_ Git - youtube-dl/blob - youtube_dl/extractor/drtv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     ExtractorError,
   7     parse_iso8601,
   8     remove_end,
   9 )
  10
  11
  12 class DRTVIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
  14
  15     _TESTS = [{
  16         'url': 'https://www.dr.dk/tv/se/boern/ultra/panisk-paske/panisk-paske-5',
  17         'md5': 'dc515a9ab50577fa14cc4e4b0265168f',
  18         'info_dict': {
  19             'id': 'panisk-paske-5',
  20             'ext': 'mp4',
  21             'title': 'Panisk Påske (5)',
  22             'description': 'md5:ca14173c5ab24cd26b0fcc074dff391c',
  23             'timestamp': 1426984612,
  24             'upload_date': '20150322',
  25             'duration': 1455,
  26         },
  27         'skip': 'Video is no longer available',
  28     }, {
  29         'url': 'https://www.dr.dk/nyheder/indland/live-christianias-rydning-af-pusher-street-er-i-gang',
  30         'md5': '2ada5074f9e79afc0d324a8e9784d850',
  31         'info_dict': {
  32             'id': 'christiania-pusher-street-ryddes-drdkrjpo',
  33             'ext': 'mp4',
  34             'title': 'LIVE Christianias rydning af Pusher Street er i gang',
  35             'description': '- Det er det fedeste, der er sket i 20 år, fortæller christianit til DR Nyheder.',
  36             'timestamp': 1472800279,
  37             'upload_date': '20160902',
  38             'duration': 131.4,
  39         }
  40     }]
  41
  42     def _real_extract(self, url):
  43         video_id = self._match_id(url)
  44
  45         webpage = self._download_webpage(url, video_id)
  46
  47         if '>Programmet er ikke længere tilgængeligt' in webpage:
  48             raise ExtractorError(
  49                 'Video %s is not available' % video_id, expected=True)
  50
  51         video_id = self._search_regex(
  52             (r'data-(?:material-identifier|episode-slug)="([^"]+)"',
  53                 r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'),
  54             webpage, 'video id')
  55
  56         programcard = self._download_json(
  57             'http://www.dr.dk/mu/programcard/expanded/%s' % video_id,
  58             video_id, 'Downloading video JSON')
  59         data = programcard['Data'][0]
  60
  61         title = remove_end(self._og_search_title(webpage), ' | TV | DR') or data['Title']
  62         description = self._og_search_description(webpage) or data['Description']
  63
  64         timestamp = parse_iso8601(data['CreatedTime'])
  65
  66         thumbnail = None
  67         duration = None
  68
  69         restricted_to_denmark = False
  70
  71         formats = []
  72         subtitles = {}
  73
  74         for asset in data['Assets']:
  75             if asset['Kind'] == 'Image':
  76                 thumbnail = asset['Uri']
  77             elif asset['Kind'] == 'VideoResource':
  78                 duration = asset['DurationInMilliseconds'] / 1000.0
  79                 restricted_to_denmark = asset['RestrictedToDenmark']
  80                 spoken_subtitles = asset['Target'] == 'SpokenSubtitles'
  81                 for link in asset['Links']:
  82                     uri = link['Uri']
  83                     target = link['Target']
  84                     format_id = target
  85                     preference = None
  86                     if spoken_subtitles:
  87                         preference = -1
  88                         format_id += '-spoken-subtitles'
  89                     if target == 'HDS':
  90                         formats.extend(self._extract_f4m_formats(
  91                             uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43',
  92                             video_id, preference, f4m_id=format_id))
  93                     elif target == 'HLS':
  94                         formats.extend(self._extract_m3u8_formats(
  95                             uri, video_id, 'mp4', preference=preference,
  96                             m3u8_id=format_id))
  97                     else:
  98                         bitrate = link.get('Bitrate')
  99                         if bitrate:
 100                             format_id += '-%s' % bitrate
 101                         formats.append({
 102                             'url': uri,
 103                             'format_id': format_id,
 104                             'tbr': bitrate,
 105                             'ext': link.get('FileFormat'),
 106                         })
 107                 subtitles_list = asset.get('SubtitlesList')
 108                 if isinstance(subtitles_list, list):
 109                     LANGS = {
 110                         'Danish': 'da',
 111                     }
 112                     for subs in subtitles_list:
 113                         lang = subs['Language']
 114                         subtitles[LANGS.get(lang, lang)] = [{'url': subs['Uri'], 'ext': 'vtt'}]
 115
 116         if not formats and restricted_to_denmark:
 117             raise ExtractorError(
 118                 'Unfortunately, DR is not allowed to show this program outside Denmark.', expected=True)
 119
 120         self._sort_formats(formats)
 121
 122         return {
 123             'id': video_id,
 124             'title': title,
 125             'description': description,
 126             'thumbnail': thumbnail,
 127             'timestamp': timestamp,
 128             'duration': duration,
 129             'formats': formats,
 130             'subtitles': subtitles,
 131         }