yt_dlp/extractor/ccma.py

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