]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/tagesschau.py
73e7657d4bec7b1bc37753923744d92b769d8843
[youtubedl] / youtube_dl / extractor / tagesschau.py
1 # -*- coding: utf-8 -*-
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import parse_filesize
8
9
10 class TagesschauIE(InfoExtractor):
11 _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/multimedia/(?:[^/]+/)*?[^/#?]+?(?P<id>-?[0-9]+)(?:~_[^/#?]+?)?\.html'
12
13 _TESTS = [{
14 'url': 'http://www.tagesschau.de/multimedia/video/video-102143.html',
15 'md5': '917a228bc7df7850783bc47979673a09',
16 'info_dict': {
17 'id': '102143',
18 'ext': 'mp4',
19 'title': 'Regierungsumbildung in Athen: Neue Minister in Griechenland vereidigt',
20 'description': 'md5:171feccd9d9b3dd54d05d501568f6359',
21 'thumbnail': 're:^https?:.*\.jpg$',
22 },
23 }, {
24 'url': 'http://www.tagesschau.de/multimedia/sendung/ts-5727.html',
25 'md5': '3c54c1f6243d279b706bde660ceec633',
26 'info_dict': {
27 'id': '5727',
28 'ext': 'mp4',
29 'description': 'md5:695c01bfd98b7e313c501386327aea59',
30 'title': 'Sendung: tagesschau \t04.12.2014 20:00 Uhr',
31 'thumbnail': 're:^https?:.*\.jpg$',
32 },
33 }, {
34 'url': 'http://www.tagesschau.de/multimedia/politikimradio/audio-18407.html',
35 'md5': 'aef45de271c4bf0a5db834aa40bf774c',
36 'info_dict': {
37 'id': '18407',
38 'ext': 'mp3',
39 'title': 'Flüchtlingsdebatte: Hitzig, aber wenig hilfreich',
40 'description': 'Flüchtlingsdebatte: Hitzig, aber wenig hilfreich',
41 'thumbnail': 're:^https?:.*\.jpg$',
42 },
43 }, {
44 'url': 'http://www.tagesschau.de/multimedia/sendung/tsg-3771.html',
45 'only_matching': True,
46 }, {
47 'url': 'http://www.tagesschau.de/multimedia/sendung/tt-3827.html',
48 'only_matching': True,
49 }, {
50 'url': 'http://www.tagesschau.de/multimedia/sendung/nm-3475.html',
51 'only_matching': True,
52 }, {
53 'url': 'http://www.tagesschau.de/multimedia/sendung/weltspiegel-3167.html',
54 'only_matching': True,
55 }, {
56 'url': 'http://www.tagesschau.de/multimedia/tsvorzwanzig-959.html',
57 'only_matching': True,
58 }, {
59 'url': 'http://www.tagesschau.de/multimedia/sendung/bab/bab-3299~_bab-sendung-209.html',
60 'only_matching': True,
61 }, {
62 'url': 'http://www.tagesschau.de/multimedia/video/video-102303~_bab-sendung-211.html',
63 'only_matching': True,
64 }]
65
66 _FORMATS = {
67 's': {'width': 256, 'height': 144, 'quality': 1},
68 'm': {'width': 512, 'height': 288, 'quality': 2},
69 'l': {'width': 960, 'height': 544, 'quality': 3},
70 }
71
72 def _real_extract(self, url):
73 video_id = self._match_id(url)
74 display_id = video_id.lstrip('-')
75 webpage = self._download_webpage(url, display_id)
76
77 player_url = self._html_search_meta(
78 'twitter:player', webpage, 'player URL', default=None)
79 if player_url:
80 playerpage = self._download_webpage(
81 player_url, display_id, 'Downloading player page')
82
83 formats = []
84 for media in re.finditer(
85 r'''(?x)
86 (?P<q_url>["\'])(?P<url>http://media.+?)(?P=q_url)
87 ,\s*type:(?P<q_type>["\'])(?P<type>video|audio)/(?P<ext>.+?)(?P=q_type)
88 (?:,\s*quality:(?P<q_quality>["\'])(?P<quality>.+?)(?P=q_quality))?
89 ''', playerpage):
90 url = media.group('url')
91 type_ = media.group('type')
92 ext = media.group('ext')
93 res = media.group('quality')
94 f = {
95 'format_id': '%s_%s' % (res, ext) if res else ext,
96 'url': url,
97 'ext': ext,
98 'vcodec': 'none' if type_ == 'audio' else None,
99 }
100 f.update(self._FORMATS.get(res, {}))
101 formats.append(f)
102 thumbnail = self._og_search_thumbnail(playerpage)
103 title = self._og_search_title(webpage).strip()
104 description = self._og_search_description(webpage).strip()
105 else:
106 download_text = self._search_regex(
107 r'(?s)<p>Wir bieten dieses Video in folgenden Formaten zum Download an:</p>\s*<div class="controls">(.*?)</div>\s*<p>',
108 webpage, 'download links')
109 links = re.finditer(
110 r'<div class="button" title="(?P<title>[^"]*)"><a href="(?P<url>[^"]+)">(?P<name>.+?)</a></div>',
111 download_text)
112 formats = []
113 for l in links:
114 format_id = self._search_regex(
115 r'.*/[^/.]+\.([^/]+)\.[^/.]+', l.group('url'), 'format ID')
116 format = {
117 'format_id': format_id,
118 'url': l.group('url'),
119 'format_name': l.group('name'),
120 }
121 m = re.match(
122 r'''(?x)
123 Video:\s*(?P<vcodec>[a-zA-Z0-9/._-]+)\s*&\#10;
124 (?P<width>[0-9]+)x(?P<height>[0-9]+)px&\#10;
125 (?P<vbr>[0-9]+)kbps&\#10;
126 Audio:\s*(?P<abr>[0-9]+)kbps,\s*(?P<audio_desc>[A-Za-z\.0-9]+)&\#10;
127 Gr&ouml;&szlig;e:\s*(?P<filesize_approx>[0-9.,]+\s+[a-zA-Z]*B)''',
128 l.group('title'))
129 if m:
130 format.update({
131 'format_note': m.group('audio_desc'),
132 'vcodec': m.group('vcodec'),
133 'width': int(m.group('width')),
134 'height': int(m.group('height')),
135 'abr': int(m.group('abr')),
136 'vbr': int(m.group('vbr')),
137 'filesize_approx': parse_filesize(m.group('filesize_approx')),
138 })
139 formats.append(format)
140 thumbnail = self._og_search_thumbnail(webpage)
141 description = self._html_search_regex(
142 r'(?s)<p class="teasertext">(.*?)</p>',
143 webpage, 'description', default=None)
144 title = self._html_search_regex(
145 r'<span class="headline".*?>(.*?)</span>', webpage, 'title')
146
147 self._sort_formats(formats)
148
149 return {
150 'id': display_id,
151 'title': title,
152 'thumbnail': thumbnail,
153 'formats': formats,
154 'description': description,
155 }