spider/Finnal Work.py

import requests
from bs4 import BeautifulSoup
from lxml import etree
from bs4 import BeautifulSoup
import re
import json
import os

headers = {  # 设置请求头
    "User-agent":
        "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.71 Safari/537.36 Core/1.94.169.400 QQBrowser/11.0.5130.400",
    "Cookie":
        "kg_mid=14e57fa8f8bd5163efe72e9847a80e64; kg_dfid=0jICDR1Z9i6c3Xwh3n02F2uD; kg_dfid_collect=d41d8cd98f00b204e9800998ecf8427e; Hm_lvt_aedee6983d4cfc62f509129360d6bb3d=1669556862,1669856911,1669877618,1669889562; kg_mid_temp=14e57fa8f8bd5163efe72e9847a80e64; KuGoo=KugooID=650152187&KugooPwd=3C564C11588FE543C170C1DE2FE12CBE&NickName=%u0035%u0035%u0035%u0035%u0034%u0034&Pic=http://imge.kugou.com/kugouicon/165/20100101/20100101192931478054.jpg&RegState=1&RegFrom=&t=8ea6a545bf550f5845a622cab06619f65cf61eb2ad5f17b725c792751ad4732d&t_ts=1669893548&t_key=&a_id=1014&ct=1669893548&UserName=%u006b%u0067%u006f%u0070%u0065%u006e%u0036%u0035%u0030%u0031%u0035%u0032%u0031%u0038%u0037; KugooID=650152187; t=8ea6a545bf550f5845a622cab06619f65cf61eb2ad5f17b725c792751ad4732d; a_id=1014; UserName=%u006b%u0067%u006f%u0070%u0065%u006e%u0036%u0035%u0030%u0031%u0035%u0032%u0031%u0038%u0037; mid=14e57fa8f8bd5163efe72e9847a80e64; dfid=0jICDR1Z9i6c3Xwh3n02F2uD; Hm_lpvt_aedee6983d4cfc62f509129360d6bb3d=1669893568",
}


def the_hot_list():
    print("为你创建文件夹music")
    isExists = os.path.exists("./music")
    if not isExists:
        os.makedirs("./music")
        print("music文件夹已经创建完成")
    else:
        print("music文件夹已经存在")
    print("开始爬取内容")
    print("请稍等一会")
    list_url = "https://www.kugou.com/yy/html/rank.html"
    list_req = requests.get(url=list_url, headers=headers)  # 对热门榜网页请求
    soup = BeautifulSoup(list_req.content, "lxml")
    text = re.compile(r"global.features =(.*?);$", re.MULTILINE | re.DOTALL)  # 设置正则表达式帮助找到对应数据
    script = soup.find('script', text=text)
    list_text = script.text[(script.text.find('Hash') - 2):-5]
    m = 0
    list = []
    while (m < len(list_text)):  # 将字符串转化为字典列表方便处理
        n = list_text[m:].find('}')
        dict = eval(list_text[m:m + n + 1])
        list.append(dict)
        m = m + n + 2
    for x in list:
        url = 'https://wwwapi.kugou.com/yy/index.php?r=play/getdata&hash='  # 获取歌曲的地址
        url = url + x["Hash"] + "&album_id=" + str(x['album_id'])
        req = requests.get(url=url, headers=headers)
        req_json = json.loads(req.text)
        song_url = req_json['data'].get('play_url')
        song_req = requests.get(url=song_url)
        with open(f'./music/{req_json["data"].get("audio_name")}.mp3', 'wb') as f:
            f.write(song_req.content)
            f.close()
        song_req.close()
        req.close()
    list_req.close()
    print("爬取完成")


def the_Any_music():
    print("为你创建文件夹music")
    isExists = os.path.exists("./music")
    if not isExists:
        os.makedirs("./music")
        print("music文件夹已经创建完成")
    else:
        print("music文件夹已经存在")
    song_name = input("输入你想获得歌曲名字:")
    url = "http://mobilecdn.kugou.com/api/v3/search/song?format=json&keyword=" + song_name  # 实现不同歌曲的搜索
    req = requests.get(url=url, headers=headers)  # 请求歌曲数据
    n = req.text.find("{")
    list_json = json.loads(req.text[n:])
    total = list_json['data']['total']
    list_num = total // 20  # 获取歌曲总页数进行不同页数爬取
    if list_num == 0:
        list_num =1
    print(f"页数总数为{list_num}")
    num = input("输入你想查看得页数:")
    #song_num = ''
    while True:
        list_url = "http://mobilecdn.kugou.com/api/v3/search/song?format=json&keyword=" + song_name + "&page=" + str(num)
        list_req = requests.get(url=list_url, headers=headers)
        list_json = json.loads(list_req.text[n:])
        y = 1
        for x in list_json['data']['info']:
            print(f"{y}.{x.get('songname')} {x.get('singername')}")
            y = y + 1
        song_num = input("输入你想获取第几首歌曲（或者输入next查看下一页）:")
        if song_num == 'next':
            num = str(int(num) + 1)
            if int(num) >list_num:
                print('已经到达最后1页')
                num = str(list_num)
        else:
            break
    print("开始爬取内容")
    print("请稍等一会")
    y = 1
    song_url = 'https://wwwapi.kugou.com/yy/index.php?r=play/getdata&hash='
    for x in list_json['data']['info']:
        if y == int(song_num):
            song_url = song_url + x.get("hash") + "&album_id=" + str(x.get('album_id'))
            # print(song_url)
        y = y + 1
    # print(song_url)2
    song_req = requests.get(url=song_url, headers=headers)
    song_json = json.loads(song_req.text)
    # print(song_json)
    song_url1 = song_json['data'].get('play_url')
    song_req1 = requests.get(url=song_url1, headers=headers)
    with open(f'./music/{song_json["data"].get("audio_name")}.mp3', 'wb') as f:
        f.write(song_req1.content)
        f.close()
    song_req1.close()
    song_req.close()
    list_req.close()
    req.close()
    print("爬取完成")



menubar = ["功能榜单", "1.爬取酷狗热门榜", "2.爬取任意音乐", "3.退出系统"]
for x in menubar:
    print(x)
feature_option = int(input("输入你想进行的功能:"))
if feature_option == 1:
    the_hot_list()
elif feature_option == 2:
    the_Any_music()
else:
    exit()