[Python爬虫系列]1— 音乐平台外链以及歌词提取

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22

def cloudMusic(input):
    id = re.search('id=(.*)$', input).group(1)
    # print(id)
    url = ' http://music.163.com/song/media/outer/url?id=' + id + '.mp3'
    ## 获取详细信息
    detailUrl = 'http://music.163.com/api/song/detail/?&ids=[' + id + ']&csrf_token='

    ## 获取歌词信息
    lycUrl = 'http://music.163.com/api/song/media?id=' + id
    detail = json.loads(get_one_page(detailUrl))
    name = detail["songs"][0]["name"]
    author = detail["songs"][0]["artists"][0]["name"]
    pic = detail["songs"][0]["album"]["picUrl"]
    lyric = json.loads(get_one_page(lycUrl))['lyric']
    return {
        "title": name,
        "author": author,
        "url": url,
        "pic": pic,
        "lrc": lyric

    }

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29

def kuwo(input):
    id = re.search('.*/(.*)$', input).group(1)
    # print(id)
    url = 'http://player.kuwo.cn/webmusic/st/getNewMuiseByRid?rid=MUSIC_' + id
    # 解决中文乱码
    html = get_one_page(url)
    # 歌名
    title = pq(html)('name').text()
    # 歌手
    author = pq(html)('singer').text()
    # 链接地址
    url = 'http://' + pq(html)('mp3dl').text() + '/resource/' + pq(html)('mp3path').text()
    # 封面图片
    pic = pq(html)('artist_pic').text()

    lyc = json.loads(re.search('lrcList = (.*?])', get_one_page(input)).group(1))
    ## 解析歌词
    lyric = ''
    for item in lyc:
        time = '[' + timeTag(seconds=float(item["time"])) + ']'
        lyric = lyric + time + item['lineLyric'] + '\n'
    return {
        "title": title,
        "author": author,
        "url": url,
        "pic": pic,
        "lrc": lyric

    }

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37

def xiaMi(input):
    id=re.search('.*/(.*)$',input).group(1)
    #print(id)

    ## 恺撒阵列
    import urllib
    def caesar(location):
        num = int(location[0])
        avg_len, remainder = int(len(location[1:]) / num), int(len(location[1:]) % num)
        result = [location[i * (avg_len + 1) + 1: (i + 1) * (avg_len + 1) + 1] for i in range(remainder)]
        result.extend([location[(avg_len + 1) * remainder:][i * avg_len + 1: (i + 1) * avg_len + 1] for i in range(num-remainder)])
        url = urllib.parse.unquote(''.join([''.join([result[j][i] for j in range(num)]) for i in range(avg_len)]) + \
                            ''.join([result[r][-1] for r in range(remainder)])).replace('^','0')
        return url

    ## json链接
    jsonUrl='https://www.xiami.com/song/playlist/id/'+id+'%20/object_name/default/object_id/0/cat/json'
    headers = {'User-Agent':'Mozilla/5.0 (iPhone; CPU iPhone OS 7_0 like Mac OS X; en-us) AppleWebKit/537.51.1 (KHTML, like Gecko) Version/7.0 Mobile/11A465 Safari/9537.53',
    'Referer':'http://www.xiami.com/song/playlist/id/'+id
    }

    ## 没有headers就不行
    info=json.loads(requests.get(jsonUrl,headers=headers).content)['data']['trackList'][0]
    #print(info)
    name=info['songName']
    author=info['artist']
    url='http:'+caesar(info['location'])
    lrc=requests.get('http:'+info['lyric_url']).text
    pic='http:'+info['pic']
    return{
    "title":name,
    "author":author,
    "url":url,
    "pic":pic,
    "lrc":lrc

    }

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55

def qqMusic(input):
    html=get_one_page(input)
    # 歌曲的基本信息
    songData=json.loads(re.search('g_SongData = (.*?);',html).group(1))
    # print(songData)
    name=songData['songtitle']
    author=songData['singername']
    songid=songData['songid']
    pic='https://y.gtimg.cn/music/photo_new/T002R300x300M000'+songData['albummid']+'.jpg?max_age=2592000'
    ## 获取vkey
    vkeyUrl = 'https://u.y.qq.com/cgi-bin/musicu.fcg?data={"req_0":{"module":"vkey.GetVkeyServer","method":"CgiGetVkey","param":\
{"guid":"0","songmid":["' +songData['songmid'] + '"],"uin":"0"}}}'
    # print(vkeyUrl)
    data=json.loads(get_one_page(vkeyUrl))['req_0']['data']
    print("data",data)
    #print(data)
    vkey=data['midurlinfo'][0]['purl']
    filename=data['midurlinfo'][0]['filename']
    url='https://isure.stream.qqmusic.qq.com/'+vkey
    lrcUrl="https://c.y.qq.com/lyric/fcgi-bin/fcg_query_lyric_new.fcg"
    #print(lrcUrl)
    #lrc=re.search('CDATA\[(.*)\]\]>',get_one_page(lrcUrl),re.S).group(1)
    # 模拟请求歌词
    headers={
    'accept': 'application/json, text/javascript, */*; q=0.01',
    'accept-encoding': 'gzip, deflate, br',
    'accept-language': 'zh-CN,zh;q=0.9',
    'origin': 'https://y.qq.com',
    'referer': 'https://y.qq.com/portal/player.html',
    'user-agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'
}
    params={
        '-': 'MusicJsonCallback_lrc',
        'pcachetime': '1548902360952',
        'songmid': songData['songmid'],
        'g_tk': '5381',
        'loginUin': 0,
        'hostUin': 0,
        'format': 'json',
        'inCharset': 'utf8',
        'outCharset': 'utf-8',
        'notice': 0,
        'platform': 'yqq.json',
        'needNewCode': 0
    }
    lrc=base64.b64decode(json.loads(requests.get(lrcUrl,headers=headers,params=params).text)['lyric']).decode('UTF-8')
    return{
    "title":name,
    "author":author,
    "url":url,
    "pic":pic,
    "lrc":lrc

}