yt_dlp/extractor/hketv.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     ExtractorError,
   4     clean_html,
   5     int_or_none,
   6     merge_dicts,
   7     parse_count,
   8     str_or_none,
   9     try_get,
  10     unified_strdate,
  11     urlencode_postdata,
  12     urljoin,
  13 )
  14
  15
  16 class HKETVIE(InfoExtractor):
  17     IE_NAME = 'hketv'
  18     IE_DESC = '香港教育局教育電視 (HKETV) Educational Television, Hong Kong Educational Bureau'
  19     _GEO_BYPASS = False
  20     _GEO_COUNTRIES = ['HK']
  21     _VALID_URL = r'https?://(?:www\.)?hkedcity\.net/etv/resource/(?P<id>[0-9]+)'
  22     _TESTS = [{
  23         'url': 'https://www.hkedcity.net/etv/resource/2932360618',
  24         'md5': 'f193712f5f7abb208ddef3c5ea6ed0b7',
  25         'info_dict': {
  26             'id': '2932360618',
  27             'ext': 'mp4',
  28             'title': '喜閱一生(共享閱讀樂) (中、英文字幕可供選擇)',
  29             'description': 'md5:d5286d05219ef50e0613311cbe96e560',
  30             'upload_date': '20181024',
  31             'duration': 900,
  32             'subtitles': 'count:2',
  33         },
  34         'skip': 'Geo restricted to HK',
  35     }, {
  36         'url': 'https://www.hkedcity.net/etv/resource/972641418',
  37         'md5': '1ed494c1c6cf7866a8290edad9b07dc9',
  38         'info_dict': {
  39             'id': '972641418',
  40             'ext': 'mp4',
  41             'title': '衣冠楚楚 (天使系列之一)',
  42             'description': 'md5:10bb3d659421e74f58e5db5691627b0f',
  43             'upload_date': '20070109',
  44             'duration': 907,
  45             'subtitles': {},
  46         },
  47         'params': {
  48             'geo_verification_proxy': '<HK proxy here>',
  49         },
  50         'skip': 'Geo restricted to HK',
  51     }]
  52
  53     _CC_LANGS = {
  54         '中文（繁體中文）': 'zh-Hant',
  55         '中文（简体中文）': 'zh-Hans',
  56         'English': 'en',
  57         'Bahasa Indonesia': 'id',
  58         '\u0939\u093f\u0928\u094d\u0926\u0940': 'hi',
  59         '\u0928\u0947\u092a\u093e\u0932\u0940': 'ne',
  60         'Tagalog': 'tl',
  61         '\u0e44\u0e17\u0e22': 'th',
  62         '\u0627\u0631\u062f\u0648': 'ur',
  63     }
  64     _FORMAT_HEIGHTS = {
  65         'SD': 360,
  66         'HD': 720,
  67     }
  68     _APPS_BASE_URL = 'https://apps.hkedcity.net'
  69
  70     def _real_extract(self, url):
  71         video_id = self._match_id(url)
  72         webpage = self._download_webpage(url, video_id)
  73
  74         title = (
  75             self._html_search_meta(
  76                 ('ed_title', 'search.ed_title'), webpage, default=None)
  77             or self._search_regex(
  78                 r'data-favorite_title_(?:eng|chi)=(["\'])(?P<id>(?:(?!\1).)+)\1',
  79                 webpage, 'title', default=None, group='url')
  80             or self._html_search_regex(
  81                 r'<h1>([^<]+)</h1>', webpage, 'title', default=None)
  82             or self._og_search_title(webpage)
  83         )
  84
  85         file_id = self._search_regex(
  86             r'post_var\[["\']file_id["\']\s*\]\s*=\s*(.+?);',
  87             webpage, 'file ID')
  88         curr_url = self._search_regex(
  89             r'post_var\[["\']curr_url["\']\s*\]\s*=\s*"(.+?)";',
  90             webpage, 'curr URL')
  91         data = {
  92             'action': 'get_info',
  93             'curr_url': curr_url,
  94             'file_id': file_id,
  95             'video_url': file_id,
  96         }
  97
  98         response = self._download_json(
  99             self._APPS_BASE_URL + '/media/play/handler.php', video_id,
 100             data=urlencode_postdata(data),
 101             headers=merge_dicts({
 102                 'Content-Type': 'application/x-www-form-urlencoded'},
 103                 self.geo_verification_headers()))
 104
 105         result = response['result']
 106
 107         if not response.get('success') or not response.get('access'):
 108             error = clean_html(response.get('access_err_msg'))
 109             if 'Video streaming is not available in your country' in error:
 110                 self.raise_geo_restricted(
 111                     msg=error, countries=self._GEO_COUNTRIES)
 112             else:
 113                 raise ExtractorError(error, expected=True)
 114
 115         formats = []
 116
 117         width = int_or_none(result.get('width'))
 118         height = int_or_none(result.get('height'))
 119
 120         playlist0 = result['playlist'][0]
 121         for fmt in playlist0['sources']:
 122             file_url = urljoin(self._APPS_BASE_URL, fmt.get('file'))
 123             if not file_url:
 124                 continue
 125             # If we ever wanted to provide the final resolved URL that
 126             # does not require cookies, albeit with a shorter lifespan:
 127             #     urlh = self._downloader.urlopen(file_url)
 128             #     resolved_url = urlh.url
 129             label = fmt.get('label')
 130             h = self._FORMAT_HEIGHTS.get(label)
 131             w = h * width // height if h and width and height else None
 132             formats.append({
 133                 'format_id': label,
 134                 'ext': fmt.get('type'),
 135                 'url': file_url,
 136                 'width': w,
 137                 'height': h,
 138             })
 139
 140         subtitles = {}
 141         tracks = try_get(playlist0, lambda x: x['tracks'], list) or []
 142         for track in tracks:
 143             if not isinstance(track, dict):
 144                 continue
 145             track_kind = str_or_none(track.get('kind'))
 146             if not track_kind or not isinstance(track_kind, str):
 147                 continue
 148             if track_kind.lower() not in ('captions', 'subtitles'):
 149                 continue
 150             track_url = urljoin(self._APPS_BASE_URL, track.get('file'))
 151             if not track_url:
 152                 continue
 153             track_label = track.get('label')
 154             subtitles.setdefault(self._CC_LANGS.get(
 155                 track_label, track_label), []).append({
 156                     'url': self._proto_relative_url(track_url),
 157                     'ext': 'srt',
 158                 })
 159
 160         # Likes
 161         emotion = self._download_json(
 162             'https://emocounter.hkedcity.net/handler.php', video_id,
 163             data=urlencode_postdata({
 164                 'action': 'get_emotion',
 165                 'data[bucket_id]': 'etv',
 166                 'data[identifier]': video_id,
 167             }),
 168             headers={'Content-Type': 'application/x-www-form-urlencoded'},
 169             fatal=False) or {}
 170         like_count = int_or_none(try_get(
 171             emotion, lambda x: x['data']['emotion_data'][0]['count']))
 172
 173         return {
 174             'id': video_id,
 175             'title': title,
 176             'description': self._html_search_meta(
 177                 'description', webpage, fatal=False),
 178             'upload_date': unified_strdate(self._html_search_meta(
 179                 'ed_date', webpage, fatal=False), day_first=False),
 180             'duration': int_or_none(result.get('length')),
 181             'formats': formats,
 182             'subtitles': subtitles,
 183             'thumbnail': urljoin(self._APPS_BASE_URL, result.get('image')),
 184             'view_count': parse_count(result.get('view_count')),
 185             'like_count': like_count,
 186         }