咪咕音乐爬虫

import requests
import json


def beautifulJSON(value):
    return json.dumps(value, ensure_ascii=False, sort_keys=True, indent=4, separators=(",", ": "))


def searchAll(name, pageNo=1):
    url = f"https://c.musicapp.migu.cn/v1.0/content/search_all.do?text={name}&pageNo={pageNo}&pageSize=20&isCopyright=1&sort=1&searchSwitch=%7B%22song%22%3A1%2C%22album%22%3A0%2C%22singer%22%3A0%2C%22tagSong%22%3A1%2C%22mvSong%22%3A0%2C%22bestShow%22%3A1%7D"
    headers = {
        "content-type": "application/json",
        "channel": "0140210",
        "User-Agent": "Mozilla/5.0 (iPhone; CPU iPhone OS 15_6_1 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Mobile/15E148 MicroMessenger/8.0.31(0x18001f2a) NetType/WIFI Language/zh_CN",
        "Referer": "https://servicewechat.com/",
    }
    res_data = json.loads(requests.get(url=url, headers=headers).text)
    if not res_data.get("songResultData"):
        return
    if len(res_data.get("songResultData").get("result")) == 0:
        return
    song_list = res_data.get("songResultData").get("result")
    for i in range(len(song_list)):
        item = song_list[i]
        singers = ""
        imgItems = []
        for j in item.get("singers"):
            singers += j.get("name") + " / "
        for j in item.get("imgItems"):
            imgItems.append(j.get("img"))
        url = analysis_url(contentId=item.get("contentId"), copyrightId=item.get("copyrightId"), resourceType=item.get("resourceType"))
        song_list[i] = {"name": item.get("name"), "singers": singers[:-3], "lyricUrl": item.get("lyricUrl"), "imgItems": imgItems, "url": url}

    print(beautifulJSON(song_list))


def analysis_url(contentId, copyrightId, resourceType):
    url = f"https://app.c.nf.migu.cn/strategy/listen-url/v2.4?contentId={contentId}©rightId={copyrightId}&lowerQualityContentId=600902000006889010&resourceType={resourceType}&toneFlag=PQ"
    headers = {"User-Agent": "MGMobileMusic/7.20.2 (iPhone; iOS 15.6.1; Scale/3.00)", "channel": "0140070"}
    res_data = json.loads(requests.get(url=url, headers=headers).text)
    if res_data.get("code") == "000000":
        return res_data.get("data").get("url")
    print(res_data.get("info"))
    return ""


if __name__ == "__main__":
    searchAll("周杰伦")