yt_dlp/extractor/biqle.py

   1 from .common import InfoExtractor
   2 from .vk import VKIE
   3 from ..compat import compat_b64decode
   4 from ..utils import (
   5     int_or_none,
   6     js_to_json,
   7     traverse_obj,
   8     unified_timestamp,
   9 )
  10
  11
  12 class BIQLEIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?biqle\.(?:com|org|ru)/watch/(?P<id>-?\d+_\d+)'
  14     _TESTS = [{
  15         'url': 'https://biqle.ru/watch/-2000421746_85421746',
  16         'md5': 'ae6ef4f04d19ac84e4658046d02c151c',
  17         'info_dict': {
  18             'id': '-2000421746_85421746',
  19             'ext': 'mp4',
  20             'title': 'Forsaken By Hope Studio Clip',
  21             'description': 'Forsaken By Hope Studio Clip — Смотреть онлайн',
  22             'upload_date': '19700101',
  23             'thumbnail': r're:https://[^/]+/impf/7vN3ACwSTgChP96OdOfzFjUCzFR6ZglDQgWsIw/KPaACiVJJxM\.jpg\?size=800x450&quality=96&keep_aspect_ratio=1&background=000000&sign=b48ea459c4d33dbcba5e26d63574b1cb&type=video_thumb',
  24             'timestamp': 0,
  25         },
  26     }, {
  27         'url': 'http://biqle.org/watch/-44781847_168547604',
  28         'md5': '7f24e72af1db0edf7c1aaba513174f97',
  29         'info_dict': {
  30             'id': '-44781847_168547604',
  31             'ext': 'mp4',
  32             'title': 'Ребенок в шоке от автоматической мойки',
  33             'description': 'Ребенок в шоке от автоматической мойки — Смотреть онлайн',
  34             'timestamp': 1396633454,
  35             'upload_date': '20140404',
  36             'thumbnail': r're:https://[^/]+/c535507/u190034692/video/l_b84df002\.jpg',
  37         },
  38     }]
  39
  40     def _real_extract(self, url):
  41         video_id = self._match_id(url)
  42         webpage = self._download_webpage(url, video_id)
  43
  44         title = self._html_search_meta('name', webpage, 'Title', fatal=False)
  45         timestamp = unified_timestamp(self._html_search_meta('uploadDate', webpage, 'Upload Date', default=None))
  46         description = self._html_search_meta('description', webpage, 'Description', default=None)
  47
  48         global_embed_url = self._search_regex(
  49             r'<script[^<]+?window.globEmbedUrl\s*=\s*\'((?:https?:)?//(?:daxab\.com|dxb\.to|[^/]+/player)/[^\']+)\'',
  50             webpage, 'global Embed url')
  51         hash = self._search_regex(
  52             r'<script id="data-embed-video[^<]+?hash: "([^"]+)"[^<]*</script>', webpage, 'Hash')
  53
  54         embed_url = global_embed_url + hash
  55
  56         if VKIE.suitable(embed_url):
  57             return self.url_result(embed_url, VKIE.ie_key(), video_id)
  58
  59         embed_page = self._download_webpage(
  60             embed_url, video_id, 'Downloading embed webpage', headers={'Referer': url})
  61
  62         glob_params = self._parse_json(self._search_regex(
  63             r'<script id="globParams">[^<]*window.globParams = ([^;]+);[^<]+</script>',
  64             embed_page, 'Global Parameters'), video_id, transform_source=js_to_json)
  65         host_name = compat_b64decode(glob_params['server'][::-1]).decode()
  66
  67         item = self._download_json(
  68             f'https://{host_name}/method/video.get/{video_id}', video_id,
  69             headers={'Referer': url}, query={
  70                 'token': glob_params['video']['access_token'],
  71                 'videos': video_id,
  72                 'ckey': glob_params['c_key'],
  73                 'credentials': glob_params['video']['credentials'],
  74             })['response']['items'][0]
  75
  76         formats = []
  77         for f_id, f_url in item.get('files', {}).items():
  78             if f_id == 'external':
  79                 return self.url_result(f_url)
  80             ext, height = f_id.split('_')
  81             height_extra_key = traverse_obj(glob_params, ('video', 'partial', 'quality', height))
  82             if height_extra_key:
  83                 formats.append({
  84                     'format_id': f'{height}p',
  85                     'url': f'https://{host_name}/{f_url[8:]}&videos={video_id}&extra_key={height_extra_key}',
  86                     'height': int_or_none(height),
  87                     'ext': ext,
  88                 })
  89
  90         thumbnails = []
  91         for k, v in item.items():
  92             if k.startswith('photo_') and v:
  93                 width = k.replace('photo_', '')
  94                 thumbnails.append({
  95                     'id': width,
  96                     'url': v,
  97                     'width': int_or_none(width),
  98                 })
  99
 100         return {
 101             'id': video_id,
 102             'title': title,
 103             'formats': formats,
 104             'comment_count': int_or_none(item.get('comments')),
 105             'description': description,
 106             'duration': int_or_none(item.get('duration')),
 107             'thumbnails': thumbnails,
 108             'timestamp': timestamp,
 109             'view_count': int_or_none(item.get('views')),
 110         }