python爬蟲_微信公眾號推送信息爬取的實例

更新時間：2017年10月23日 10:03:08 作者：ChaseChoi

下面小編就為大家?guī)硪黄猵ython爬蟲_微信公眾號推送信息爬取的實例。小編覺得挺不錯的，現(xiàn)在就分享給大家，也給大家做個參考。一起跟隨小編過來看看吧

問題描述

利用搜狗的微信搜索抓取指定公眾號的最新一條推送，并保存相應(yīng)的網(wǎng)頁至本地。

注意點

搜狗微信獲取的地址為臨時鏈接，具有時效性。

公眾號為動態(tài)網(wǎng)頁(JavaScript渲染)，使用requests.get()獲取的內(nèi)容是不含推送消息的，這里使用selenium+PhantomJS處理

代碼

#! /usr/bin/env python3
from selenium import webdriver
from datetime import datetime
import bs4, requests
import os, time, sys

# 獲取公眾號鏈接
def getAccountURL(searchURL):
 res = requests.get(searchURL)
 res.raise_for_status()
 soup = bs4.BeautifulSoup(res.text, "lxml")
 # 選擇第一個鏈接
 account = soup.select('a[uigs="account_name_0"]')
 return account[0]['href']

# 獲取首篇文章的鏈接，如果有驗證碼返回None
def getArticleURL(accountURL):
 browser = webdriver.PhantomJS("/Users/chasechoi/Downloads/phantomjs-2.1.1-macosx/bin/phantomjs")
 # 進入公眾號
 browser.get(accountURL)
 # 獲取網(wǎng)頁信息
 html = browser.page_source
 accountSoup = bs4.BeautifulSoup(html, "lxml")
 time.sleep(1)
 contents = accountSoup.find_all(hrefs=True)
 try:
  partitialLink = contents[0]['hrefs']
  firstLink = base + partitialLink
 except IndexError:
  firstLink = None 
  print('CAPTCHA!')
 return firstLink

# 創(chuàng)建文件夾存儲html網(wǎng)頁，以時間命名
def folderCreation():
 path = os.path.join(os.getcwd(), datetime.now().strftime('%Y-%m-%d_%H-%M-%S'))
 try:
  os.makedirs(path)
 except OSError as e:
  if e.errno != errno.EEXIST:
   raise
  print("folder not exist!")
 return path

# 將html頁面寫入本地
def writeToFile(path, account, title):
 myfile = open("{}/{}_{}.html".format(path, account, title), 'wb')
 myfile.write(res.content)
 myfile.close()

base ='https://mp.weixin.qq.com'
accountList = ['央視新聞', '新浪新聞','鳳凰新聞','羊城晚報']
query = 'http://weixin.sogou.com/weixin?type=1&s_from=input&query='

path = folderCreation()

for index, account in enumerate(accountList):
 searchURL = query + account
 accountURL = getAccountURL(searchURL)
 time.sleep(10)
 articleURL = getArticleURL(accountURL)
 if articleURL != None:
  print("#{}({}/{}): {}".format(account, index+1, len(accountList), accountURL))
  # 讀取第一篇文章內(nèi)容
  res = requests.get(articleURL)
  res.raise_for_status()
  detailPage = bs4.BeautifulSoup(res.text, "lxml")
  title = detailPage.title.text
  print("標(biāo)題: {}\n鏈接: {}\n".format(title, articleURL))
  writeToFile(path, account, title)
 else:
  print('{} files successfully written to {}'.format(index, path))
  sys.exit()

print('{} files successfully written to {}'.format(len(accountList), path))

參考輸出

Terminal輸出