Python

python 爬取酷狗音乐

admin 2240 次阅读 约 1 分钟
music python

声明

注意

此代码仅用于爬虫技术的学习交流，如有侵权，请联系站长。

引言

自己写的一个爬虫工具，我这个人比较喜欢离线的东西，当然，只有掌握在自己手心中的才会安心。这也催生出了这个小工具。后期可能还会加入其它网站的爬取操作。
i> 收费的也可以下载嗷~

直接上代码吧

# coding=gbk
import requests
import os
import json
import time

from urllib.parse import unquote


class kugou:
    def __init__(self, name, page=1):
        print("正在初始化")
        self.name = name
        self.reqId = "66732db1-8977-11eb-92ee-2b146622418c"
        self.page = page
        self.init()
        self.searchURL = "http://bd.kuwo.cn/api/www/search/searchMusicBykeyWord?key=" + str(
            name) + "&pn=" + str(self.page) + "&rn=30&httpsStatus=1&reqId=" + self.reqId
        self.songName = ""
        self.songList = {}
        self.songId = 0
        self.headers = {
            'Accept': 'application/json, text/plain, */*',
            'Accept-Encoding': 'gzip, deflate',
            'Accept-Language': 'zh-CN,zh;q=0.9',
            'Connection': 'keep-alive',
            'Cookie': '_ga=GA1.2.162059578.1616242395; _gid=GA1.2.1967165994.1616242395; _gat=1;',
            'DNT': '1',
            'Host': 'bd.kuwo.cn',
            'Referer': 'http://bd.kuwo.cn/search/list?key=%E9%BA%BB%E9%9B%80',
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36',
        }
        self.headers2 = {
            '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=0.9',
            'Accept-Encoding': 'gzip, deflate',
            'Accept-Language': 'zh-CN,zh;q=0.9',
            'Cache-Control': 'max-age=0',
            'Connection': 'keep-alive',
            'Cookie': '_ga=GA1.2.162059578.1616242395; _gid=GA1.2.1967165994.1616242395; kw_token=',
            'DNT': '1',
            'Host': 'bd.kuwo.cn',
            'Upgrade-Insecure-Requests': '1',
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36',
        }
        print("初始化结束...")
        self.search()
        self.show()
        self.check()
        self.getLink()

    def init(self):
        self.cookiesGetter = requests.get(url="http://bd.kuwo.cn/search/list?key=" + str(self.name))

    def search(self):
        print("正在检索...")
        self.headers["csrf"] = str(self.cookiesGetter.cookies.get("kw_token"))
        self.headers["Cookie"] = self.headers["Cookie"] + "kw_token=" + str(self.cookiesGetter.cookies.get("kw_token"))
        try:
            content = requests.get(url=self.searchURL, headers=self.headers).content
            self.searchResult = json.loads(content)["data"]["list"]
            self.num = 0
            for i in self.searchResult:
                self.songList[self.num] = (i["name"], i["artist"], i["songTimeMinutes"], i["rid"])
                self.num += 1
            print("检索结束...共计查询结果" + str(self.num) + "条")
        except requests.exceptions as e:
            print("检索时故障发生在连接阶段，可能酷狗音乐API变更或连接不稳定\n" + e)
        except Exception as e:
            print("JSON 解析故障，服务器返回值不符合模板规范，可能API变更\n" + e)

    def show(self):
        self.num = 0
        print("{:<3}{:<20}{:<20}{:<8}{:<18}".format("编号", "名称", "歌手", "时长", "sid"))
        for i in self.songList:
            print("{:<3}{:<20}{:<20}{:<8}{:<18}".format(self.num,
                                                        str(self.songList[i][0]),
                                                        str(self.songList[i][1]),
                                                        str(self.songList[i][2]),
                                                        str(self.songList[i][3])
                                                        ), end="\n")
            self.num += 1

    def getLink(self):
        print("当前页：" + str(self.page) + "下载歌曲序号(-上一页 +下一页):")
        s = input()
        if s == '+':
            self.page += 1
            self.__init__(self.name, self.page)
        elif s == '-':
            self.page -= 1
            if self.page <= 0:
                print("[!] 页码不合法！")
                self.__init__(self.name, 1)
            self.__init__(self.name, self.page)

        s = int(s)

        songName = self.songList[s][0]
        songArtist = self.songList[s][1]
        songTime = self.songList[s][2]
        songSid = self.songList[s][3]
        self.songId = songSid
        self.headers2["csrf"] = str(self.cookiesGetter.cookies.get("kw_token"))
        self.headers2["Cookie"] = self.headers["Cookie"] + "kw_token=" + str(self.cookiesGetter.cookies.get("kw_token"))
        self.downloadURL = "http://bd.kuwo.cn/url?format=mp3&rid=" + str(self.songId) + \
                           "&response=url&type=convert_url3&br=969kmp3&from=web&t=" + str(
            int(time.time())) + "000&httpsStatus=1" + \
                           "&reqId=" + self.reqId
        try:
            content = requests.get(self.downloadURL, headers=self.headers2).content
            files = json.loads(content)["url"]
            print(
                "[#] 歌曲名称：" + songName + "\n[#] 歌手：" + songArtist + "\n[#] 歌曲时长" + songTime + "\n[#] 歌曲ID" + str(
                    songSid) + "\n[$]即将下载")
            self.download(songName, songArtist, files)
        except requests.exceptions as e:
            print("获取链接时故障发生在连接阶段，可能酷狗音乐API变更或连接不稳定\n" + e)
        except Exception as e:
            print("JSON 解析故障，服务器返回值不符合模板规范，可能API变更\n" + e)

    def download(self, songName, songArtist, files):
        try:
            with open("download/" + songName + "-" + songArtist + ".mp3", "wb+") as f:
                f.write(requests.get(files).content)
        except requests.exceptions as e:
            print("下载时发生故障，可能酷狗音乐进行校验或连接不稳定\n" + e)

    def check(self):
        if not os.path.exists("download"):
            os.makedirs("download")


class _5Sing:
    def __init__(self, name, page=1):
        self.name = name
        self.page = page
        self.searchURL = "http://search.5sing.kugou.com/home/json?keyword=" + \
                         name + "sort=1&page=" + str(page) + "&filter=0&type=0"
        self.searchHeader = {'Accept': 'application/json, text/javascript, */*; q=0.01',
                             'Accept-Encoding': 'gzip, deflate',
                             'Accept-Language': 'zh-CN,zh;q=0.9',
                             'Connection': 'keep-alive',
                             'Referer': 'http://search.5sing.kugou.com/home/index?keyword=',
                             'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36',
                             'X-Requested-With': 'XMLHttpRequest',
                             }

    def init(self):
        self.cookiesGetter = requests.get(url="http://search.5sing.kugou.com/home/index?keyword=" + str(self.name))

    def getList(self):
        print("正在检索...")
        try:
            list_raw = requests.get(url=self.searchURL, headers=self.searchHeader).content.decode('unicode_escape')
            self.searchResult = json.loads(list_raw)["list"]
        except requests.exceptions as e:
            print("获取链接时故障发生在连接阶段，可能酷狗音乐API变更或连接不稳定\n" + e)
        except Exception as e:
            print("JSON 解析故障，服务器返回值不符合模板规范，可能API变更\n" + e)

if __name__ == '__main__':

    _5Sing("星星电灯")

    try:
        print("歌曲名称：", end="")
        song = input()

        while song == "":
            print("[!] 歌曲名为空, 请重新输入歌曲名: ", end="")
            song = input()

        print("接口：1.酷狗")
        interfaces = input()
        while interfaces == '' or interfaces not in ("1"):
            print("[!] 接口代号不匹配，请重新选择接口: ", end="")
            interfaces = input()

        if interfaces == "1":
            kugou(song)
        # if interfaces == "2":
        #     _5Sing(song)
    except Exception as e:
        print("存在故障:" + e)

相关文章

同分类推荐
中公教育CTS视频下载 2021 年 04 月 24 日 · 11186 次阅读 GodEyes - 网络空间资产搜索引擎开源项目 2022 年 01 月 07 日 · 11075 次阅读 基于Lively wallpaper的壁纸 2022 年 09 月 26 日 · 9532 次阅读

评论 0

还没有评论，来说点什么吧。

提交后需要审核才会公开。