3 爬取网页的通用代码框架

爬取网页的通用代码框架

 

"""通用代码框架"""


import requests

def getHTMLText(url):
    try:
        r = requests.get(url, timeout = 30)
        r.raise_for_status() # 如果状态码不是200，引发HTTPERROR
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return "产生异常"


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