yt_dlp/extractor/camfm.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     clean_html,
   6     get_element_by_class,
   7     get_elements_by_class,
   8     join_nonempty,
   9     traverse_obj,
  10     unified_timestamp,
  11     urljoin,
  12 )
  13
  14
  15 class CamFMShowIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?camfm\.co\.uk/shows/(?P<id>[^/]+)'
  17     _TESTS = [{
  18         'playlist_mincount': 5,
  19         'url': 'https://camfm.co.uk/shows/soul-mining/',
  20         'info_dict': {
  21             'id': 'soul-mining',
  22             'thumbnail': 'md5:6a873091f92c936f23bdcce80f75e66a',
  23             'title': 'Soul Mining',
  24             'description': 'Telling the stories of jazz, funk and soul from all corners of the world.',
  25         },
  26     }]
  27
  28     def _real_extract(self, url):
  29         show_id = self._match_id(url)
  30         page = self._download_webpage(url, show_id)
  31
  32         return {
  33             '_type': 'playlist',
  34             'id': show_id,
  35             'entries': [self.url_result(urljoin('https://camfm.co.uk', i), CamFMEpisodeIE)
  36                         for i in re.findall(r"javascript:popup\('(/player/[^']+)', 'listen'", page)],
  37             'thumbnail': urljoin('https://camfm.co.uk', self._search_regex(
  38                 r'<img[^>]+class="thumb-expand"[^>]+src="([^"]+)"', page, 'thumbnail', fatal=False)),
  39             'title': self._html_search_regex('<h1>([^<]+)</h1>', page, 'title', fatal=False),
  40             'description': clean_html(get_element_by_class('small-12 medium-8 cell', page)),
  41         }
  42
  43
  44 class CamFMEpisodeIE(InfoExtractor):
  45     _VALID_URL = r'https?://(?:www\.)?camfm\.co\.uk/player/(?P<id>[^/]+)'
  46     _TESTS = [{
  47         'url': 'https://camfm.co.uk/player/43336',
  48         'skip': 'Episode will expire - don\'t actually know when, but it will go eventually',
  49         'info_dict': {
  50             'id': '43336',
  51             'title': 'AITAA: Am I the Agony Aunt? - 19:00 Tue 16/05/2023',
  52             'ext': 'mp3',
  53             'upload_date': '20230516',
  54             'description': 'md5:f165144f94927c0f1bfa2ee6e6ab7bbf',
  55             'timestamp': 1684263600,
  56             'series': 'AITAA: Am I the Agony Aunt?',
  57             'thumbnail': 'md5:5980a831360d0744c3764551be3d09c1',
  58             'categories': ['Entertainment'],
  59         },
  60     }]
  61
  62     def _real_extract(self, url):
  63         episode_id = self._match_id(url)
  64         page = self._download_webpage(url, episode_id)
  65         audios = self._parse_html5_media_entries('https://audio.camfm.co.uk', page, episode_id)
  66
  67         caption = get_element_by_class('caption', page)
  68         series = clean_html(re.sub(r'<span[^<]+<[^<]+>', '', caption))
  69
  70         card_section = get_element_by_class('card-section', page)
  71         date = self._html_search_regex('>Aired at ([^<]+)<', card_section, 'air date', fatal=False)
  72
  73         return {
  74             'id': episode_id,
  75             'title': join_nonempty(series, date, delim=' - '),
  76             'formats': traverse_obj(audios, (..., 'formats', ...)),
  77             'timestamp': unified_timestamp(date),  # XXX: Does not account for UK's daylight savings
  78             'series': series,
  79             'description': clean_html(re.sub(r'<b>[^<]+</b><br[^>]+/>', '', card_section)),
  80             'thumbnail': urljoin('https://camfm.co.uk', self._search_regex(
  81                 r'<div[^>]+class="cover-art"[^>]+style="[^"]+url\(\'([^\']+)',
  82                 page, 'thumbnail', fatal=False)),
  83             'categories': get_elements_by_class('label', caption),
  84             'was_live': True,
  85         }