yt_dlp/extractor/wevidi.py

   1 from .common import InfoExtractor
   2 from ..utils import clean_html, float_or_none, get_element_by_class, js_to_json, traverse_obj
   3
   4
   5 class WeVidiIE(InfoExtractor):
   6     _VALID_URL = r'https?://(?:www\.)?wevidi\.net/watch/(?P<id>[\w-]{11})'
   7     _TESTS = [{
   8         'url': 'https://wevidi.net/watch/2th7UO5F4KV',
   9         'md5': 'b913d1ff5bbad499e2c7ef4aa6d829d7',
  10         'info_dict': {
  11             'id': '2th7UO5F4KV',
  12             'ext': 'mp4',
  13             'title': 'YouTube Alternative: WeVidi - customizable channels & more',
  14             'thumbnail': r're:^https?://.*\.jpg$',
  15             'description': 'md5:73a27d0a87d49fbcc5584566326ebeed',
  16             'uploader': 'eclecRC',
  17             'duration': 932.098,
  18         },
  19     }, {
  20         'url': 'https://wevidi.net/watch/ievRuuQHbPS',
  21         'md5': 'ce8a94989a959bff9003fa27ee572935',
  22         'info_dict': {
  23             'id': 'ievRuuQHbPS',
  24             'ext': 'mp4',
  25             'title': 'WeVidi Playlists',
  26             'thumbnail': r're:^https?://.*\.jpg$',
  27             'description': 'md5:32cdfca272687390d9bd9b0c9c6153ee',
  28             'uploader': 'WeVidi',
  29             'duration': 36.1999,
  30         },
  31     }, {
  32         'url': 'https://wevidi.net/watch/PcMzDWaQSWb',
  33         'md5': '55ee0d3434be5d9e5cc76b83f2bb57ec',
  34         'info_dict': {
  35             'id': 'PcMzDWaQSWb',
  36             'ext': 'mp4',
  37             'title': 'Cat blep',
  38             'thumbnail': r're:^https?://.*\.jpg$',
  39             'description': 'md5:e2c9e2b54b8bb424cc64937c8fdc068f',
  40             'uploader': 'WeVidi',
  41             'duration': 41.972,
  42         },
  43     }, {
  44         'url': 'https://wevidi.net/watch/wJnRqDHNe_u',
  45         'md5': 'c8f263dd47e66cc17546b3abf47b5a77',
  46         'info_dict': {
  47             'id': 'wJnRqDHNe_u',
  48             'ext': 'mp4',
  49             'title': 'Gissy Talks: YouTube Alternatives',
  50             'thumbnail': r're:^https?://.*\.jpg$',
  51             'description': 'md5:e65036f0d4af80e0af191bd11af5195e',
  52             'uploader': 'GissyEva',
  53             'duration': 630.451,
  54         },
  55     }, {
  56         'url': 'https://wevidi.net/watch/4m1c4yJR_yc',
  57         'md5': 'c63ce5ca6990dce86855fc02ca5bc1ed',
  58         'info_dict': {
  59             'id': '4m1c4yJR_yc',
  60             'ext': 'mp4',
  61             'title': 'Enough of that! - Awesome Exilez Podcast',
  62             'thumbnail': r're:^https?://.*\.jpg$',
  63             'description': 'md5:96af99dd63468b2dfab3020560e3e9b2',
  64             'uploader': 'eclecRC',
  65             'duration': 6.804,
  66         },
  67     }]
  68
  69     def _extract_formats(self, wvplayer_props):
  70         # Taken from WeVidi player JS: https://wevidi.net/layouts/default/static/player.min.js
  71         resolution_map = {
  72             1: 144,
  73             2: 240,
  74             3: 360,
  75             4: 480,
  76             5: 720,
  77             6: 1080,
  78         }
  79
  80         src_path = f'{wvplayer_props["srcVID"]}/{wvplayer_props["srcUID"]}/{wvplayer_props["srcNAME"]}'
  81         for res in traverse_obj(wvplayer_props, ('resolutions', ..., {int}, {lambda x: x or None})):
  82             format_id = str(-(res // -2) - 1)
  83             yield {
  84                 'acodec': 'mp4a.40.2',
  85                 'ext': 'mp4',
  86                 'format_id': format_id,
  87                 'height': resolution_map.get(res),
  88                 'url': f'https://www.wevidi.net/videoplayback/{src_path}/{format_id}',
  89                 'vcodec': 'avc1.42E01E',
  90             }
  91
  92     def _real_extract(self, url):
  93         video_id = self._match_id(url)
  94         webpage = self._download_webpage(url, video_id)
  95
  96         wvplayer_props = self._search_json(
  97             r'WVPlayer\(', webpage, 'player', video_id,
  98             transform_source=lambda x: js_to_json(x.replace('||', '}')))
  99
 100         return {
 101             'id': video_id,
 102             'title': clean_html(get_element_by_class('video_title', webpage)),
 103             'description': clean_html(get_element_by_class('descr_long', webpage)),
 104             'uploader': clean_html(get_element_by_class('username', webpage)),
 105             'formats': list(self._extract_formats(wvplayer_props)),
 106             'thumbnail': self._og_search_thumbnail(webpage),
 107             'duration': float_or_none(wvplayer_props.get('duration')),
 108         }