py每日spider案例之某website影视资源链接下载(厂长资源)

import re
from lxml import etree
import requests


headers = {
    "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
    "accept-language": "zh-CN,zh;q=0.9",
    "cache-control": "no-cache",
    "pragma": "no-cache",
    "priority": "u=0, i",
    "referer": "https://www.cz233.com/",
    "sec-ch-ua": "\"Google Chrome\";v=\"137\", \"Chromium\";v=\"137\", \"Not/A)Brand\";v=\"24\"",
    "sec-ch-ua-mobile": "?0",
    "sec-ch-ua-platform": "\"Windows\"",
    "sec-fetch-dest": "iframe",
    "sec-fetch-mode": "navigate",
    "sec-fetch-site": "cross-site",
    "sec-fetch-storage-access": "active",
    "upgrade-insecure-requests": "1",
    "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/137.0.0.0 Safari/537.36"
}

url = "https://www.cz233.com/v_play/bXZfMjA0NDctbm1fMQ==.html"
response = requests.get(url, headers=headers)

html=etree.HTML(response.text)
href=html.xpath('//iframe/@src')[-1].split('=')[-1]
print(href)


url = "https://pla.py1080p.com:2096/player/py.php"
params = {
    "code": "cs",
    "if": "1",
    "url":href
}
response = requests.get(url, headers=headers, params=params)

mp4=re.findall('mysvg = \'(.*?)\';',response.text)[-1]
print(mp4)

目标网址