yt_dlp/extractor/antenna.py

   1 import urllib.parse
   2
   3 from .common import InfoExtractor
   4 from ..networking import HEADRequest
   5 from ..utils import (
   6     ExtractorError,
   7     determine_ext,
   8     make_archive_id,
   9     scale_thumbnails_to_max_format_width,
  10 )
  11
  12
  13 class AntennaBaseIE(InfoExtractor):
  14     def _download_and_extract_api_data(self, video_id, netloc, cid=None):
  15         info = self._download_json(f'{self.http_scheme()}//{netloc}{self._API_PATH}',
  16                                    video_id, query={'cid': cid or video_id})
  17         if not info.get('url'):
  18             raise ExtractorError(f'No source found for {video_id}')
  19
  20         ext = determine_ext(info['url'])
  21         if ext == 'm3u8':
  22             formats, subs = self._extract_m3u8_formats_and_subtitles(info['url'], video_id, 'mp4')
  23         else:
  24             formats, subs = [{'url': info['url'], 'format_id': ext}], {}
  25
  26         thumbnails = scale_thumbnails_to_max_format_width(
  27             formats, [{'url': info['thumb']}], r'(?<=/imgHandler/)\d+') if info.get('thumb') else []
  28         return {
  29             'id': video_id,
  30             'title': info.get('title'),
  31             'thumbnails': thumbnails,
  32             'formats': formats,
  33             'subtitles': subs,
  34         }
  35
  36
  37 class AntennaGrWatchIE(AntennaBaseIE):
  38     IE_NAME = 'antenna:watch'
  39     IE_DESC = 'antenna.gr and ant1news.gr videos'
  40     _VALID_URL = r'https?://(?P<netloc>(?:www\.)?(?:antenna|ant1news)\.gr)/watch/(?P<id>\d+)/'
  41     _API_PATH = '/templates/data/player'
  42
  43     _TESTS = [{
  44         'url': 'https://www.ant1news.gr/watch/1506168/ant1-news-09112021-stis-18-45',
  45         'md5': 'c472d9dd7cd233c63aff2ea42201cda6',
  46         'info_dict': {
  47             'id': '1506168',
  48             'ext': 'mp4',
  49             'title': 'md5:0ad00fa66ecf8aa233d26ab0dba7514a',
  50             'description': 'md5:18665af715a6dcfeac1d6153a44f16b0',
  51             'thumbnail': r're:https://ant1media\.azureedge\.net/imgHandler/\d+/26d46bf6-8158-4f02-b197-7096c714b2de\.jpg',
  52         },
  53     }, {
  54         'url': 'https://www.antenna.gr/watch/1643812/oi-prodotes-epeisodio-01',
  55         'md5': '8f6f7dd3b1dba4d835ba990e25f31243',
  56         'info_dict': {
  57             'id': '1643812',
  58             'ext': 'mp4',
  59             'format_id': 'mp4',
  60             'title': 'ΟΙ ΠΡΟΔΟΤΕΣ – ΕΠΕΙΣΟΔΙΟ 01',
  61             'thumbnail': r're:https://ant1media\.azureedge\.net/imgHandler/\d+/b3d63096-e72d-43c4-87a0-00d4363d242f\.jpg',
  62         },
  63     }]
  64
  65     def _real_extract(self, url):
  66         video_id, netloc = self._match_valid_url(url).group('id', 'netloc')
  67         webpage = self._download_webpage(url, video_id)
  68         info = self._download_and_extract_api_data(video_id, netloc)
  69         info['description'] = self._og_search_description(webpage, default=None)
  70         info['_old_archive_ids'] = [make_archive_id('Ant1NewsGrWatch', video_id)]
  71         return info
  72
  73
  74 class Ant1NewsGrArticleIE(AntennaBaseIE):
  75     IE_NAME = 'ant1newsgr:article'
  76     IE_DESC = 'ant1news.gr articles'
  77     _VALID_URL = r'https?://(?:www\.)?ant1news\.gr/[^/]+/article/(?P<id>\d+)/'
  78
  79     _TESTS = [{
  80         'url': 'https://www.ant1news.gr/afieromata/article/549468/o-tzeims-mpont-sta-meteora-oi-apeiles-kai-o-xesikomos-ton-kalogeron',
  81         'md5': '57eb8d12181f0fa2b14b0b138e1de9b6',
  82         'info_dict': {
  83             'id': '_xvg/m_cmbatw=',
  84             'ext': 'mp4',
  85             'title': 'md5:a93e8ecf2e4073bfdffcb38f59945411',
  86             'timestamp': 1666166520,
  87             'upload_date': '20221019',
  88             'thumbnail': 'https://ant1media.azureedge.net/imgHandler/1920/756206d2-d640-40e2-b201-3555abdfc0db.jpg',
  89         },
  90     }, {
  91         'url': 'https://ant1news.gr/Society/article/620286/symmoria-anilikon-dikigoros-thymaton-ithelan-na-toys-apoteleiosoyn',
  92         'info_dict': {
  93             'id': '620286',
  94             'title': 'md5:91fe569e952e4d146485740ae927662b',
  95         },
  96         'playlist_mincount': 2,
  97         'params': {
  98             'skip_download': True,
  99         },
 100     }]
 101
 102     def _real_extract(self, url):
 103         video_id = self._match_id(url)
 104         webpage = self._download_webpage(url, video_id)
 105         info = self._search_json_ld(webpage, video_id, expected_type='NewsArticle')
 106         embed_urls = list(Ant1NewsGrEmbedIE._extract_embed_urls(url, webpage))
 107         if not embed_urls:
 108             raise ExtractorError(f'no videos found for {video_id}', expected=True)
 109         return self.playlist_from_matches(
 110             embed_urls, video_id, info.get('title'), ie=Ant1NewsGrEmbedIE.ie_key(),
 111             video_kwargs={'url_transparent': True, 'timestamp': info.get('timestamp')})
 112
 113
 114 class Ant1NewsGrEmbedIE(AntennaBaseIE):
 115     IE_NAME = 'ant1newsgr:embed'
 116     IE_DESC = 'ant1news.gr embedded videos'
 117     _BASE_PLAYER_URL_RE = r'(?:https?:)?//(?:[a-zA-Z0-9\-]+\.)?(?:antenna|ant1news)\.gr/templates/pages/player'
 118     _VALID_URL = rf'{_BASE_PLAYER_URL_RE}\?([^#]+&)?cid=(?P<id>[^#&]+)'
 119     _EMBED_REGEX = [rf'<iframe[^>]+?src=(?P<_q1>["\'])(?P<url>{_BASE_PLAYER_URL_RE}\?(?:(?!(?P=_q1)).)+)(?P=_q1)']
 120     _API_PATH = '/templates/data/jsonPlayer'
 121
 122     _TESTS = [{
 123         'url': 'https://www.antenna.gr/templates/pages/player?cid=3f_li_c_az_jw_y_u=&w=670&h=377',
 124         'md5': 'dfc58c3a11a5a9aad2ba316ed447def3',
 125         'info_dict': {
 126             'id': '3f_li_c_az_jw_y_u=',
 127             'ext': 'mp4',
 128             'title': 'md5:a30c93332455f53e1e84ae0724f0adf7',
 129             'thumbnail': 'https://ant1media.azureedge.net/imgHandler/640/bbe31201-3f09-4a4e-87f5-8ad2159fffe2.jpg',
 130         },
 131     }]
 132
 133     def _real_extract(self, url):
 134         video_id = self._match_id(url)
 135
 136         canonical_url = self._request_webpage(
 137             HEADRequest(url), video_id,
 138             note='Resolve canonical player URL',
 139             errnote='Could not resolve canonical player URL').url
 140         _, netloc, _, _, query, _ = urllib.parse.urlparse(canonical_url)
 141         cid = urllib.parse.parse_qs(query)['cid'][0]
 142
 143         return self._download_and_extract_api_data(video_id, netloc, cid=cid)