用python简单爬取一个网页

1打开编辑器

2撸几行代码

import urllib.request

import urllib.error

def main():

    askURl("http://movie.douban.com/top250?start")

#URL的网页内容
def askURl(url):

    head = {
        "User-Agent": "Mozilla/5.0(Windows NT 10.0;WOW64) AppleWebKit / 537.36(KHTML, likeGecko) Chrome / 80.0.3987.122Safari / 537.36"
    }
    #head伪装一下 告诉机器
    
    request = urllib.request.Request(url,headers=head)
    html = ""
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode("utf-8")
        print(html)
    except urllib.error.URLError as e:
        if hasattr(e,"code"):
            print(e.code)
        if hasattr(e,"reason"):
            print(e.reason)

if __name__ == '__main__':
    #调用函数
    main()