Python爬取网站信息requests库的基本代码

基本爬取代码

import requests def getHTMLText(url): try: kv = {'user-agent':'Mozilla/5.0'} r = requests.get(url, headers = kv) r.raise_for_status() r.encoding = r.apparent_encoding return r.text[:1000] except: return '产生异常' if __name__ =='__main__': url = 'http://www.baidu.com/' print(getHTMLText(url))