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BeautifulSoup库解析HTML基本使用教程
Mar 31 Python
Python中的左斜杠、右斜杠(正斜杠和反斜杠)
Aug 30 Python
django实现前后台交互实例
Aug 07 Python
基于python3实现socket文件传输和校验
Jul 28 Python
使用EduBlock轻松学习Python编程
Oct 08 Python
解决使用PyCharm时无法启动控制台的问题
Jan 19 Python
Python 实现大整数乘法算法的示例代码
Sep 17 Python
利用Python的turtle库绘制玫瑰教程
Nov 23 Python
PyTorch实现ResNet50、ResNet101和ResNet152示例
Jan 14 Python
TensorBoard 计算图的可视化实现
Feb 15 Python
解决Pycharm 中遇到Unresolved reference 'sklearn'的问题
Jul 13 Python
python实现调用摄像头并拍照发邮箱
Apr 27 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
过滤掉PHP数组中的重复值的实现代码
2011/07/17 PHP
PHP面向对象继承用法详解(优化与减少代码重复)
2016/12/02 PHP
Zend Framework入门教程之Zend_Registry组件用法详解
2016/12/09 PHP
PHP基于XMLWriter操作xml的方法分析
2017/07/17 PHP
抽出www.templatemonster.com的鼠标悬停加载大图模板的代码
2007/07/11 Javascript
Select标签下拉列表二级联动级联实例代码
2014/02/07 Javascript
Javascript基础知识(三)BOM,DOM总结
2014/09/29 Javascript
JS获得图片alt信息的方法
2015/04/01 Javascript
JS及PHP代码编写八大排序算法
2016/07/12 Javascript
详解Javascript中的原型OOP
2016/10/12 Javascript
JS实现Ajax的方法分析
2016/12/20 Javascript
angular.js 路由及页面传参示例
2017/02/24 Javascript
关于在vue-cli中使用微信自动登录和分享的实例
2017/06/22 Javascript
JS库之Three.js 简易入门教程(详解之一)
2017/09/13 Javascript
vue + vuex todolist的实现示例代码
2018/03/09 Javascript
JavaScript实现短暂提示框功能
2018/04/04 Javascript
在Vue中使用axios请求拦截的实现方法
2018/10/25 Javascript
jQuery实现的点击图片居中放大缩小功能示例
2019/01/16 jQuery
jQuery位置选择器用法实例分析
2019/06/28 jQuery
js时间转换毫秒的实例代码
2019/08/21 Javascript
微信小程序自定义扫码功能界面的实现代码
2020/07/02 Javascript
python中常用检测字符串相关函数汇总
2015/04/15 Python
使用Python脚本生成随机IP的简单方法
2015/07/30 Python
Python中内建函数的简单用法说明
2016/05/05 Python
python字符串的常用操作方法小结
2016/05/21 Python
理解Python中的绝对路径和相对路径
2017/08/30 Python
TF-IDF与余弦相似性的应用(二) 找出相似文章
2017/12/21 Python
python实现文件的分割与合并
2019/08/29 Python
Python编译为二进制so可执行文件实例
2019/12/23 Python
基于Pytorch版yolov5的滑块验证码破解思路详解
2021/02/25 Python
缅甸网上购物:Shop.com.mm
2017/12/05 全球购物
小蚁科技官方商店:YI Technology
2019/08/23 全球购物
俄罗斯电动工具和设备购物网站:Vseinstrumenti.ru
2020/11/12 全球购物
入党自我评价优缺点
2014/01/25 职场文书
2014院党委领导班子及其成员群众路线对照检查材料思想汇报
2014/10/04 职场文书
适合后台管理系统开发的12个前端框架(小结)
2021/06/29 Javascript