爬取网页的通用代码框架

import requests

def getHTMLText(url):
    try:
        headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36'
               }
        r = requests.get(url,  headers=headers, timeout=30)
        r.raise_for_status()    #如果状态不是200，引发HTTPError异常
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return "产生异常"

if __name__ == '__main__':
    url = "http://www.baidu.com"
    print(getHTMLText(url))