yt_dlp/extractor/ximalaya.py

   1 import math
   2
   3 from .common import InfoExtractor
   4 from ..utils import InAdvancePagedList, str_or_none, traverse_obj, try_call
   5
   6
   7 class XimalayaBaseIE(InfoExtractor):
   8     _GEO_COUNTRIES = ['CN']
   9
  10
  11 class XimalayaIE(XimalayaBaseIE):
  12     IE_NAME = 'ximalaya'
  13     IE_DESC = '喜马拉雅FM'
  14     _VALID_URL = r'https?://(?:www\.|m\.)?ximalaya\.com/(:?(?P<uid>\d+)/)?sound/(?P<id>[0-9]+)'
  15     _TESTS = [
  16         {
  17             'url': 'http://www.ximalaya.com/sound/47740352/',
  18             'info_dict': {
  19                 'id': '47740352',
  20                 'ext': 'm4a',
  21                 'uploader': '小彬彬爱听书',
  22                 'uploader_id': '61425525',
  23                 'uploader_url': 'http://www.ximalaya.com/zhubo/61425525/',
  24                 'title': '261.唐诗三百首.卷八.送孟浩然之广陵.李白',
  25                 'description': "contains:《送孟浩然之广陵》\n作者：李白\n故人西辞黄鹤楼，烟花三月下扬州。\n孤帆远影碧空尽，惟见长江天际流。",
  26                 'thumbnail': r're:^https?://.*\.jpg',
  27                 'thumbnails': [
  28                     {
  29                         'name': 'cover_url',
  30                         'url': r're:^https?://.*\.jpg',
  31                     },
  32                     {
  33                         'name': 'cover_url_142',
  34                         'url': r're:^https?://.*\.jpg',
  35                         'width': 180,
  36                         'height': 180
  37                     }
  38                 ],
  39                 'categories': ['其他'],
  40                 'duration': 93,
  41                 'view_count': int,
  42                 'like_count': int,
  43             }
  44         },
  45         {
  46             'url': 'http://m.ximalaya.com/61425525/sound/47740352/',
  47             'info_dict': {
  48                 'id': '47740352',
  49                 'ext': 'm4a',
  50                 'uploader': '小彬彬爱听书',
  51                 'uploader_id': '61425525',
  52                 'uploader_url': 'http://www.ximalaya.com/zhubo/61425525/',
  53                 'title': '261.唐诗三百首.卷八.送孟浩然之广陵.李白',
  54                 'description': "contains:《送孟浩然之广陵》\n作者：李白\n故人西辞黄鹤楼，烟花三月下扬州。\n孤帆远影碧空尽，惟见长江天际流。",
  55                 'thumbnail': r're:^https?://.*\.jpg',
  56                 'thumbnails': [
  57                     {
  58                         'name': 'cover_url',
  59                         'url': r're:^https?://.*\.jpg',
  60                     },
  61                     {
  62                         'name': 'cover_url_142',
  63                         'url': r're:^https?://.*\.jpg',
  64                         'width': 180,
  65                         'height': 180
  66                     }
  67                 ],
  68                 'categories': ['人文'],
  69                 'duration': 93,
  70                 'view_count': int,
  71                 'like_count': int,
  72             }
  73         }
  74     ]
  75
  76     def _real_extract(self, url):
  77         scheme = 'https' if url.startswith('https') else 'http'
  78
  79         audio_id = self._match_id(url)
  80         audio_info_file = '%s://m.ximalaya.com/tracks/%s.json' % (scheme, audio_id)
  81         audio_info = self._download_json(audio_info_file, audio_id,
  82                                          'Downloading info json %s' % audio_info_file,
  83                                          'Unable to download info file')
  84
  85         formats = [{
  86             'format_id': f'{bps}k',
  87             'url': audio_info[k],
  88             'abr': bps,
  89             'vcodec': 'none'
  90         } for bps, k in ((24, 'play_path_32'), (64, 'play_path_64')) if audio_info.get(k)]
  91
  92         thumbnails = []
  93         for k in audio_info.keys():
  94             # cover pics kyes like: cover_url', 'cover_url_142'
  95             if k.startswith('cover_url'):
  96                 thumbnail = {'name': k, 'url': audio_info[k]}
  97                 if k == 'cover_url_142':
  98                     thumbnail['width'] = 180
  99                     thumbnail['height'] = 180
 100                 thumbnails.append(thumbnail)
 101
 102         audio_uploader_id = audio_info.get('uid')
 103
 104         audio_description = try_call(
 105             lambda: audio_info['intro'].replace('\r\n\r\n\r\n ', '\n').replace('\r\n', '\n'))
 106
 107         return {
 108             'id': audio_id,
 109             'uploader': audio_info.get('nickname'),
 110             'uploader_id': str_or_none(audio_uploader_id),
 111             'uploader_url': f'{scheme}://www.ximalaya.com/zhubo/{audio_uploader_id}/' if audio_uploader_id else None,
 112             'title': audio_info['title'],
 113             'thumbnails': thumbnails,
 114             'description': audio_description,
 115             'categories': list(filter(None, [audio_info.get('category_name')])),
 116             'duration': audio_info.get('duration'),
 117             'view_count': audio_info.get('play_count'),
 118             'like_count': audio_info.get('favorites_count'),
 119             'formats': formats,
 120         }
 121
 122
 123 class XimalayaAlbumIE(XimalayaBaseIE):
 124     IE_NAME = 'ximalaya:album'
 125     IE_DESC = '喜马拉雅FM 专辑'
 126     _VALID_URL = r'https?://(?:www\.|m\.)?ximalaya\.com/(?:\d+/)?album/(?P<id>[0-9]+)'
 127     _TESTS = [{
 128         'url': 'http://www.ximalaya.com/61425525/album/5534601/',
 129         'info_dict': {
 130             'title': '唐诗三百首（含赏析）',
 131             'id': '5534601',
 132         },
 133         'playlist_mincount': 323,
 134     }, {
 135         'url': 'https://www.ximalaya.com/album/6912905',
 136         'info_dict': {
 137             'title': '埃克哈特《修炼当下的力量》',
 138             'id': '6912905',
 139         },
 140         'playlist_mincount': 41,
 141     }]
 142
 143     def _real_extract(self, url):
 144         playlist_id = self._match_id(url)
 145
 146         first_page = self._fetch_page(playlist_id, 1)
 147         page_count = math.ceil(first_page['trackTotalCount'] / first_page['pageSize'])
 148
 149         entries = InAdvancePagedList(
 150             lambda idx: self._get_entries(self._fetch_page(playlist_id, idx + 1) if idx else first_page),
 151             page_count, first_page['pageSize'])
 152
 153         title = traverse_obj(first_page, ('tracks', 0, 'albumTitle'), expected_type=str)
 154
 155         return self.playlist_result(entries, playlist_id, title)
 156
 157     def _fetch_page(self, playlist_id, page_idx):
 158         return self._download_json(
 159             'https://www.ximalaya.com/revision/album/v1/getTracksList',
 160             playlist_id, note=f'Downloading tracks list page {page_idx}',
 161             query={'albumId': playlist_id, 'pageNum': page_idx})['data']
 162
 163     def _get_entries(self, page_data):
 164         for e in page_data['tracks']:
 165             yield self.url_result(
 166                 self._proto_relative_url(f'//www.ximalaya.com{e["url"]}'),
 167                 XimalayaIE, e.get('trackId'), e.get('title'))