yt_dlp/extractor/trueid.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_HTTPError
   6 from ..utils import (
   7     determine_ext,
   8     ExtractorError,
   9     int_or_none,
  10     parse_age_limit,
  11     traverse_obj,
  12     unified_timestamp,
  13     url_or_none
  14 )
  15
  16
  17 class TrueIDIE(InfoExtractor):
  18     _VALID_URL = r'https?://(?P<domain>vn\.trueid\.net|trueid\.(?:id|ph))/(?:movie|series/[^/]+)/(?P<id>[^/?#&]+)'
  19     _TESTS = [{
  20         'url': 'https://trueid.id/movie/XYNlDOZZJzL6/pengabdi-setan/',
  21         'md5': '2552c7535125885901f1a2a4bcf32ca3',
  22         'info_dict': {
  23             'id': 'XYNlDOZZJzL6',
  24             'ext': 'mp4',
  25             'title': 'Pengabdi Setan',
  26             'display_id': 'pengabdi-setan',
  27             'description': 'md5:b0b41df08601e85e5291496c9bbe52cd',
  28             'timestamp': 1600243511,
  29             'categories': ['Film Indonesia', 'Horror', 'Mystery'],
  30             'release_timestamp': 1593536400,
  31             'release_year': 1982,
  32             'cast': list,
  33             'thumbnail': 'https://cms.dmpcdn.com/movie/2020/09/18/8b6e35c0-f97f-11ea-81fe-c52fc9dd314f_original.png',
  34             'upload_date': '20200916',
  35             'release_date': '20200630',
  36         },
  37         'expected_warnings': ['Video is geo restricted.']
  38     }, {
  39         'url': 'https://trueid.id/series/zZOBVPb62EwR/qXY73rwyl7oj/one-piece-ep-1/',
  40         'md5': '1c6d976049bc3c89a8a25aed2c3fb081',
  41         'info_dict': {
  42             'id': 'qXY73rwyl7oj',
  43             'ext': 'mp4',
  44             'title': 'One Piece Ep. 1',
  45             'display_id': 'one-piece-ep-1',
  46             'description': 'md5:13226d603bd03c4150a1cf5758e842ea',
  47             'timestamp': 1610421085,
  48             'categories': ['Animation & Cartoon', 'Kids & Family', 'Adventure'],
  49             'release_timestamp': 1612112400,
  50             'release_year': 1999,
  51             'age_limit': 7,
  52             'cast': ['Kounosuke Uda', 'Junji Shimizu'],
  53             'thumbnail': 'https://cms.dmpcdn.com/movie/2021/01/13/f84e9e70-5562-11eb-9fe2-dd6c2099a468_original.png',
  54             'upload_date': '20210112',
  55             'release_date': '20210131',
  56         },
  57         'expected_warnings': ['Video is geo restricted.']
  58     }, {
  59         'url': 'https://vn.trueid.net/series/7DNPM7Bpa9wv/pwLgEQ4Xbda2/haikyu-vua-bong-chuyen-phan-1/',
  60         'info_dict': {
  61             'id': 'pwLgEQ4Xbda2',
  62             'ext': 'mp4',
  63             'title': 'Haikyu!!: Vua Bóng Chuyền Phần 1 - Tập 1',
  64             'display_id': 'haikyu-vua-bong-chuyen-phan-1-tap-1',
  65             'description': 'md5:0374dd44d247799169449ee30cca963a',
  66             'timestamp': 1629270901,
  67             'categories': ['Anime', 'Phim Hài', 'Phim Học Đường', 'Phim Thể Thao', 'Shounen'],
  68             'release_timestamp': 1629270720,
  69             'release_year': 2014,
  70             'age_limit': 13,
  71             'thumbnail': 'https://cms.dmpcdn.com/movie/2021/09/28/b6e7ec00-2039-11ec-8436-974544e5841f_webp_original.jpg',
  72             'upload_date': '20210818',
  73             'release_date': '20210818',
  74         },
  75         'expected_warnings': ['Video is geo restricted.']
  76     }, {
  77         'url': 'https://trueid.ph/series/l8rvvAw7Jwv8/l8rvvAw7Jwv8/naruto-trailer/',
  78         'only_matching': True,
  79     }]
  80     _CUSTOM_RATINGS = {
  81         'PG': 7,
  82     }
  83
  84     def _real_extract(self, url):
  85         domain, video_id = self._match_valid_url(url).group('domain', 'id')
  86         webpage = self._download_webpage(url, video_id)
  87         initial_data = traverse_obj(
  88             self._search_nextjs_data(webpage, video_id, fatal=False), ('props', 'pageProps', 'initialContentData'), default={})
  89
  90         try:
  91             stream_data = self._download_json(
  92                 f'https://{domain}/cmsPostProxy/contents/video/{video_id}/streamer?os=android', video_id, data=b'')['data']
  93         except ExtractorError as e:
  94             if not isinstance(e.cause, compat_HTTPError):
  95                 raise e
  96             errmsg = self._parse_json(e.cause.read().decode(), video_id)['meta']['message']
  97             if 'country' in errmsg:
  98                 self.raise_geo_restricted(
  99                     errmsg, [initial_data['display_country']] if initial_data.get('display_country') else None, True)
 100             else:
 101                 self.raise_no_formats(errmsg, video_id=video_id)
 102
 103         if stream_data:
 104             stream_url = stream_data['stream']['stream_url']
 105             stream_ext = determine_ext(stream_url)
 106             if stream_ext == 'm3u8':
 107                 formats, subs = self._extract_m3u8_formats_and_subtitles(stream_url, video_id, 'mp4')
 108             elif stream_ext == 'mpd':
 109                 formats, subs = self._extract_mpd_formats_and_subtitles(stream_url, video_id)
 110             else:
 111                 formats = [{'url': stream_url}]
 112
 113         thumbnails = [
 114             {'id': thumb_key, 'url': thumb_url}
 115             for thumb_key, thumb_url in (initial_data.get('thumb_list') or {}).items()
 116             if url_or_none(thumb_url)]
 117
 118         return {
 119             'id': video_id,
 120             'title': initial_data.get('title') or self._html_search_regex(
 121                 [r'Nonton (?P<name>.+) Gratis',
 122                  r'Xem (?P<name>.+) Miễn phí',
 123                  r'Watch (?P<name>.+) Free'], webpage, 'title', group='name'),
 124             'display_id': initial_data.get('slug_title'),
 125             'description': initial_data.get('synopsis'),
 126             'timestamp': unified_timestamp(initial_data.get('create_date')),
 127             # 'duration': int_or_none(initial_data.get('duration'), invscale=60),  # duration field must atleast be accurate to the second
 128             'categories': traverse_obj(initial_data, ('article_category_details', ..., 'name')),
 129             'release_timestamp': unified_timestamp(initial_data.get('publish_date')),
 130             'release_year': int_or_none(initial_data.get('release_year')),
 131             'formats': formats,
 132             'subtitles': subs,
 133             'thumbnails': thumbnails,
 134             'age_limit': self._CUSTOM_RATINGS.get(initial_data.get('rate')) or parse_age_limit(initial_data.get('rate')),
 135             'cast': traverse_obj(initial_data, (('actor', 'director'), ...)),
 136             'view_count': int_or_none(initial_data.get('count_views')),
 137             'like_count': int_or_none(initial_data.get('count_likes')),
 138             'average_rating': int_or_none(initial_data.get('count_ratings')),
 139         }