8.15python暑期实践爬虫

最新推荐文章于 2024-06-16 10:55:10 发布

Minghao00

最新推荐文章于 2024-06-16 10:55:10 发布

阅读量242

点赞数

文章标签： python 爬虫开发语言

本文链接：https://blog.csdn.net/Minghao00/article/details/126352922

版权

# response = urllib.request.urlopen("http://www.baidu.com")
# # print(response.status)
# print(response.getheader("Server"))

# url = "https://www.douban.com"

# url = "http://httpbin.org/pos"
# data = bytes(urllib.parse.urlencode({'name':'eric'}),encoding="utf-")
# headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:103.0) Gecko/20100101 Firefox/103.0"}#伪装
# req = urllib.request.Request(url=url,data=data,headers=headers,method ="POST")
# response = urllib.request.urlopen(req)
# print(req)

# url = "https://www.douban.com"
# headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:103.0) Gecko/20100101 Firefox/103.0"}#伪装
# req = urllib.request.Request(url=url,headers=headers)
# response = urllib.request.urlopen(req)
# print(response.read().decode("utf-8"))

#得到指定URL的网页内容
def askURL(url):
    #用户代理
    head = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:103.0) Gecko/20100101 Firefox/103.0"}
    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)

    #return html
    def main():
        baseurl = "https://movie.douban.com/top250"
        askURL(baseurl)