yt_dlp/extractor/ccma.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import calendar
   5 import datetime
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     clean_html,
  10     extract_timezone,
  11     int_or_none,
  12     parse_duration,
  13     parse_resolution,
  14     try_get,
  15     url_or_none,
  16 )
  17
  18
  19 class CCMAIE(InfoExtractor):
  20     _VALID_URL = r'https?://(?:www\.)?ccma\.cat/(?:[^/]+/)*?(?P<type>video|audio)/(?P<id>\d+)'
  21     _TESTS = [{
  22         'url': 'http://www.ccma.cat/tv3/alacarta/lespot-de-la-marato-de-tv3/lespot-de-la-marato-de-tv3/video/5630208/',
  23         'md5': '7296ca43977c8ea4469e719c609b0871',
  24         'info_dict': {
  25             'id': '5630208',
  26             'ext': 'mp4',
  27             'title': 'L\'espot de La Marató de TV3',
  28             'description': 'md5:f12987f320e2f6e988e9908e4fe97765',
  29             'timestamp': 1478608140,
  30             'upload_date': '20161108',
  31             'age_limit': 0,
  32         }
  33     }, {
  34         'url': 'http://www.ccma.cat/catradio/alacarta/programa/el-consell-de-savis-analitza-el-derbi/audio/943685/',
  35         'md5': 'fa3e38f269329a278271276330261425',
  36         'info_dict': {
  37             'id': '943685',
  38             'ext': 'mp3',
  39             'title': 'El Consell de Savis analitza el derbi',
  40             'description': 'md5:e2a3648145f3241cb9c6b4b624033e53',
  41             'upload_date': '20170512',
  42             'timestamp': 1494622500,
  43             'vcodec': 'none',
  44             'categories': ['Esports'],
  45         }
  46     }, {
  47         'url': 'http://www.ccma.cat/tv3/alacarta/crims/crims-josep-tallada-lespereu-me-capitol-1/video/6031387/',
  48         'md5': 'b43c3d3486f430f3032b5b160d80cbc3',
  49         'info_dict': {
  50             'id': '6031387',
  51             'ext': 'mp4',
  52             'title': 'Crims - Josep Talleda, l\'"Espereu-me" (capítol 1)',
  53             'description': 'md5:7cbdafb640da9d0d2c0f62bad1e74e60',
  54             'timestamp': 1582577700,
  55             'upload_date': '20200224',
  56             'subtitles': 'mincount:4',
  57             'age_limit': 16,
  58             'series': 'Crims',
  59         }
  60     }]
  61
  62     def _real_extract(self, url):
  63         media_type, media_id = self._match_valid_url(url).groups()
  64
  65         media = self._download_json(
  66             'http://dinamics.ccma.cat/pvideo/media.jsp', media_id, query={
  67                 'media': media_type,
  68                 'idint': media_id,
  69             })
  70
  71         formats = []
  72         media_url = media['media']['url']
  73         if isinstance(media_url, list):
  74             for format_ in media_url:
  75                 format_url = url_or_none(format_.get('file'))
  76                 if not format_url:
  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         self._sort_formats(formats)
  91
  92         informacio = media['informacio']
  93         title = informacio['titol']
  94         durada = informacio.get('durada') or {}
  95         duration = int_or_none(durada.get('milisegons'), 1000) or parse_duration(durada.get('text'))
  96         tematica = try_get(informacio, lambda x: x['tematica']['text'])
  97
  98         timestamp = None
  99         data_utc = try_get(informacio, lambda x: x['data_emissio']['utc'])
 100         try:
 101             timezone, data_utc = extract_timezone(data_utc)
 102             timestamp = calendar.timegm((datetime.datetime.strptime(
 103                 data_utc, '%Y-%d-%mT%H:%M:%S') - timezone).timetuple())
 104         except TypeError:
 105             pass
 106
 107         subtitles = {}
 108         subtitols = media.get('subtitols') or []
 109         if isinstance(subtitols, dict):
 110             subtitols = [subtitols]
 111         for st in subtitols:
 112             sub_url = st.get('url')
 113             if sub_url:
 114                 subtitles.setdefault(
 115                     st.get('iso') or st.get('text') or 'ca', []).append({
 116                         'url': sub_url,
 117                     })
 118
 119         thumbnails = []
 120         imatges = media.get('imatges', {})
 121         if imatges:
 122             thumbnail_url = imatges.get('url')
 123             if thumbnail_url:
 124                 thumbnails = [{
 125                     'url': thumbnail_url,
 126                     'width': int_or_none(imatges.get('amplada')),
 127                     'height': int_or_none(imatges.get('alcada')),
 128                 }]
 129
 130         age_limit = None
 131         codi_etic = try_get(informacio, lambda x: x['codi_etic']['id'])
 132         if codi_etic:
 133             codi_etic_s = codi_etic.split('_')
 134             if len(codi_etic_s) == 2:
 135                 if codi_etic_s[1] == 'TP':
 136                     age_limit = 0
 137                 else:
 138                     age_limit = int_or_none(codi_etic_s[1])
 139
 140         return {
 141             'id': media_id,
 142             'title': title,
 143             'description': clean_html(informacio.get('descripcio')),
 144             'duration': duration,
 145             'timestamp': timestamp,
 146             'thumbnails': thumbnails,
 147             'subtitles': subtitles,
 148             'formats': formats,
 149             'age_limit': age_limit,
 150             'alt_title': informacio.get('titol_complet'),
 151             'episode_number': int_or_none(informacio.get('capitol')),
 152             'categories': [tematica] if tematica else None,
 153             'series': informacio.get('programa'),
 154         }