Raphaël G. Git Repositories - youtubedl/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 )
   9
  10
  11 class DRTVIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
  13
  14     _TEST = {
  15         'url': 'https://www.dr.dk/tv/se/boern/ultra/panisk-paske/panisk-paske-5',
  16         'md5': 'dc515a9ab50577fa14cc4e4b0265168f',
  17         'info_dict': {
  18             'id': 'panisk-paske-5',
  19             'ext': 'mp4',
  20             'title': 'Panisk Påske (5)',
  21             'description': 'md5:ca14173c5ab24cd26b0fcc074dff391c',
  22             'timestamp': 1426984612,
  23             'upload_date': '20150322',
  24             'duration': 1455,
  25         },
  26     }
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30
  31         webpage = self._download_webpage(url, video_id)
  32
  33         if '>Programmet er ikke længere tilgængeligt' in webpage:
  34             raise ExtractorError(
  35                 'Video %s is not available' % video_id, expected=True)
  36
  37         video_id = self._search_regex(
  38             r'data-(?:material-identifier|episode-slug)="([^"]+)"',
  39             webpage, 'video id')
  40
  41         programcard = self._download_json(
  42             'http://www.dr.dk/mu/programcard/expanded/%s' % video_id,
  43             video_id, 'Downloading video JSON')
  44         data = programcard['Data'][0]
  45
  46         title = data['Title']
  47         description = data['Description']
  48         timestamp = parse_iso8601(data['CreatedTime'])
  49
  50         thumbnail = None
  51         duration = None
  52
  53         restricted_to_denmark = False
  54
  55         formats = []
  56         subtitles = {}
  57
  58         for asset in data['Assets']:
  59             if asset['Kind'] == 'Image':
  60                 thumbnail = asset['Uri']
  61             elif asset['Kind'] == 'VideoResource':
  62                 duration = asset['DurationInMilliseconds'] / 1000.0
  63                 restricted_to_denmark = asset['RestrictedToDenmark']
  64                 spoken_subtitles = asset['Target'] == 'SpokenSubtitles'
  65                 for link in asset['Links']:
  66                     uri = link['Uri']
  67                     target = link['Target']
  68                     format_id = target
  69                     preference = None
  70                     if spoken_subtitles:
  71                         preference = -1
  72                         format_id += '-spoken-subtitles'
  73                     if target == 'HDS':
  74                         formats.extend(self._extract_f4m_formats(
  75                             uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43',
  76                             video_id, preference, f4m_id=format_id))
  77                     elif target == 'HLS':
  78                         formats.extend(self._extract_m3u8_formats(
  79                             uri, video_id, 'mp4', preference=preference,
  80                             m3u8_id=format_id))
  81                     else:
  82                         bitrate = link.get('Bitrate')
  83                         if bitrate:
  84                             format_id += '-%s' % bitrate
  85                         formats.append({
  86                             'url': uri,
  87                             'format_id': format_id,
  88                             'tbr': bitrate,
  89                             'ext': link.get('FileFormat'),
  90                         })
  91                 subtitles_list = asset.get('SubtitlesList')
  92                 if isinstance(subtitles_list, list):
  93                     LANGS = {
  94                         'Danish': 'dk',
  95                     }
  96                     for subs in subtitles_list:
  97                         lang = subs['Language']
  98                         subtitles[LANGS.get(lang, lang)] = [{'url': subs['Uri'], 'ext': 'vtt'}]
  99
 100         if not formats and restricted_to_denmark:
 101             raise ExtractorError(
 102                 'Unfortunately, DR is not allowed to show this program outside Denmark.', expected=True)
 103
 104         self._sort_formats(formats)
 105
 106         return {
 107             'id': video_id,
 108             'title': title,
 109             'description': description,
 110             'thumbnail': thumbnail,
 111             'timestamp': timestamp,
 112             'duration': duration,
 113             'formats': formats,
 114             'subtitles': subtitles,
 115         }