python网页爬虫通用代码示例

import requests
#import time

def getHTMLText(url):
    try:
        r = requests.get(url,timeout = 30)
        r.raise_for_status()#如果状态不是200，产生HTTPError异常
        #print(r.status_code)
        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))