]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/drtv.py
f25ab319e66d4d5b151cd9a9d4509807b6a88617
[youtubedl] / youtube_dl / extractor / drtv.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor, ExtractorError
5 from ..utils import parse_iso8601
6
7
8 class DRTVIE(InfoExtractor):
9 _VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
10
11 _TEST = {
12 'url': 'https://www.dr.dk/tv/se/boern/ultra/panisk-paske/panisk-paske-5',
13 'md5': 'dc515a9ab50577fa14cc4e4b0265168f',
14 'info_dict': {
15 'id': 'panisk-paske-5',
16 'ext': 'mp4',
17 'title': 'Panisk Påske (5)',
18 'description': 'md5:ca14173c5ab24cd26b0fcc074dff391c',
19 'timestamp': 1426984612,
20 'upload_date': '20150322',
21 'duration': 1455,
22 },
23 }
24
25 def _real_extract(self, url):
26 video_id = self._match_id(url)
27
28 webpage = self._download_webpage(url, video_id)
29
30 if '>Programmet er ikke længere tilgængeligt' in webpage:
31 raise ExtractorError(
32 'Video %s is not available' % video_id, expected=True)
33
34 video_id = self._search_regex(
35 r'data-(?:material-identifier|episode-slug)="([^"]+)"',
36 webpage, 'video id')
37
38 programcard = self._download_json(
39 'http://www.dr.dk/mu/programcard/expanded/%s' % video_id,
40 video_id, 'Downloading video JSON')
41 data = programcard['Data'][0]
42
43 title = data['Title']
44 description = data['Description']
45 timestamp = parse_iso8601(data['CreatedTime'])
46
47 thumbnail = None
48 duration = None
49
50 restricted_to_denmark = False
51
52 formats = []
53 subtitles = {}
54
55 for asset in data['Assets']:
56 if asset['Kind'] == 'Image':
57 thumbnail = asset['Uri']
58 elif asset['Kind'] == 'VideoResource':
59 duration = asset['DurationInMilliseconds'] / 1000.0
60 restricted_to_denmark = asset['RestrictedToDenmark']
61 spoken_subtitles = asset['Target'] == 'SpokenSubtitles'
62 for link in asset['Links']:
63 target = link['Target']
64 uri = link['Uri']
65 format_id = target
66 preference = -1 if target == 'HDS' else -2
67 if spoken_subtitles:
68 preference -= 2
69 format_id += '-spoken-subtitles'
70 formats.append({
71 'url': uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43' if target == 'HDS' else uri,
72 'format_id': format_id,
73 'ext': link['FileFormat'],
74 'preference': preference,
75 })
76 subtitles_list = asset.get('SubtitlesList')
77 if isinstance(subtitles_list, list):
78 LANGS = {
79 'Danish': 'dk',
80 }
81 for subs in subtitles_list:
82 lang = subs['Language']
83 subtitles[LANGS.get(lang, lang)] = [{'url': subs['Uri'], 'ext': 'vtt'}]
84
85 if not formats and restricted_to_denmark:
86 raise ExtractorError(
87 'Unfortunately, DR is not allowed to show this program outside Denmark.', expected=True)
88
89 self._sort_formats(formats)
90
91 return {
92 'id': video_id,
93 'title': title,
94 'description': description,
95 'thumbnail': thumbnail,
96 'timestamp': timestamp,
97 'duration': duration,
98 'formats': formats,
99 'subtitles': subtitles,
100 }