py每日spider案例之某website之音乐搜索接口

import requests
import json


headers = {
    "accept": "*/*",
    "accept-language": "zh-CN,zh;q=0.9",
    "cache-control": "no-cache",
    "content-type": "application/json",
    "origin": "https://www.isflac.com",
    "pragma": "no-cache",
    "priority": "u=1, i",
    "referer": "https://www.isflac.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": "empty",
    "sec-fetch-mode": "cors",
    "sec-fetch-site": "same-origin",
    "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",
    "x-livewire;": ""
}
cookies = {
    "_ga": "GA1.1.914540007.1756608480",
    "Hm_lvt_10fd350dcf1fa64836fe2d25b2c77e0a": "1756608480",
    "Hm_lpvt_10fd350dcf1fa64836fe2d25b2c77e0a": "1756608480",
    "HMACCOUNT": "349C61B60410186B",
    "cf_clearance": "AFQ5KutOq6jQ0JrY9H0jztusHw5ZyAFE0Xg608vLg5Y-1756608480-1.2.1.1-M4eDS4PZdmpLHUs9kCoUn3GNxy5yjA4MhmzuozKZhGp_7x3Ozy1TtYh7jB3nJIjopE4uAK6tYhTbVolxAoWJYa65V6wgoQizppWHe9fo.wPjve5Cjqk1zJxup2KtImqsw_uoZI30o38NNbM263Rk1gcCCH1JyND7Ov.xs3wUSKAnYB.7BAs6VO7Q7g4yPAu7mbduJ4xDs7rR3dWBrdl8jA40kNE9VIfrVf2wSbF8wOU",
    "XSRF-TOKEN": "eyJpdiI6ImxaN1FlOXpmSm5IMEVZeGt4K2FPM1E9PSIsInZhbHVlIjoiQ2hDa0pyczl0UytPSkhBVU5vejA3MXpCeTNxU0RVYU42VW1tVVZXUFhEYkFjUlRMZG00cTh3bkRVL05Fb3dLdXdlbVNKbGZ1L3c0Nk1nU1UxWUNjUnUxQnM3Y3NFVzFOREdjMGF6MUNOVU5qODBZTjFtWTk4OWtaN1RNVjZrUHQiLCJtYWMiOiI2ZjRjZDdiZmNmNzdhODgxZmY0MDE3ZmY4ZDIyMjJjNzI0ODJjZTQwZTMxMWUxNDRmNjI0MDNlMGRjZTFhMTYxIiwidGFnIjoiIn0%3D",
    "isflac_session": "eyJpdiI6Ijk3N2phNVhtT3Vzc1FreWVEMDhEelE9PSIsInZhbHVlIjoieXQyWnAyd2hmNVk0ODgyNzVZRVQ1b3Y5NitTZmZoL3F6SXo5RVJWMmRvaEVVZGRxOTZaRHJRN1lHM3BnMllxb2VQN3I4S2FpVDFLOG9RMk1oUmZPMWV0NlRxSG5sZ3ltdXVtM0tuSkkxa1NxbDNwRFNzQ3gyR1BUQmxORHhUdW0iLCJtYWMiOiJiZjhjZDI3ZWY5NTQwODg0ZWQzNTcwZDY2NGFjNTg1MTI1MWMwMzNiN2FkNDRhZDJiODJmYzc2Y2FmMzNiYzY2IiwidGFnIjoiIn0%3D",
    "_ga_HK5Q7N3D5T": "GS2.1.s1756608479$o1$g0$t1756608490$j49$l0$h0"
}
url = "https://www.isflac.com/livewire/update"
data = {
    "_token": "TytLsuaX0XOYbxEzYkW2rvHvVNlRRxz69LzpEcb3",
    "components": [
        {
            "snapshot": "{\"data\":{\"searching\":true,\"query\":\"\",\"type\":\"song\",\"page\":1,\"limit\":20,\"total\":0,\"data_list\":null},\"memo\":{\"id\":\"2fDMnd20sK8ffwPEqbRG\",\"name\":\"search\",\"path\":\"\\/\",\"method\":\"GET\",\"children\":[],\"scripts\":[],\"assets\":[],\"errors\":[],\"locale\":\"zh_CN\"},\"checksum\":\"d32a5b0c4c0f62a0240cc1ee6bf1465d6770386e1fcc99574bab8f8eb3fa3ed4\"}",
            "updates": {
                "query": "周杰伦"
            },
            "calls": [
                {
                    "path": "",
                    "method": "doSearch",
                    "params": []
                }
            ]
        }
    ]
}
data = json.dumps(data, separators=(',', ':'))
response = requests.post(url, headers=headers, cookies=cookies, data=data)

data=(response.json()['components'][0]['snapshot'])
dict=json.loads(data)
key=(dict['data']['data_list'][1]['keys'])
for k in key:
    print('https://www.isflac.com/songs/'+str(k))

站点