Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/hketv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_str
   6 from ..utils import (
   7     clean_html,
   8     ExtractorError,
   9     int_or_none,
  10     merge_dicts,
  11     parse_count,
  12     str_or_none,
  13     try_get,
  14     unified_strdate,
  15     urlencode_postdata,
  16     urljoin,
  17 )
  18
  19
  20 class HKETVIE(InfoExtractor):
  21     IE_NAME = 'hketv'
  22     IE_DESC = '香港教育局教育電視 (HKETV) Educational Television, Hong Kong Educational Bureau'
  23     _GEO_BYPASS = False
  24     _GEO_COUNTRIES = ['HK']
  25     _VALID_URL = r'https?://(?:www\.)?hkedcity\.net/etv/resource/(?P<id>[0-9]+)'
  26     _TESTS = [{
  27         'url': 'https://www.hkedcity.net/etv/resource/2932360618',
  28         'md5': 'f193712f5f7abb208ddef3c5ea6ed0b7',
  29         'info_dict': {
  30             'id': '2932360618',
  31             'ext': 'mp4',
  32             'title': '喜閱一生(共享閱讀樂) (中、英文字幕可供選擇)',
  33             'description': 'md5:d5286d05219ef50e0613311cbe96e560',
  34             'upload_date': '20181024',
  35             'duration': 900,
  36             'subtitles': 'count:2',
  37         },
  38         'skip': 'Geo restricted to HK',
  39     }, {
  40         'url': 'https://www.hkedcity.net/etv/resource/972641418',
  41         'md5': '1ed494c1c6cf7866a8290edad9b07dc9',
  42         'info_dict': {
  43             'id': '972641418',
  44             'ext': 'mp4',
  45             'title': '衣冠楚楚 (天使系列之一)',
  46             'description': 'md5:10bb3d659421e74f58e5db5691627b0f',
  47             'upload_date': '20070109',
  48             'duration': 907,
  49             'subtitles': {},
  50         },
  51         'params': {
  52             'geo_verification_proxy': '<HK proxy here>',
  53         },
  54         'skip': 'Geo restricted to HK',
  55     }]
  56
  57     _CC_LANGS = {
  58         '中文（繁體中文）': 'zh-Hant',
  59         '中文（简体中文）': 'zh-Hans',
  60         'English': 'en',
  61         'Bahasa Indonesia': 'id',
  62         '\u0939\u093f\u0928\u094d\u0926\u0940': 'hi',
  63         '\u0928\u0947\u092a\u093e\u0932\u0940': 'ne',
  64         'Tagalog': 'tl',
  65         '\u0e44\u0e17\u0e22': 'th',
  66         '\u0627\u0631\u062f\u0648': 'ur',
  67     }
  68     _FORMAT_HEIGHTS = {
  69         'SD': 360,
  70         'HD': 720,
  71     }
  72     _APPS_BASE_URL = 'https://apps.hkedcity.net'
  73
  74     def _real_extract(self, url):
  75         video_id = self._match_id(url)
  76         webpage = self._download_webpage(url, video_id)
  77
  78         title = (
  79             self._html_search_meta(
  80                 ('ed_title', 'search.ed_title'), webpage, default=None)
  81             or self._search_regex(
  82                 r'data-favorite_title_(?:eng|chi)=(["\'])(?P<id>(?:(?!\1).)+)\1',
  83                 webpage, 'title', default=None, group='url')
  84             or self._html_search_regex(
  85                 r'<h1>([^<]+)</h1>', webpage, 'title', default=None)
  86             or self._og_search_title(webpage)
  87         )
  88
  89         file_id = self._search_regex(
  90             r'post_var\[["\']file_id["\']\s*\]\s*=\s*(.+?);',
  91             webpage, 'file ID')
  92         curr_url = self._search_regex(
  93             r'post_var\[["\']curr_url["\']\s*\]\s*=\s*"(.+?)";',
  94             webpage, 'curr URL')
  95         data = {
  96             'action': 'get_info',
  97             'curr_url': curr_url,
  98             'file_id': file_id,
  99             'video_url': file_id,
 100         }
 101
 102         response = self._download_json(
 103             self._APPS_BASE_URL + '/media/play/handler.php', video_id,
 104             data=urlencode_postdata(data),
 105             headers=merge_dicts({
 106                 'Content-Type': 'application/x-www-form-urlencoded'},
 107                 self.geo_verification_headers()))
 108
 109         result = response['result']
 110
 111         if not response.get('success') or not response.get('access'):
 112             error = clean_html(response.get('access_err_msg'))
 113             if 'Video streaming is not available in your country' in error:
 114                 self.raise_geo_restricted(
 115                     msg=error, countries=self._GEO_COUNTRIES)
 116             else:
 117                 raise ExtractorError(error, expected=True)
 118
 119         formats = []
 120
 121         width = int_or_none(result.get('width'))
 122         height = int_or_none(result.get('height'))
 123
 124         playlist0 = result['playlist'][0]
 125         for fmt in playlist0['sources']:
 126             file_url = urljoin(self._APPS_BASE_URL, fmt.get('file'))
 127             if not file_url:
 128                 continue
 129             # If we ever wanted to provide the final resolved URL that
 130             # does not require cookies, albeit with a shorter lifespan:
 131             #     urlh = self._downloader.urlopen(file_url)
 132             #     resolved_url = urlh.geturl()
 133             label = fmt.get('label')
 134             h = self._FORMAT_HEIGHTS.get(label)
 135             w = h * width // height if h and width and height else None
 136             formats.append({
 137                 'format_id': label,
 138                 'ext': fmt.get('type'),
 139                 'url': file_url,
 140                 'width': w,
 141                 'height': h,
 142             })
 143         self._sort_formats(formats)
 144
 145         subtitles = {}
 146         tracks = try_get(playlist0, lambda x: x['tracks'], list) or []
 147         for track in tracks:
 148             if not isinstance(track, dict):
 149                 continue
 150             track_kind = str_or_none(track.get('kind'))
 151             if not track_kind or not isinstance(track_kind, compat_str):
 152                 continue
 153             if track_kind.lower() not in ('captions', 'subtitles'):
 154                 continue
 155             track_url = urljoin(self._APPS_BASE_URL, track.get('file'))
 156             if not track_url:
 157                 continue
 158             track_label = track.get('label')
 159             subtitles.setdefault(self._CC_LANGS.get(
 160                 track_label, track_label), []).append({
 161                     'url': self._proto_relative_url(track_url),
 162                     'ext': 'srt',
 163                 })
 164
 165         # Likes
 166         emotion = self._download_json(
 167             'https://emocounter.hkedcity.net/handler.php', video_id,
 168             data=urlencode_postdata({
 169                 'action': 'get_emotion',
 170                 'data[bucket_id]': 'etv',
 171                 'data[identifier]': video_id,
 172             }),
 173             headers={'Content-Type': 'application/x-www-form-urlencoded'},
 174             fatal=False) or {}
 175         like_count = int_or_none(try_get(
 176             emotion, lambda x: x['data']['emotion_data'][0]['count']))
 177
 178         return {
 179             'id': video_id,
 180             'title': title,
 181             'description': self._html_search_meta(
 182                 'description', webpage, fatal=False),
 183             'upload_date': unified_strdate(self._html_search_meta(
 184                 'ed_date', webpage, fatal=False), day_first=False),
 185             'duration': int_or_none(result.get('length')),
 186             'formats': formats,
 187             'subtitles': subtitles,
 188             'thumbnail': urljoin(self._APPS_BASE_URL, result.get('image')),
 189             'view_count': parse_count(result.get('view_count')),
 190             'like_count': like_count,
 191         }