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
|
from .common import InfoExtractor
from ..utils import (
int_or_none,
unified_strdate,
url_or_none,
)
from ..compat import compat_urlparse
class DWIE(InfoExtractor):
IE_NAME = 'dw'
_VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+(?:av|e)-(?P<id>\d+)'
_TESTS = [{
# video
'url': 'http://www.dw.com/en/intelligent-light/av-19112290',
'md5': 'fb9dfd9520811d3ece80f04befd73428',
'info_dict': {
'id': '19112290',
'ext': 'mp4',
'title': 'Intelligent light',
'description': 'md5:90e00d5881719f2a6a5827cb74985af1',
'upload_date': '20160605',
}
}, {
# audio
'url': 'http://www.dw.com/en/worldlink-my-business/av-19111941',
'md5': '2814c9a1321c3a51f8a7aeb067a360dd',
'info_dict': {
'id': '19111941',
'ext': 'mp3',
'title': 'WorldLink: My business',
'description': 'md5:bc9ca6e4e063361e21c920c53af12405',
'upload_date': '20160311',
}
}, {
# DW documentaries, only last for one or two weeks
'url': 'http://www.dw.com/en/documentaries-welcome-to-the-90s-2016-05-21/e-19220158-9798',
'md5': '56b6214ef463bfb9a3b71aeb886f3cf1',
'info_dict': {
'id': '19274438',
'ext': 'mp4',
'title': 'Welcome to the 90s – Hip Hop',
'description': 'Welcome to the 90s - The Golden Decade of Hip Hop',
'upload_date': '20160521',
},
'skip': 'Video removed',
}]
def _real_extract(self, url):
media_id = self._match_id(url)
webpage = self._download_webpage(url, media_id)
hidden_inputs = self._hidden_inputs(webpage)
title = hidden_inputs['media_title']
media_id = hidden_inputs.get('media_id') or media_id
direct_url = url_or_none(hidden_inputs.get('file_name'))
if direct_url:
formats = [{'url': hidden_inputs['file_name']}]
else:
formats = self._extract_smil_formats(
'http://www.dw.com/smil/v-%s' % media_id, media_id,
transform_source=lambda s: s.replace(
'rtmp://tv-od.dw.de/flash/',
'http://tv-download.dw.de/dwtv_video/flv/'))
upload_date = hidden_inputs.get('display_date')
if not upload_date:
upload_date = self._html_search_regex(
r'<span[^>]+class="date">([0-9.]+)\s*\|', webpage,
'upload date', default=None)
upload_date = unified_strdate(upload_date)
return {
'id': media_id,
'title': title,
'description': self._og_search_description(webpage),
'thumbnail': hidden_inputs.get('preview_image'),
'duration': int_or_none(hidden_inputs.get('file_duration')),
'upload_date': upload_date,
'formats': formats,
}
class DWArticleIE(InfoExtractor):
IE_NAME = 'dw:article'
_VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+a-(?P<id>\d+)'
_TEST = {
'url': 'http://www.dw.com/en/no-hope-limited-options-for-refugees-in-idomeni/a-19111009',
'md5': '8ca657f9d068bbef74d6fc38b97fc869',
'info_dict': {
'id': '19105868',
'ext': 'mp4',
'title': 'The harsh life of refugees in Idomeni',
'description': 'md5:196015cc7e48ebf474db9399420043c7',
'upload_date': '20160310',
}
}
def _real_extract(self, url):
article_id = self._match_id(url)
webpage = self._download_webpage(url, article_id)
hidden_inputs = self._hidden_inputs(webpage)
media_id = hidden_inputs['media_id']
media_path = self._search_regex(r'href="([^"]+av-%s)"\s+class="overlayLink"' % media_id, webpage, 'media url')
media_url = compat_urlparse.urljoin(url, media_path)
return self.url_result(media_url, 'DW', media_id)
|
