件实例
Dec 28 Python
Flask之flask-script模块使用
Jul 26 Python
Python math库 ln(x)运算的实现及原理
Jul 17 Python
tensorflow入门:tfrecord 和tf.data.TFRecordDataset的使用
Jan 20 Python
在django中使用apscheduler 执行计划任务的实现方法
Feb 11 Python
jupyter notebook 多行输出实例
Apr 09 Python
python3+openCV 获取图片中文本区域的最小外接矩形实例
Jun 02 Python
Python在字符串中处理html和xml的方法
Jul 31 Python
python3实现常见的排序算法(示例代码)
Jul 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
十天学会php之第八天
2006/10/09 PHP
php递归实现无限分类生成下拉列表的函数
2010/08/08 PHP
php 遍历目录,生成目录下每个文件的md5值并写入到结果文件中
2016/12/12 PHP
Laravel 5.5基于内置的Auth模块实现前后台登陆详解
2017/12/21 PHP
Javascript document.referrer判断访客来源网址
2020/05/15 Javascript
js中有关IE版本检测
2012/01/04 Javascript
JS阻止用户多次提交示例代码
2014/03/26 Javascript
JavaScript判断textarea值是否为空并给出相应提示
2014/09/04 Javascript
AngularJS入门知识之MVW类框架的编程思想探讨
2014/12/08 Javascript
jQuery实现购物车数字加减效果
2015/03/14 Javascript
简介JavaScript中strike()方法的使用
2015/06/08 Javascript
JS实现在状态栏显示打字效果完整实例
2015/11/02 Javascript
JQuery实现的按钮倒计时效果
2015/12/23 Javascript
基于Vue.js实现数字拼图游戏
2016/08/02 Javascript
Angular工具方法学习
2016/12/26 Javascript
Javascript实现数组中的元素上下移动
2017/04/28 Javascript
基于vue-cli创建的项目的目录结构及说明介绍
2017/11/23 Javascript
js实现鼠标单击Tab表单切换效果
2018/05/16 Javascript
Element Breadcrumb 面包屑的使用方法
2020/07/26 Javascript
Javascript 模拟mvc实现点餐程序案例详解
2020/12/24 Javascript
Python编写屏幕截图程序方法
2015/02/18 Python
Python Tensor FLow简单使用方法实例详解
2020/01/14 Python
浅谈Tensorflow加载Vgg预训练模型的几个注意事项
2020/05/26 Python
python更新数据库中某个字段的数据(方法详解)
2020/11/18 Python
html5基础标签(html5视频标签 html5新标签用法)
2013/12/30 HTML / CSS
Html5页面二次分享的实现
2018/07/30 HTML / CSS
教师试用期自我鉴定
2014/02/12 职场文书
物业经理自我鉴定
2014/03/03 职场文书
演讲稿的写法
2014/05/19 职场文书
规范化管理年活动总结
2014/08/29 职场文书
2014县委书记四风对照检查材料思想汇报
2014/09/21 职场文书
幼儿园教师工作总结2015
2015/04/02 职场文书
诗词赏析-(浣溪沙)
2019/08/13 职场文书
导游词之江南园林狮子林
2019/09/16 职场文书
总结Python常用的魔法方法
2021/05/25 Python
python如何读取和存储dict()与.json格式文件
2022/06/25 Python