]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/br.py
Prepare for release.
[youtubedl] / youtube_dl / extractor / br.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from ..utils import (
6 ExtractorError,
7 int_or_none,
8 parse_duration,
9 )
10
11
12 class BRIE(InfoExtractor):
13 IE_DESC = 'Bayerischer Rundfunk Mediathek'
14 _VALID_URL = r'https?://(?:www\.)?br\.de/(?:[a-z0-9\-_]+/)+(?P<id>[a-z0-9\-_]+)\.html'
15 _BASE_URL = 'http://www.br.de'
16
17 _TESTS = [
18 {
19 'url': 'http://www.br.de/mediathek/video/sendungen/heimatsound/heimatsound-festival-2014-trailer-100.html',
20 'md5': '93556dd2bcb2948d9259f8670c516d59',
21 'info_dict': {
22 'id': '25e279aa-1ffd-40fd-9955-5325bd48a53a',
23 'ext': 'mp4',
24 'title': 'Wenn das Traditions-Theater wackelt',
25 'description': 'Heimatsound-Festival 2014: Wenn das Traditions-Theater wackelt',
26 'duration': 34,
27 'uploader': 'BR',
28 'upload_date': '20140802',
29 }
30 },
31 {
32 'url': 'http://www.br.de/nachrichten/schaeuble-haushaltsentwurf-bundestag-100.html',
33 'md5': '3db0df1a9a9cd9fa0c70e6ea8aa8e820',
34 'info_dict': {
35 'id': 'c6aae3de-2cf9-43f2-957f-f17fef9afaab',
36 'ext': 'aac',
37 'title': '"Keine neuen Schulden im nächsten Jahr"',
38 'description': 'Haushaltsentwurf: "Keine neuen Schulden im nächsten Jahr"',
39 'duration': 64,
40 }
41 },
42 {
43 'url': 'http://www.br.de/radio/bayern1/service/team/videos/team-video-erdelt100.html',
44 'md5': 'dbab0aef2e047060ea7a21fc1ce1078a',
45 'info_dict': {
46 'id': '6ba73750-d405-45d3-861d-1ce8c524e059',
47 'ext': 'mp4',
48 'title': 'Umweltbewusster Häuslebauer',
49 'description': 'Uwe Erdelt: Umweltbewusster Häuslebauer',
50 'duration': 116,
51 }
52 },
53 {
54 'url': 'http://www.br.de/fernsehen/br-alpha/sendungen/kant-fuer-anfaenger/kritik-der-reinen-vernunft/kant-kritik-01-metaphysik100.html',
55 'md5': '23bca295f1650d698f94fc570977dae3',
56 'info_dict': {
57 'id': 'd982c9ce-8648-4753-b358-98abb8aec43d',
58 'ext': 'mp4',
59 'title': 'Folge 1 - Metaphysik',
60 'description': 'Kant für Anfänger: Folge 1 - Metaphysik',
61 'duration': 893,
62 'uploader': 'Eva Maria Steimle',
63 'upload_date': '20140117',
64 }
65 },
66 ]
67
68 def _real_extract(self, url):
69 display_id = self._match_id(url)
70 page = self._download_webpage(url, display_id)
71 xml_url = self._search_regex(
72 r"return BRavFramework\.register\(BRavFramework\('avPlayer_(?:[a-f0-9-]{36})'\)\.setup\({dataURL:'(/(?:[a-z0-9\-]+/)+[a-z0-9/~_.-]+)'}\)\);", page, 'XMLURL')
73 xml = self._download_xml(self._BASE_URL + xml_url, None)
74
75 medias = []
76
77 for xml_media in xml.findall('video') + xml.findall('audio'):
78 media = {
79 'id': xml_media.get('externalId'),
80 'title': xml_media.find('title').text,
81 'duration': parse_duration(xml_media.find('duration').text),
82 'formats': self._extract_formats(xml_media.find('assets')),
83 'thumbnails': self._extract_thumbnails(xml_media.find('teaserImage/variants')),
84 'description': ' '.join(xml_media.find('shareTitle').text.splitlines()),
85 'webpage_url': xml_media.find('permalink').text
86 }
87 if xml_media.find('author').text:
88 media['uploader'] = xml_media.find('author').text
89 if xml_media.find('broadcastDate').text:
90 media['upload_date'] = ''.join(reversed(xml_media.find('broadcastDate').text.split('.')))
91 medias.append(media)
92
93 if len(medias) > 1:
94 self._downloader.report_warning(
95 'found multiple medias; please '
96 'report this with the video URL to http://yt-dl.org/bug')
97 if not medias:
98 raise ExtractorError('No media entries found')
99 return medias[0]
100
101 def _extract_formats(self, assets):
102
103 def text_or_none(asset, tag):
104 elem = asset.find(tag)
105 return None if elem is None else elem.text
106
107 formats = [{
108 'url': text_or_none(asset, 'downloadUrl'),
109 'ext': text_or_none(asset, 'mediaType'),
110 'format_id': asset.get('type'),
111 'width': int_or_none(text_or_none(asset, 'frameWidth')),
112 'height': int_or_none(text_or_none(asset, 'frameHeight')),
113 'tbr': int_or_none(text_or_none(asset, 'bitrateVideo')),
114 'abr': int_or_none(text_or_none(asset, 'bitrateAudio')),
115 'vcodec': text_or_none(asset, 'codecVideo'),
116 'acodec': text_or_none(asset, 'codecAudio'),
117 'container': text_or_none(asset, 'mediaType'),
118 'filesize': int_or_none(text_or_none(asset, 'size')),
119 } for asset in assets.findall('asset')
120 if asset.find('downloadUrl') is not None]
121
122 self._sort_formats(formats)
123 return formats
124
125 def _extract_thumbnails(self, variants):
126 thumbnails = [{
127 'url': self._BASE_URL + variant.find('url').text,
128 'width': int_or_none(variant.find('width').text),
129 'height': int_or_none(variant.find('height').text),
130 } for variant in variants.findall('variant')]
131 thumbnails.sort(key=lambda x: x['width'] * x['height'], reverse=True)
132 return thumbnails