yt_dlp/extractor/ccma.py

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