projects / yt-dlp.git / blame
| Commit | Line | Data |
|---|---|---|
| a4da9db8 SS |
1 | import functools |
| 2 | ||
| 3 | from .common import InfoExtractor | |
| 4 | from ..utils import ( | |
| 5 | ExtractorError, | |
| 6 | extract_attributes, | |
| 7 | get_elements_html_by_class, | |
| 8 | url_or_none, | |
| 9 | ) | |
| 10 | from ..utils.traversal import traverse_obj | |
| 11 | ||
| 12 | ||
| 13 | class GBNewsIE(InfoExtractor): | |
| 14 | IE_DESC = 'GB News clips, features and live streams' | |
| 15 | _VALID_URL = r'https?://(?:www\.)?gbnews\.(?:uk|com)/(?:\w+/)?(?P<id>[^#?]+)' | |
| 16 | ||
| 17 | _PLATFORM = 'safari' | |
| 18 | _SSMP_URL = 'https://mm-v2.simplestream.com/ssmp/api.php' | |
| 19 | _TESTS = [{ | |
| 20 | 'url': 'https://www.gbnews.com/news/bbc-claudine-gay-harvard-university-antisemitism-row', | |
| 21 | 'info_dict': { | |
| 22 | 'id': '52264136', | |
| 23 | 'ext': 'mp4', | |
| 24 | 'thumbnail': r're:https?://www\.gbnews\.\w+/.+\.(?:jpe?g|png|webp)', | |
| 25 | 'display_id': 'bbc-claudine-gay-harvard-university-antisemitism-row', | |
| 26 | 'description': 'The post was criticised by former employers of the broadcaster', | |
| 27 | 'title': 'BBC deletes post after furious backlash over headline downplaying antisemitism', | |
| 28 | }, | |
| 29 | }, { | |
| 30 | 'url': 'https://www.gbnews.com/royal/prince-harry-in-love-with-kate-meghan-markle-jealous-royal', | |
| 31 | 'info_dict': { | |
| 32 | 'id': '52328390', | |
| 33 | 'ext': 'mp4', | |
| 34 | 'thumbnail': r're:https?://www\.gbnews\.\w+/.+\.(?:jpe?g|png|webp)', | |
| 35 | 'display_id': 'prince-harry-in-love-with-kate-meghan-markle-jealous-royal', | |
| 36 | 'description': 'Ingrid Seward has published 17 books documenting the highs and lows of the Royal Family', | |
| 37 | 'title': 'Royal author claims Prince Harry was \'in love\' with Kate - Meghan was \'jealous\'', | |
| 38 | } | |
| 39 | }, { | |
| 40 | 'url': 'https://www.gbnews.uk/watchlive', | |
| 41 | 'info_dict': { | |
| 42 | 'id': '1069', | |
| 43 | 'ext': 'mp4', | |
| 44 | 'thumbnail': r're:https?://www\.gbnews\.\w+/.+\.(?:jpe?g|png|webp)', | |
| 45 | 'display_id': 'watchlive', | |
| 46 | 'live_status': 'is_live', | |
| 47 | 'title': r're:^GB News Live', | |
| 48 | }, | |
| 49 | 'params': {'skip_download': 'm3u8'}, | |
| 50 | }] | |
| 51 | ||
| 52 | @functools.lru_cache | |
| 53 | def _get_ss_endpoint(self, data_id, data_env): | |
| 54 | if not data_id: | |
| 55 | data_id = 'GB003' | |
| 56 | if not data_env: | |
| 57 | data_env = 'production' | |
| 58 | ||
| 59 | json_data = self._download_json( | |
| 60 | self._SSMP_URL, None, 'Downloading Simplestream JSON metadata', query={ | |
| 61 | 'id': data_id, | |
| 62 | 'env': data_env, | |
| 63 | }) | |
| 64 | meta_url = traverse_obj(json_data, ('response', 'api_hostname', {url_or_none})) | |
| 65 | if not meta_url: | |
| 66 | raise ExtractorError('No API host found') | |
| 67 | ||
| 68 | return meta_url | |
| 69 | ||
| 70 | def _real_extract(self, url): | |
| 71 | display_id = self._match_id(url).rpartition('/')[2] | |
| 72 | webpage = self._download_webpage(url, display_id) | |
| 73 | ||
| 74 | video_data = None | |
| 75 | elements = get_elements_html_by_class('simplestream', webpage) | |
| 76 | for html_tag in elements: | |
| 77 | attributes = extract_attributes(html_tag) | |
| 78 | if 'sidebar' not in (attributes.get('class') or ''): | |
| 79 | video_data = attributes | |
| 80 | if not video_data: | |
| 81 | raise ExtractorError('Could not find video element', expected=True) | |
| 82 | ||
| 83 | endpoint_url = self._get_ss_endpoint(video_data.get('data-id'), video_data.get('data-env')) | |
| 84 | ||
| 85 | uvid = video_data['data-uvid'] | |
| 86 | video_type = video_data.get('data-type') | |
| 87 | if not video_type or video_type == 'vod': | |
| 88 | video_type = 'show' | |
| 89 | stream_data = self._download_json( | |
| 90 | f'{endpoint_url}/api/{video_type}/stream/{uvid}', | |
| 91 | uvid, 'Downloading stream JSON', query={ | |
| 92 | 'key': video_data.get('data-key'), | |
| 93 | 'platform': self._PLATFORM, | |
| 94 | }) | |
| 95 | if traverse_obj(stream_data, 'drm'): | |
| 96 | self.report_drm(uvid) | |
| 97 | ||
| 98 | return { | |
| 99 | 'id': uvid, | |
| 100 | 'display_id': display_id, | |
| 101 | 'title': self._og_search_title(webpage, default=None), | |
| 102 | 'description': self._og_search_description(webpage, default=None), | |
| 103 | 'formats': self._extract_m3u8_formats(traverse_obj(stream_data, ( | |
| 104 | 'response', 'stream', {url_or_none})), uvid, 'mp4'), | |
| 105 | 'thumbnail': self._og_search_thumbnail(webpage, default=None), | |
| 106 | 'is_live': video_type == 'live', | |
| 107 | } |