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