Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/swrmediathek.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     parse_duration,
   7     int_or_none,
   8     determine_protocol,
   9 )
  10
  11
  12 class SWRMediathekIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?swrmediathek\.de/(?:content/)?player\.htm\?show=(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
  14
  15     _TESTS = [{
  16         'url': 'http://swrmediathek.de/player.htm?show=849790d0-dab8-11e3-a953-0026b975f2e6',
  17         'md5': '8c5f6f0172753368547ca8413a7768ac',
  18         'info_dict': {
  19             'id': '849790d0-dab8-11e3-a953-0026b975f2e6',
  20             'ext': 'mp4',
  21             'title': 'SWR odysso',
  22             'description': 'md5:2012e31baad36162e97ce9eb3f157b8a',
  23             'thumbnail': r're:^http:.*\.jpg$',
  24             'duration': 2602,
  25             'upload_date': '20140515',
  26             'uploader': 'SWR Fernsehen',
  27             'uploader_id': '990030',
  28         },
  29     }, {
  30         'url': 'http://swrmediathek.de/player.htm?show=0e1a8510-ddf2-11e3-9be3-0026b975f2e6',
  31         'md5': 'b10ab854f912eecc5a6b55cd6fc1f545',
  32         'info_dict': {
  33             'id': '0e1a8510-ddf2-11e3-9be3-0026b975f2e6',
  34             'ext': 'mp4',
  35             'title': 'Nachtcafé - Alltagsdroge Alkohol - zwischen Sektempfang und Komasaufen',
  36             'description': 'md5:e0a3adc17e47db2c23aab9ebc36dbee2',
  37             'thumbnail': r're:http://.*\.jpg',
  38             'duration': 5305,
  39             'upload_date': '20140516',
  40             'uploader': 'SWR Fernsehen',
  41             'uploader_id': '990030',
  42         },
  43         'skip': 'redirect to http://swrmediathek.de/index.htm?hinweis=swrlink',
  44     }, {
  45         'url': 'http://swrmediathek.de/player.htm?show=bba23e10-cb93-11e3-bf7f-0026b975f2e6',
  46         'md5': '4382e4ef2c9d7ce6852535fa867a0dd3',
  47         'info_dict': {
  48             'id': 'bba23e10-cb93-11e3-bf7f-0026b975f2e6',
  49             'ext': 'mp3',
  50             'title': 'Saša Stanišic: Vor dem Fest',
  51             'description': 'md5:5b792387dc3fbb171eb709060654e8c9',
  52             'thumbnail': r're:http://.*\.jpg',
  53             'duration': 3366,
  54             'upload_date': '20140520',
  55             'uploader': 'SWR 2',
  56             'uploader_id': '284670',
  57         },
  58         'skip': 'redirect to http://swrmediathek.de/index.htm?hinweis=swrlink',
  59     }]
  60
  61     def _real_extract(self, url):
  62         video_id = self._match_id(url)
  63
  64         video = self._download_json(
  65             'http://swrmediathek.de/AjaxEntry?ekey=%s' % video_id,
  66             video_id, 'Downloading video JSON')
  67
  68         attr = video['attr']
  69         title = attr['entry_title']
  70         media_type = attr.get('entry_etype')
  71
  72         formats = []
  73         for entry in video.get('sub', []):
  74             if entry.get('name') != 'entry_media':
  75                 continue
  76
  77             entry_attr = entry.get('attr', {})
  78             f_url = entry_attr.get('val2')
  79             if not f_url:
  80                 continue
  81             codec = entry_attr.get('val0')
  82             if codec == 'm3u8':
  83                 formats.extend(self._extract_m3u8_formats(
  84                     f_url, video_id, 'mp4', 'm3u8_native',
  85                     m3u8_id='hls', fatal=False))
  86             elif codec == 'f4m':
  87                 formats.extend(self._extract_f4m_formats(
  88                     f_url + '?hdcore=3.7.0', video_id,
  89                     f4m_id='hds', fatal=False))
  90             else:
  91                 formats.append({
  92                     'format_id': determine_protocol({'url': f_url}),
  93                     'url': f_url,
  94                     'quality': int_or_none(entry_attr.get('val1')),
  95                     'vcodec': codec if media_type == 'Video' else 'none',
  96                     'acodec': codec if media_type == 'Audio' else None,
  97                 })
  98         self._sort_formats(formats)
  99
 100         upload_date = None
 101         entry_pdatet = attr.get('entry_pdatet')
 102         if entry_pdatet:
 103             upload_date = entry_pdatet[:-4]
 104
 105         return {
 106             'id': video_id,
 107             'title': title,
 108             'description': attr.get('entry_descl'),
 109             'thumbnail': attr.get('entry_image_16_9'),
 110             'duration': parse_duration(attr.get('entry_durat')),
 111             'upload_date': upload_date,
 112             'uploader': attr.get('channel_title'),
 113             'uploader_id': attr.get('channel_idkey'),
 114             'formats': formats,
 115         }