yt_dlp/extractor/ccma.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import calendar
   5 import datetime
   6 import re
   7
   8 from .common import InfoExtractor
   9 from ..utils import (
  10     clean_html,
  11     extract_timezone,
  12     int_or_none,
  13     parse_duration,
  14     parse_resolution,
  15     try_get,
  16     url_or_none,
  17 )
  18
  19
  20 class CCMAIE(InfoExtractor):
  21     _VALID_URL = r'https?://(?:www\.)?ccma\.cat/(?:[^/]+/)*?(?P<type>video|audio)/(?P<id>\d+)'
  22     _TESTS = [{
  23         'url': 'http://www.ccma.cat/tv3/alacarta/lespot-de-la-marato-de-tv3/lespot-de-la-marato-de-tv3/video/5630208/',
  24         'md5': '7296ca43977c8ea4469e719c609b0871',
  25         'info_dict': {
  26             'id': '5630208',
  27             'ext': 'mp4',
  28             'title': 'L\'espot de La Marató de TV3',
  29             'description': 'md5:f12987f320e2f6e988e9908e4fe97765',
  30             'timestamp': 1478608140,
  31             'upload_date': '20161108',
  32             'age_limit': 0,
  33         }
  34     }, {
  35         'url': 'http://www.ccma.cat/catradio/alacarta/programa/el-consell-de-savis-analitza-el-derbi/audio/943685/',
  36         'md5': 'fa3e38f269329a278271276330261425',
  37         'info_dict': {
  38             'id': '943685',
  39             'ext': 'mp3',
  40             'title': 'El Consell de Savis analitza el derbi',
  41             'description': 'md5:e2a3648145f3241cb9c6b4b624033e53',
  42             'upload_date': '20170512',
  43             'timestamp': 1494622500,
  44             'vcodec': 'none',
  45             'categories': ['Esports'],
  46         }
  47     }, {
  48         'url': 'http://www.ccma.cat/tv3/alacarta/crims/crims-josep-tallada-lespereu-me-capitol-1/video/6031387/',
  49         'md5': 'b43c3d3486f430f3032b5b160d80cbc3',
  50         'info_dict': {
  51             'id': '6031387',
  52             'ext': 'mp4',
  53             'title': 'Crims - Josep Talleda, l\'"Espereu-me" (capítol 1)',
  54             'description': 'md5:7cbdafb640da9d0d2c0f62bad1e74e60',
  55             'timestamp': 1582577700,
  56             'upload_date': '20200224',
  57             'subtitles': 'mincount:4',
  58             'age_limit': 16,
  59             'series': 'Crims',
  60         }
  61     }]
  62
  63     def _real_extract(self, url):
  64         media_type, media_id = re.match(self._VALID_URL, url).groups()
  65
  66         media = self._download_json(
  67             'http://dinamics.ccma.cat/pvideo/media.jsp', media_id, query={
  68                 'media': media_type,
  69                 'idint': media_id,
  70             })
  71
  72         formats = []
  73         media_url = media['media']['url']
  74         if isinstance(media_url, list):
  75             for format_ in media_url:
  76                 format_url = url_or_none(format_.get('file'))
  77                 if not format_url:
  78                     continue
  79                 label = format_.get('label')
  80                 f = parse_resolution(label)
  81                 f.update({
  82                     'url': format_url,
  83                     'format_id': label,
  84                 })
  85                 formats.append(f)
  86         else:
  87             formats.append({
  88                 'url': media_url,
  89                 'vcodec': 'none' if media_type == 'audio' else None,
  90             })
  91         self._sort_formats(formats)
  92
  93         informacio = media['informacio']
  94         title = informacio['titol']
  95         durada = informacio.get('durada') or {}
  96         duration = int_or_none(durada.get('milisegons'), 1000) or parse_duration(durada.get('text'))
  97         tematica = try_get(informacio, lambda x: x['tematica']['text'])
  98
  99         timestamp = None
 100         data_utc = try_get(informacio, lambda x: x['data_emissio']['utc'])
 101         try:
 102             timezone, data_utc = extract_timezone(data_utc)
 103             timestamp = calendar.timegm((datetime.datetime.strptime(
 104                 data_utc, '%Y-%d-%mT%H:%M:%S') - timezone).timetuple())
 105         except TypeError:
 106             pass
 107
 108         subtitles = {}
 109         subtitols = media.get('subtitols') or []
 110         if isinstance(subtitols, dict):
 111             subtitols = [subtitols]
 112         for st in subtitols:
 113             sub_url = st.get('url')
 114             if sub_url:
 115                 subtitles.setdefault(
 116                     st.get('iso') or st.get('text') or 'ca', []).append({
 117                         'url': sub_url,
 118                     })
 119
 120         thumbnails = []
 121         imatges = media.get('imatges', {})
 122         if imatges:
 123             thumbnail_url = imatges.get('url')
 124             if thumbnail_url:
 125                 thumbnails = [{
 126                     'url': thumbnail_url,
 127                     'width': int_or_none(imatges.get('amplada')),
 128                     'height': int_or_none(imatges.get('alcada')),
 129                 }]
 130
 131         age_limit = None
 132         codi_etic = try_get(informacio, lambda x: x['codi_etic']['id'])
 133         if codi_etic:
 134             codi_etic_s = codi_etic.split('_')
 135             if len(codi_etic_s) == 2:
 136                 if codi_etic_s[1] == 'TP':
 137                     age_limit = 0
 138                 else:
 139                     age_limit = int_or_none(codi_etic_s[1])
 140
 141         return {
 142             'id': media_id,
 143             'title': title,
 144             'description': clean_html(informacio.get('descripcio')),
 145             'duration': duration,
 146             'timestamp': timestamp,
 147             'thumbnails': thumbnails,
 148             'subtitles': subtitles,
 149             'formats': formats,
 150             'age_limit': age_limit,
 151             'alt_title': informacio.get('titol_complet'),
 152             'episode_number': int_or_none(informacio.get('capitol')),
 153             'categories': [tematica] if tematica else None,
 154             'series': informacio.get('programa'),
 155         }