youtube_dlc/extractor/ccma.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import datetime
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     clean_html,
  10     int_or_none,
  11     parse_duration,
  12     parse_resolution,
  13     try_get,
  14     url_or_none,
  15 )
  16
  17
  18 class CCMAIE(InfoExtractor):
  19     _VALID_URL = r'https?://(?:www\.)?ccma\.cat/(?:[^/]+/)*?(?P<type>video|audio)/(?P<id>\d+)'
  20     _TESTS = [{
  21         'url': 'http://www.ccma.cat/tv3/alacarta/lespot-de-la-marato-de-tv3/lespot-de-la-marato-de-tv3/video/5630208/',
  22         'md5': '7296ca43977c8ea4469e719c609b0871',
  23         'info_dict': {
  24             'id': '5630208',
  25             'ext': 'mp4',
  26             'title': 'L\'espot de La Marató de TV3',
  27             'description': 'md5:f12987f320e2f6e988e9908e4fe97765',
  28             'timestamp': 1478608140,
  29             'upload_date': '20161108',
  30             'age_limit': 0,
  31         }
  32     }, {
  33         'url': 'http://www.ccma.cat/catradio/alacarta/programa/el-consell-de-savis-analitza-el-derbi/audio/943685/',
  34         'md5': 'fa3e38f269329a278271276330261425',
  35         'info_dict': {
  36             'id': '943685',
  37             'ext': 'mp3',
  38             'title': 'El Consell de Savis analitza el derbi',
  39             'description': 'md5:e2a3648145f3241cb9c6b4b624033e53',
  40             'upload_date': '20170512',
  41             'timestamp': 1494622500,
  42             'vcodec': 'none',
  43             'categories': ['Esports'],
  44         }
  45     }, {
  46         'url': 'http://www.ccma.cat/tv3/alacarta/crims/crims-josep-tallada-lespereu-me-capitol-1/video/6031387/',
  47         'md5': 'b43c3d3486f430f3032b5b160d80cbc3',
  48         'info_dict': {
  49             'id': '6031387',
  50             'ext': 'mp4',
  51             'title': 'Crims - Josep Talleda, l\'"Espereu-me" (capítol 1)',
  52             'description': 'md5:7cbdafb640da9d0d2c0f62bad1e74e60',
  53             'timestamp': 1582577700,
  54             'upload_date': '20200224',
  55             'subtitles': 'mincount:4',
  56             'age_limit': 16,
  57             'series': 'Crims',
  58         }
  59     }]
  60
  61     def _real_extract(self, url):
  62         media_type, media_id = re.match(self._VALID_URL, url).groups()
  63
  64         media = self._download_json(
  65             'http://dinamics.ccma.cat/pvideo/media.jsp', media_id, query={
  66                 'media': media_type,
  67                 'idint': media_id,
  68             })
  69
  70         formats = []
  71         media_url = media['media']['url']
  72         if isinstance(media_url, list):
  73             for format_ in media_url:
  74                 format_url = url_or_none(format_.get('file'))
  75                 if not format_url:
  76                     continue
  77                 label = format_.get('label')
  78                 f = parse_resolution(label)
  79                 f.update({
  80                     'url': format_url,
  81                     'format_id': label,
  82                 })
  83                 formats.append(f)
  84         else:
  85             formats.append({
  86                 'url': media_url,
  87                 'vcodec': 'none' if media_type == 'audio' else None,
  88             })
  89         self._sort_formats(formats)
  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         timestamp = None
  98         data_utc = try_get(informacio, lambda x: x['data_emissio']['utc'])
  99         try:
 100             timestamp = datetime.datetime.strptime(
 101                 data_utc, '%Y-%d-%mT%H:%M:%S%z').timestamp()
 102         except TypeError:
 103             pass
 104
 105         subtitles = {}
 106         subtitols = media.get('subtitols') or []
 107         if isinstance(subtitols, dict):
 108             subtitols = [subtitols]
 109         for st in subtitols:
 110             sub_url = st.get('url')
 111             if sub_url:
 112                 subtitles.setdefault(
 113                     st.get('iso') or st.get('text') or 'ca', []).append({
 114                         'url': sub_url,
 115                     })
 116
 117         thumbnails = []
 118         imatges = media.get('imatges', {})
 119         if imatges:
 120             thumbnail_url = imatges.get('url')
 121             if thumbnail_url:
 122                 thumbnails = [{
 123                     'url': thumbnail_url,
 124                     'width': int_or_none(imatges.get('amplada')),
 125                     'height': int_or_none(imatges.get('alcada')),
 126                 }]
 127
 128         age_limit = None
 129         codi_etic = try_get(informacio, lambda x: x['codi_etic']['id'])
 130         if codi_etic:
 131             codi_etic_s = codi_etic.split('_')
 132             if len(codi_etic_s) == 2:
 133                 if codi_etic_s[1] == 'TP':
 134                     age_limit = 0
 135                 else:
 136                     age_limit = int_or_none(codi_etic_s[1])
 137
 138         return {
 139             'id': media_id,
 140             'title': title,
 141             'description': clean_html(informacio.get('descripcio')),
 142             'duration': duration,
 143             'timestamp': timestamp,
 144             'thumbnails': thumbnails,
 145             'subtitles': subtitles,
 146             'formats': formats,
 147             'age_limit': age_limit,
 148             'alt_title': informacio.get('titol_complet'),
 149             'episode_number': int_or_none(informacio.get('capitol')),
 150             'categories': [tematica] if tematica else None,
 151             'series': informacio.get('programa'),
 152         }