yt_dlp/extractor/telecaribe.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import traverse_obj
   5
   6
   7 class TelecaribePlayIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?play\.telecaribe\.co/(?P<id>[\w-]+)'
   9     _TESTS = [{
  10         'url': 'https://www.play.telecaribe.co/breicok',
  11         'info_dict': {
  12             'id': 'breicok',
  13             'title': 'Breicok',
  14         },
  15         'playlist_count': 7,
  16     }, {
  17         'url': 'https://www.play.telecaribe.co/si-fue-gol-de-yepes',
  18         'info_dict': {
  19             'id': 'si-fue-gol-de-yepes',
  20             'title': 'Sí Fue Gol de Yepes',
  21         },
  22         'playlist_count': 6,
  23     }, {
  24         'url': 'https://www.play.telecaribe.co/ciudad-futura',
  25         'info_dict': {
  26             'id': 'ciudad-futura',
  27             'title': 'Ciudad Futura',
  28         },
  29         'playlist_count': 10,
  30     }, {
  31         'url': 'https://www.play.telecaribe.co/live',
  32         'info_dict': {
  33             'id': 'live',
  34             'title': r're:^Señal en vivo',
  35             'live_status': 'is_live',
  36             'ext': 'mp4',
  37         },
  38         'params': {
  39             'skip_download': 'Livestream',
  40         }
  41     }, {
  42         'url': 'https://www.play.telecaribe.co/liveplus',
  43         'info_dict': {
  44             'id': 'liveplus',
  45             'title': r're:^Señal en vivo Plus',
  46             'live_status': 'is_live',
  47             'ext': 'mp4',
  48         },
  49         'params': {
  50             'skip_download': 'Livestream',
  51         },
  52         'skip': 'Geo-restricted to Colombia',
  53     }]
  54
  55     def _download_player_webpage(self, webpage, display_id):
  56         page_id = self._search_regex(
  57             (r'window\.firstPageId\s*=\s*["\']([^"\']+)', r'<div[^>]+id\s*=\s*"pageBackground_([^"]+)'),
  58             webpage, 'page_id')
  59
  60         props = self._download_json(self._search_regex(
  61             rf'<link[^>]+href\s*=\s*"([^"]+)"[^>]+id\s*=\s*"features_{page_id}"',
  62             webpage, 'json_props_url'), display_id)['props']['render']['compProps']
  63
  64         return self._download_webpage(traverse_obj(props, (..., 'url'))[-1], display_id)
  65
  66     def _get_clean_title(self, title):
  67         return re.sub(r'\s*\|\s*Telecaribe\s*VOD', '', title or '').strip() or None
  68
  69     def _real_extract(self, url):
  70         display_id = self._match_id(url)
  71         webpage = self._download_webpage(url, display_id)
  72         player = self._download_player_webpage(webpage, display_id)
  73
  74         livestream_url = self._search_regex(
  75             r'(?:let|const|var)\s+source\s*=\s*["\']([^"\']+)', player, 'm3u8 url', default=None)
  76
  77         if not livestream_url:
  78             return self.playlist_from_matches(
  79                 re.findall(r'<a[^>]+href\s*=\s*"([^"]+\.mp4)', player), display_id,
  80                 self._get_clean_title(self._og_search_title(webpage)))
  81
  82         formats, subtitles = self._extract_m3u8_formats_and_subtitles(
  83             livestream_url, display_id, 'mp4', live=True)
  84
  85         return {
  86             'id': display_id,
  87             'title': self._get_clean_title(self._og_search_title(webpage)),
  88             'formats': formats,
  89             'subtitles': subtitles,
  90             'is_live': True,
  91         }