yt_dlp/extractor/megatvcom.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..networking import HEADRequest
   5 from ..utils import (
   6     ExtractorError,
   7     clean_html,
   8     determine_ext,
   9     extract_attributes,
  10     get_element_by_class,
  11     get_element_html_by_id,
  12     parse_qs,
  13     unescapeHTML,
  14     unified_timestamp,
  15 )
  16
  17
  18 class MegaTVComBaseIE(InfoExtractor):
  19     _PLAYER_DIV_ID = 'player_div_id'
  20
  21     def _extract_player_attrs(self, webpage):
  22         player_el = get_element_html_by_id(self._PLAYER_DIV_ID, webpage)
  23         return {
  24             re.sub(r'^data-(?:kwik_)?', '', k): v
  25             for k, v in extract_attributes(player_el).items()
  26             if k not in ('id',)
  27         }
  28
  29
  30 class MegaTVComIE(MegaTVComBaseIE):
  31     IE_NAME = 'megatvcom'
  32     IE_DESC = 'megatv.com videos'
  33     _VALID_URL = r'https?://(?:www\.)?megatv\.com/(?:\d{4}/\d{2}/\d{2}|[^/]+/(?P<id>\d+))/(?P<slug>[^/]+)'
  34
  35     _TESTS = [{
  36         'url': 'https://www.megatv.com/2021/10/23/egkainia-gia-ti-nea-skini-omega-tou-dimotikou-theatrou-peiraia/',
  37         'md5': '6546a1a37fff0dd51c9dce5f490b7d7d',
  38         'info_dict': {
  39             'id': '520979',
  40             'ext': 'mp4',
  41             'title': 'md5:70eef71a9cd2c1ecff7ee428354dded2',
  42             'description': 'md5:0209fa8d318128569c0d256a5c404db1',
  43             'timestamp': 1634975747,
  44             'upload_date': '20211023',
  45             'display_id': 'egkainia-gia-ti-nea-skini-omega-tou-dimotikou-theatrou-peiraia',
  46             'thumbnail': 'https://www.megatv.com/wp-content/uploads/2021/10/ΠΕΙΡΑΙΑΣ-1024x450.jpg',
  47         },
  48     }, {
  49         'url': 'https://www.megatv.com/tvshows/527800/epeisodio-65-12/',
  50         'md5': 'cba2085d45c1abeb8e7e9b7e1d6c0072',
  51         'info_dict': {
  52             'id': '527800',
  53             'ext': 'mp4',
  54             'title': 'md5:fc322cb51f682eecfe2f54cd5ab3a157',
  55             'description': 'md5:b2b7ed3690a78f2a0156eb790fdc00df',
  56             'timestamp': 1636048859,
  57             'upload_date': '20211104',
  58             'display_id': 'epeisodio-65-12',
  59             'thumbnail': 'https://www.megatv.com/wp-content/uploads/2021/11/16-1-1.jpg',
  60         },
  61     }]
  62
  63     def _real_extract(self, url):
  64         video_id, display_id = self._match_valid_url(url).group('id', 'slug')
  65         _is_article = video_id is None
  66         webpage = self._download_webpage(url, video_id or display_id)
  67         if _is_article:
  68             video_id = self._search_regex(
  69                 r'<article[^>]*\sid=["\']Article_(\d+)["\']', webpage, 'article id')
  70         player_attrs = self._extract_player_attrs(webpage)
  71         title = player_attrs.get('label') or self._og_search_title(webpage)
  72         description = get_element_by_class(
  73             'article-wrapper' if _is_article else 'story_content',
  74             webpage)
  75         description = clean_html(re.sub(r'<script[^>]*>[^<]+</script>', '', description))
  76         if not description:
  77             description = self._og_search_description(webpage)
  78         thumbnail = player_attrs.get('image') or self._og_search_thumbnail(webpage)
  79         timestamp = unified_timestamp(self._html_search_meta(
  80             'article:published_time', webpage))
  81         source = player_attrs.get('source')
  82         if not source:
  83             raise ExtractorError('No source found', video_id=video_id)
  84         if determine_ext(source) == 'm3u8':
  85             formats, subs = self._extract_m3u8_formats_and_subtitles(source, video_id, 'mp4')
  86         else:
  87             formats, subs = [{'url': source}], {}
  88         if player_attrs.get('subs'):
  89             self._merge_subtitles({'und': [{'url': player_attrs['subs']}]}, target=subs)
  90         return {
  91             'id': video_id,
  92             'display_id': display_id,
  93             'title': title,
  94             'description': description,
  95             'thumbnail': thumbnail,
  96             'timestamp': timestamp,
  97             'formats': formats,
  98             'subtitles': subs,
  99         }
 100
 101
 102 class MegaTVComEmbedIE(MegaTVComBaseIE):
 103     IE_NAME = 'megatvcom:embed'
 104     IE_DESC = 'megatv.com embedded videos'
 105     _VALID_URL = r'(?:https?:)?//(?:www\.)?megatv\.com/embed/?\?p=(?P<id>\d+)'
 106     _EMBED_REGEX = [rf'''<iframe[^>]+?src=(?P<_q1>["'])(?P<url>{_VALID_URL})(?P=_q1)''']
 107
 108     _TESTS = [{
 109         'url': 'https://www.megatv.com/embed/?p=2020520979',
 110         'md5': '6546a1a37fff0dd51c9dce5f490b7d7d',
 111         'info_dict': {
 112             'id': '520979',
 113             'ext': 'mp4',
 114             'title': 'md5:70eef71a9cd2c1ecff7ee428354dded2',
 115             'description': 'md5:0209fa8d318128569c0d256a5c404db1',
 116             'timestamp': 1634975747,
 117             'upload_date': '20211023',
 118             'display_id': 'egkainia-gia-ti-nea-skini-omega-tou-dimotikou-theatrou-peiraia',
 119             'thumbnail': 'https://www.megatv.com/wp-content/uploads/2021/10/ΠΕΙΡΑΙΑΣ-1024x450.jpg',
 120         },
 121     }, {
 122         'url': 'https://www.megatv.com/embed/?p=2020534081',
 123         'md5': '6ac8b3ce4dc6120c802f780a1e6b3812',
 124         'info_dict': {
 125             'id': '534081',
 126             'ext': 'mp4',
 127             'title': 'md5:062e9d5976ef854d8bdc1f5724d9b2d0',
 128             'description': 'md5:36dbe4c3762d2ede9513eea8d07f6d52',
 129             'timestamp': 1636376351,
 130             'upload_date': '20211108',
 131             'display_id': 'neo-rekor-stin-timi-tou-ilektrikou-reymatos-pano-apo-ta-200e-i-xondriki-timi-tou-ilektrikou',
 132             'thumbnail': 'https://www.megatv.com/wp-content/uploads/2021/11/Capture-266.jpg',
 133         },
 134     }]
 135
 136     def _match_canonical_url(self, webpage):
 137         LINK_RE = r'''(?x)
 138         <link(?:
 139             rel=(?P<_q1>["'])(?P<canonical>canonical)(?P=_q1)|
 140             href=(?P<_q2>["'])(?P<href>(?:(?!(?P=_q2)).)+)(?P=_q2)|
 141             [^>]*?
 142         )+>
 143         '''
 144         for mobj in re.finditer(LINK_RE, webpage):
 145             canonical, href = mobj.group('canonical', 'href')
 146             if canonical and href:
 147                 return unescapeHTML(href)
 148
 149     def _real_extract(self, url):
 150         video_id = self._match_id(url)
 151         webpage = self._download_webpage(url, video_id)
 152         player_attrs = self._extract_player_attrs(webpage)
 153         canonical_url = player_attrs.get('share_url') or self._match_canonical_url(webpage)
 154         if not canonical_url:
 155             raise ExtractorError('canonical URL not found')
 156         video_id = parse_qs(canonical_url)['p'][0]
 157
 158         # Defer to megatvcom as the metadata extracted from the embeddable page some
 159         # times are slightly different, for the same video
 160         canonical_url = self._request_webpage(
 161             HEADRequest(canonical_url), video_id,
 162             note='Resolve canonical URL',
 163             errnote='Could not resolve canonical URL').url
 164         return self.url_result(canonical_url, MegaTVComIE.ie_key(), video_id)