yt_dlp/extractor/zingmp3.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7 )
   8
   9
  10 class ZingMp3BaseIE(InfoExtractor):
  11     _VALID_URL_TMPL = r'https?://(?:mp3\.zing|zingmp3)\.vn/(?:%s)/[^/]+/(?P<id>\w+)\.html'
  12     _GEO_COUNTRIES = ['VN']
  13
  14     def _extract_item(self, item, fatal):
  15         item_id = item['id']
  16         title = item.get('name') or item['title']
  17
  18         formats = []
  19         for k, v in (item.get('source') or {}).items():
  20             if not v:
  21                 continue
  22             if k in ('mp4', 'hls'):
  23                 for res, video_url in v.items():
  24                     if not video_url:
  25                         continue
  26                     if k == 'hls':
  27                         formats.extend(self._extract_m3u8_formats(
  28                             video_url, item_id, 'mp4',
  29                             'm3u8_native', m3u8_id=k, fatal=False))
  30                     elif k == 'mp4':
  31                         formats.append({
  32                             'format_id': 'mp4-' + res,
  33                             'url': video_url,
  34                             'height': int_or_none(self._search_regex(
  35                                 r'^(\d+)p', res, 'resolution', default=None)),
  36                         })
  37             else:
  38                 formats.append({
  39                     'ext': 'mp3',
  40                     'format_id': k,
  41                     'tbr': int_or_none(k),
  42                     'url': self._proto_relative_url(v),
  43                     'vcodec': 'none',
  44                 })
  45         if not formats:
  46             if not fatal:
  47                 return
  48             msg = item['msg']
  49             if msg == 'Sorry, this content is not available in your country.':
  50                 self.raise_geo_restricted(countries=self._GEO_COUNTRIES, metadata_available=True)
  51             self.raise_no_formats(msg, expected=True)
  52         self._sort_formats(formats)
  53
  54         subtitles = None
  55         lyric = item.get('lyric')
  56         if lyric:
  57             subtitles = {
  58                 'origin': [{
  59                     'url': lyric,
  60                 }],
  61             }
  62
  63         album = item.get('album') or {}
  64
  65         return {
  66             'id': item_id,
  67             'title': title,
  68             'formats': formats,
  69             'thumbnail': item.get('thumbnail'),
  70             'subtitles': subtitles,
  71             'duration': int_or_none(item.get('duration')),
  72             'track': title,
  73             'artist': item.get('artists_names'),
  74             'album': album.get('name') or album.get('title'),
  75             'album_artist': album.get('artists_names'),
  76         }
  77
  78     def _real_extract(self, url):
  79         page_id = self._match_id(url)
  80         webpage = self._download_webpage(
  81             url.replace('://zingmp3.vn/', '://mp3.zing.vn/'),
  82             page_id, query={'play_song': 1})
  83         data_path = self._search_regex(
  84             r'data-xml="([^"]+)', webpage, 'data path')
  85         return self._process_data(self._download_json(
  86             'https://mp3.zing.vn/xhr' + data_path, page_id)['data'])
  87
  88
  89 class ZingMp3IE(ZingMp3BaseIE):
  90     _VALID_URL = ZingMp3BaseIE._VALID_URL_TMPL % 'bai-hat|video-clip'
  91     _TESTS = [{
  92         'url': 'http://mp3.zing.vn/bai-hat/Xa-Mai-Xa-Bao-Thy/ZWZB9WAB.html',
  93         'md5': 'ead7ae13693b3205cbc89536a077daed',
  94         'info_dict': {
  95             'id': 'ZWZB9WAB',
  96             'title': 'Xa Mãi Xa',
  97             'ext': 'mp3',
  98             'thumbnail': r're:^https?://.+\.jpg',
  99             'subtitles': {
 100                 'origin': [{
 101                     'ext': 'lrc',
 102                 }]
 103             },
 104             'duration': 255,
 105             'track': 'Xa Mãi Xa',
 106             'artist': 'Bảo Thy',
 107             'album': 'Special Album',
 108             'album_artist': 'Bảo Thy',
 109         },
 110     }, {
 111         'url': 'https://mp3.zing.vn/video-clip/Suong-Hoa-Dua-Loi-K-ICM-RYO/ZO8ZF7C7.html',
 112         'md5': 'e9c972b693aa88301ef981c8151c4343',
 113         'info_dict': {
 114             'id': 'ZO8ZF7C7',
 115             'title': 'Sương Hoa Đưa Lối',
 116             'ext': 'mp4',
 117             'thumbnail': r're:^https?://.+\.jpg',
 118             'duration': 207,
 119             'track': 'Sương Hoa Đưa Lối',
 120             'artist': 'K-ICM, RYO',
 121         },
 122     }, {
 123         'url': 'https://zingmp3.vn/bai-hat/Xa-Mai-Xa-Bao-Thy/ZWZB9WAB.html',
 124         'only_matching': True,
 125     }]
 126     IE_NAME = 'zingmp3'
 127     IE_DESC = 'mp3.zing.vn'
 128
 129     def _process_data(self, data):
 130         return self._extract_item(data, True)
 131
 132
 133 class ZingMp3AlbumIE(ZingMp3BaseIE):
 134     _VALID_URL = ZingMp3BaseIE._VALID_URL_TMPL % 'album|playlist'
 135     _TESTS = [{
 136         'url': 'http://mp3.zing.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html',
 137         'info_dict': {
 138             '_type': 'playlist',
 139             'id': 'ZWZBWDAF',
 140             'title': 'Lâu Đài Tình Ái',
 141         },
 142         'playlist_count': 10,
 143     }, {
 144         'url': 'http://mp3.zing.vn/playlist/Duong-Hong-Loan-apollobee/IWCAACCB.html',
 145         'only_matching': True,
 146     }, {
 147         'url': 'https://zingmp3.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html',
 148         'only_matching': True,
 149     }]
 150     IE_NAME = 'zingmp3:album'
 151
 152     def _process_data(self, data):
 153         def entries():
 154             for item in (data.get('items') or []):
 155                 entry = self._extract_item(item, False)
 156                 if entry:
 157                     yield entry
 158         info = data.get('info') or {}
 159         return self.playlist_result(
 160             entries(), info.get('id'), info.get('name') or info.get('title'))