#! /usr/bin/env python3from selenium import webdriverfrom datetime import datetimeimport bs4, requestsimport 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Nonedef 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# 創建文件夾存儲html網頁，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))  # 讀取第一篇文章內容  res = requests.get(articleURL)  res.raise_for_status()  detailPage = bs4.BeautifulSoup(res.text, "lxml")  print("標題: {}/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))