python爬取微信公众号文章

本文实例为大家分享了python爬取微信公众号文章的具体代码，供大家参考，具体内容如下

# -*- coding: utf-8 -*-
import requests
from bs4 import beautifulsoup
from requests.exceptions import requestexception
import time
import random
import mysqldb
import threading
import socket
import math
 
socket.setdefaulttimeout(60)#这里对整个socket层设置超时时间。后续文件中如果再使用到socket，不必再设置
 
glock = threading.lock() #定义全局锁
 
category_url= ['http://www.we123.com/gzh/onclick/'] #获取地区分类链接
all_url = [] #
all_urls = [] #所有详细页面链接
proxy_list = [] #ip池
url = 'http://www.we123.com'
page_url = [] #所有分页链接
 
#获取ip池
def get_ip():
  headers = {'user-agent':'mozilla/5.0 (windows nt 6.1; win64; x64) applewebkit/537.36 (khtml, like gecko) chrome/58.0.3029.110 safari/537.36'}
  url = 'http://http-webapi.zhimaruanjian.com'#可以使用芝麻代理，好用稳定还不贵
  resp = requests.get(url,headers=headers)
  obj = resp.json() #获取json ip池对象
  for ip in obj:
    arr = 'http://' + str(ip['ip']) + ':' + str(ip['port'])
    proxy_list.append(arr)
 
#获取页面源码函数
def get_html(url):
  # headers = {}
  user_agent_list = [
    'mozilla/5.0 (windows nt 10.0; wow64) applewebkit/537.36 (khtml, like gecko) chrome/53.0.2785.104 safari/537.36 core/1.53.3538.400 qqbrowser/9.6.12501.400',
    'mozilla/5.0 (windows nt 10.0; wow64) applewebkit/537.36 (khtml, like gecko) chrome/58.0.3029.110 safari/537.36',
    'mozilla/5.0 (windows nt 10.0; win64; x64; rv:56.0) gecko/20100101 firefox/56.0'
  ]
  # user_agent = random.choice(user_agent_list)
  headers = {
    'user-agent':'mozilla/5.0 (windows nt 10.0; wow64) applewebkit/537.36 (khtml, like gecko) chrome/53.0.2785.104 safari/537.36 core/1.53.3538.400 qqbrowser/9.6.12501.400'
  }
  # 代理，免费的代理只能维持一会可能就没用了，自行更换
  # proxy_list = [
  #   "http://27.192.185.62:3252",
  # ]
  # proxy_ip = random.choice(proxy_list)
  # proxies = {'http': proxy_ip}
  # print(str(url))
  try:
    resp = requests.get(url,headers=headers)
    # print("72行：status_code = " + str(resp.status_code))
    # print(type(resp.text))
    # print(resp.url) # 请求的url
    if resp.status_code == 200:
      return resp
    elif resp.status_code == 404:
      return resp
    elif resp.status_code == 500:
      return resp
    return resp
  except runtimeerror:
    print("超时")
    return "error"
  except connectionerror:
    print("连接超时")
    return "error"
  except requestexception:
    print("http请求父类错误")
    with open('url_exception.txt','a+', encoding='utf-8') as f:
      f.write(str(url))
      f.write('\n')
    return "error"
 
#获取区域分类链接
def get_categoty_url():
  url = 'http://www.we123.com/gzh/onclick/'
  resp = get_html(url)
  soup = beautifulsoup(resp.text,'lxml')
  html = soup.select('div.div-subs2 > div.divst-content > div.divst-subs > li > a')
  # 获取区域分类链接
  for i in html:
    city = i['href'].split("/")[-1]
    if (city == '海外' or city == '*' or city == '澳门'):
      continue
    url = url + i['href']
    category_url.append(url)
  print(category_url)
 
 
#获取每个区域下所有分页链接
def get_page_url(url):
  city = url.split('/')[-1]
  html = get_html(url)
  if html == "error":
    print("98行：connect url error")
    time.sleep(random.randint(10,20))
    return "error"
  soup = beautifulsoup(html.text,'lxml')
  #获取总条数
  all_nums = soup.select("div.page > a > b")
  if len(all_nums) == 0:
    return "error"
  else:
    all_nums = soup.select("div.page > a > b")[0].get_text()
  #获取总分页数
  all_pages = math.ceil((int(all_nums) / 30))
  #获取所有分页链接
  all_page_url = []
  for i in range(0,int(all_pages)):
    page_url = 'http://www.we123.com/e/action/listinfo.php?page=' + str(i) + '&classid=45&line=30&tempid=10&orderby=onclick&myorder=0&totalnum=' + str(all_nums)
    all_page_url.append(page_url)
  return all_page_url
 
# 获取所有详细页面链接
def get_page_urls():
    global page_url
    c_url = category_url.pop()
    print('121 行：请求链接' + c_url)
    page_url = get_page_url(c_url) #获取每个区域下面的所有分页链接
 
# 获取所有详细页面链接
def get_info_urls():
  while true:
    global page_url #设置全局变量
    glock.acquire() #加锁
    if len(page_url) == 0:
      glock.release() #解锁
      print('131 行：category_url 为空')
      break
    else:
      p_url = page_url.pop()
      print('135 行：请求链接' + p_url)
      glock.release() #解锁
 
      glock.acquire() #加锁
      html = get_html(p_url)
      if html == "error":
        print("141行：connect url error")
        time.sleep(2)
        return
      soup = beautifulsoup(html.text,'lxml')
      info_urls = soup.select('div.gzhright > div.gzh_list > ul > li > a')
      for x in info_urls:
        i_url = url + x['href']
        all_urls.append(i_url)
      print("库存链接共:" + str(len(all_urls)))
    glock.release() #解锁
#获取每一页需要的数据
def get_data():
  while true:
    global all_urls #设置全局变量
    glock.acquire() #加锁
    print("当前库存："+str(len(all_urls)))
    if len(all_urls) == 0:
      glock.release() #解锁
      print('159 行 ：all_urls 为空')
      break
    else:
      url = all_urls.pop()
      print("开始抓取数据：" + url)
      glock.release() #解锁
      time.sleep(1) #睡眠1秒钟
      html = get_html(url)
      if html == "error":
        print("168行：connect url error")
        time.sleep(random.randint(2, 4))
        return
      html.encoding='utf-8' #显式地指定网页编码，一般情况可以不用
      soup = beautifulsoup(html.text,'lxml')
      #公众号名称
      names = soup.select('div.artcleleft > div.xcxnry > div.xcxtop > div.xcxtop_left > div.gzhtop_logo > h1')
      #微信号id
      accounts = []
      accounts.append(soup.select('div.artcleleft > div.xcxnry > div.xcxtop > div.xcxtop_left > div.gzhtop_logo > p')[0])
      #微信头像
      imgs = soup.select('div.artcleleft > div.xcxnry > div.xcxtop > div.xcxtop_left > div.gzhtop_logo > img')
      #公众号二维码
      qr_codes= soup.select('div.artcleleft > div.xcxnry > div.xcxtop > div.xcxtop_right > img')
      #介绍
      descs = soup.select('div.artcleleft > div.xcxnry > div.xcxinfo')
      #公众号分类
      categorys = []
      category = ''
      cate = soup.select('div.artcleleft > div.xcxnry > div.xcxtop > div.xcxtop_left > div.xcx_p > span > a')
      if not len(cate) == 0:
        category = cate[0].get_text()
      else:
        category = '综合'
      glock.acquire() #加锁
      for name,account,img,qr_code,desc in zip(names,accounts,imgs,qr_codes,descs):
        data = {
          'name':name.get_text(),
          'category':category,
          'account':account.get_text().split("：")[-1],
          'img':img['src'],
          'qr_code':qr_code['src'],
          'desc':desc.get_text()
        }
        add_data(data,url)
      glock.release() #解锁
#添加数据
def add_data(data,url):
  con = mysqldb.connect('127.0.0.1','root','root','test',charset="utf8",use_unicode=true)
  cursor = con.cursor()
  # exit()
  insert_sql = """
    insert ignore into weixin5(w_name,category,account,img,qr_code,introduce)
    values (%s,%s,%s,%s,%s,%s)
    """
  print('212行 ：' + data['name'] + '_' + data['account'] + '添加成功！-' + url)
  try:
    cursor.execute(insert_sql,(data['name'],data['category'],data['account'],data['img'],data['qr_code'],str(data['desc'])))
    con.commit()
  except:
    all_urls.insert(0,url)
    print("218行：" + url + '插入失败')
    con.rollback()
  con.close()
 
# 将时间字符串转化为时间戳
def time_to(dt):
  timearray = time.strptime(dt, "%y年%m月%d日")
  timestamp = int(time.mktime(timearray))
  return timestamp
 
#启动多线程爬取
def main():
  for x in range(3):
    th = threading.thread(target=get_info_urls)
    th.start()
     # get_info_urls()
  time.sleep(3)
  for x in range(5):
    th = threading.thread(target=get_data)
    th.start()
 
if __name__ == '__main__':
  # 计时
  t1 = time.time()
  # 调用函数
  get_ip() #获取ip池
  get_page_urls()
  time.sleep(2)
  # get_categoty_url()
  main()
  print(time.time() - t1)

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持。