爬虫简单框架

爬虫简单框架

import  requests
def getHTMLText(url):
    try:
        r=requests.get(url,timeout=30)
        r.raise_for_status()# 如果状态不是200 就引发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))