简单的request实例

不爱缺氧i

已于 2023-07-16 07:05:53 修改

阅读量49

点赞数

文章标签： python 开发语言爬虫

于 2023-07-16 07:02:14 首次发布

本文链接：https://blog.csdn.net/qq_38236017/article/details/131746649

版权

import requests
import re

url = "https://www.dy2018.com"
head = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.87 Safari/537.36 SE 2.X MetaSr 1.0"
    }

#获取电影名字和url
def getdy():
    req = requests.get(url,headers=head)
    req.encoding = "gb2312"
    r = req.text
    obj = re.compile(r'''<li><a href='(?P<xzurl>.*?)' title=".*?>(?P<name>.*?)</a><span><font color=.*?>.*?</font></span></li>'''
                , re.S)
    result = obj.finditer(r)
    for item in result:
        dxz = url+item.group("xzurl")
        dym = item.group("name").strip("<strong><font color='FF0000'></font></")
        print(dym)
        li = paljy(dxz,dym)



def paljy(url,name):
    req = requests.get(url, headers=head)
    req.encoding = "gb2312"
    r = req.text
    #print(r)
    #print("ftp链接")
    obj = re.compile(r'''ftp://(?P<lianjie>.*?)">'''
                , re.S)
    resul = obj.finditer(r)
    lianjieli = []

    for item in resul:
        ftpaaaa =  "ftp://"+item.group("lianjie")
        print(ftpaaaa)
        lianjieli.append(ftpaaaa)


    obj = re.compile(r'<a href="magnet:?(?P<malian>.*?)tr=http'
                , re.S)
    #print("夸克链接")
    resul1 = obj.finditer(r)
    for item in resul1:
        kkkkkk = "magnet:"+item.group("malian").strip("&")
        print(kkkkkk)
        lianjieli.append(kkkkkk)

    return lianjieli

if __name__ == '__main__':
    getdy()