利用搜狗的微信搜索抓取指定公衆號的最新一條推送,並保存相應的網頁至本地。html
臨時連接
,具備時效性。JavaScript
渲染),使用requests.get()
獲取的內容是不含推送消息的,這裏使用selenium+PhantomJS
處理#! /usr/bin/env python3 from selenium import webdriver from datetime import datetime import bs4, requests import os, time, sys # 獲取公衆號連接 def getAccountURL(searchURL): res = requests.get(searchURL) res.raise_for_status() soup = bs4.BeautifulSoup(res.text, "lxml") # 選擇第一個連接 account = soup.select('a[uigs="account_name_0"]') return account[0]['href'] # 獲取首篇文章的連接,若是有驗證碼返回None def getArticleURL(accountURL): browser = webdriver.PhantomJS("/Users/chasechoi/Downloads/phantomjs-2.1.1-macosx/bin/phantomjs") # 進入公衆號 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[1]['hrefs'] firstLink = base + partitialLink except IndexError: firstLink = None print('CAPTCHA!') return firstLink # 建立文件夾存儲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): pathToWrite = os.path.join(path, '{}_{}.html'.format(account, title)) myfile = open(pathToWrite, '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") title = detailPage.title.text print("標題: {}\n連接: {}\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))
requests
獲取html文件,再用BeautifulSoup
選擇須要的內容selenium+PhantomJS
獲取html文件,再用BeautifulSoup
選擇須要的內容驗證碼(CAPTCHA)
,輸出提示。此版本代碼沒有對驗證碼作實際處理,須要人爲訪問後,再跑程序,才能避開驗證碼。os.path.join()
構造存儲路徑能夠提升通用性。好比Windows
路徑分隔符使用back slash(\), 而OS X
和 Linux
使用forward slash
(/),經過該函數能根據平臺進行自動轉換。open()
使用b
(binary mode)參數一樣爲了提升通用性(適應Windows
)datetime.now()
獲取當前時間進行命名,並經過strftime()
格式化時間(函數名中的f表明format),具體使用參考下表(摘自 Automate the Boring Stuff with Python)enumerate
的使用: https://stackoverflow.com/questions/3162271/get-loop-count-inside-a-python-for-loopopen()
使用b
參數理由: https://stackoverflow.com/questions/2665866/what-is-the-wb-mean-in-this-code-using-python