yt_dlp/extractor/ccma.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     clean_html,
   4     determine_ext,
   5     int_or_none,
   6     parse_duration,
   7     parse_resolution,
   8     try_get,
   9     unified_timestamp,
  10     url_or_none,
  11 )
  12
  13
  14 class CCMAIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?ccma\.cat/(?:[^/]+/)*?(?P<type>video|audio)/(?P<id>\d+)'
  16     _TESTS = [{
  17         'url': 'http://www.ccma.cat/tv3/alacarta/lespot-de-la-marato-de-tv3/lespot-de-la-marato-de-tv3/video/5630208/',
  18         'md5': '7296ca43977c8ea4469e719c609b0871',
  19         'info_dict': {
  20             'id': '5630208',
  21             'ext': 'mp4',
  22             'title': 'L\'espot de La Marató de TV3',
  23             'description': 'md5:f12987f320e2f6e988e9908e4fe97765',
  24             'timestamp': 1478608140,
  25             'upload_date': '20161108',
  26             'age_limit': 0,
  27         },
  28     }, {
  29         'url': 'http://www.ccma.cat/catradio/alacarta/programa/el-consell-de-savis-analitza-el-derbi/audio/943685/',
  30         'md5': 'fa3e38f269329a278271276330261425',
  31         'info_dict': {
  32             'id': '943685',
  33             'ext': 'mp3',
  34             'title': 'El Consell de Savis analitza el derbi',
  35             'description': 'md5:e2a3648145f3241cb9c6b4b624033e53',
  36             'upload_date': '20170512',
  37             'timestamp': 1494622500,
  38             'vcodec': 'none',
  39             'categories': ['Esports'],
  40         },
  41     }, {
  42         'url': 'http://www.ccma.cat/tv3/alacarta/crims/crims-josep-tallada-lespereu-me-capitol-1/video/6031387/',
  43         'md5': 'b43c3d3486f430f3032b5b160d80cbc3',
  44         'info_dict': {
  45             'id': '6031387',
  46             'ext': 'mp4',
  47             'title': 'Crims - Josep Talleda, l\'"Espereu-me" (capítol 1)',
  48             'description': 'md5:7cbdafb640da9d0d2c0f62bad1e74e60',
  49             'timestamp': 1582577700,
  50             'upload_date': '20200224',
  51             'subtitles': 'mincount:4',
  52             'age_limit': 16,
  53             'series': 'Crims',
  54         },
  55     }]
  56
  57     def _real_extract(self, url):
  58         media_type, media_id = self._match_valid_url(url).groups()
  59
  60         media = self._download_json(
  61             'http://dinamics.ccma.cat/pvideo/media.jsp', media_id, query={
  62                 'media': media_type,
  63                 'idint': media_id,
  64                 'format': 'dm',
  65             })
  66
  67         formats = []
  68         media_url = media['media']['url']
  69         if isinstance(media_url, list):
  70             for format_ in media_url:
  71                 format_url = url_or_none(format_.get('file'))
  72                 if not format_url:
  73                     continue
  74                 if determine_ext(format_url) == 'mpd':
  75                     formats.extend(self._extract_mpd_formats(
  76                         format_url, media_id, mpd_id='dash', fatal=False))
  77                     continue
  78                 label = format_.get('label')
  79                 f = parse_resolution(label)
  80                 f.update({
  81                     'url': format_url,
  82                     'format_id': label,
  83                 })
  84                 formats.append(f)
  85         else:
  86             formats.append({
  87                 'url': media_url,
  88                 'vcodec': 'none' if media_type == 'audio' else None,
  89             })
  90
  91         informacio = media['informacio']
  92         title = informacio['titol']
  93         durada = informacio.get('durada') or {}
  94         duration = int_or_none(durada.get('milisegons'), 1000) or parse_duration(durada.get('text'))
  95         tematica = try_get(informacio, lambda x: x['tematica']['text'])
  96
  97         data_utc = try_get(informacio, lambda x: x['data_emissio']['utc'])
  98         timestamp = unified_timestamp(data_utc)
  99
 100         subtitles = {}
 101         subtitols = media.get('subtitols') or []
 102         if isinstance(subtitols, dict):
 103             subtitols = [subtitols]
 104         for st in subtitols:
 105             sub_url = st.get('url')
 106             if sub_url:
 107                 subtitles.setdefault(
 108                     st.get('iso') or st.get('text') or 'ca', []).append({
 109                         'url': sub_url,
 110                     })
 111
 112         thumbnails = []
 113         imatges = media.get('imatges', {})
 114         if imatges:
 115             thumbnail_url = imatges.get('url')
 116             if thumbnail_url:
 117                 thumbnails = [{
 118                     'url': thumbnail_url,
 119                     'width': int_or_none(imatges.get('amplada')),
 120                     'height': int_or_none(imatges.get('alcada')),
 121                 }]
 122
 123         age_limit = None
 124         codi_etic = try_get(informacio, lambda x: x['codi_etic']['id'])
 125         if codi_etic:
 126             codi_etic_s = codi_etic.split('_')
 127             if len(codi_etic_s) == 2:
 128                 if codi_etic_s[1] == 'TP':
 129                     age_limit = 0
 130                 else:
 131                     age_limit = int_or_none(codi_etic_s[1])
 132
 133         return {
 134             'id': media_id,
 135             'title': title,
 136             'description': clean_html(informacio.get('descripcio')),
 137             'duration': duration,
 138             'timestamp': timestamp,
 139             'thumbnails': thumbnails,
 140             'subtitles': subtitles,
 141             'formats': formats,
 142             'age_limit': age_limit,
 143             'alt_title': informacio.get('titol_complet'),
 144             'episode_number': int_or_none(informacio.get('capitol')),
 145             'categories': [tematica] if tematica else None,
 146             'series': informacio.get('programa'),
 147         }