]>
Commit | Line | Data |
---|---|---|
c8868a9d | 1 | from .common import InfoExtractor |
ac88d231 YCH |
2 | from ..utils import ( |
3 | int_or_none, | |
4 | unified_strdate, | |
d98b006b | 5 | url_or_none, |
ac88d231 | 6 | ) |
36bb63e0 | 7 | from ..compat import compat_urlparse |
c8868a9d | 8 | |
9 | ||
10 | class DWIE(InfoExtractor): | |
36bb63e0 | 11 | IE_NAME = 'dw' |
ac88d231 | 12 | _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+(?:av|e)-(?P<id>\d+)' |
91d6aafb | 13 | _TESTS = [{ |
14 | # video | |
c8868a9d | 15 | 'url': 'http://www.dw.com/en/intelligent-light/av-19112290', |
d98b006b | 16 | 'md5': 'fb9dfd9520811d3ece80f04befd73428', |
c8868a9d | 17 | 'info_dict': { |
18 | 'id': '19112290', | |
19 | 'ext': 'mp4', | |
20 | 'title': 'Intelligent light', | |
21 | 'description': 'md5:90e00d5881719f2a6a5827cb74985af1', | |
d98b006b | 22 | 'upload_date': '20160605', |
c8868a9d | 23 | } |
91d6aafb | 24 | }, { |
25 | # audio | |
26 | 'url': 'http://www.dw.com/en/worldlink-my-business/av-19111941', | |
27 | 'md5': '2814c9a1321c3a51f8a7aeb067a360dd', | |
28 | 'info_dict': { | |
29 | 'id': '19111941', | |
30 | 'ext': 'mp3', | |
31 | 'title': 'WorldLink: My business', | |
32 | 'description': 'md5:bc9ca6e4e063361e21c920c53af12405', | |
33 | 'upload_date': '20160311', | |
34 | } | |
ac88d231 | 35 | }, { |
6c0376fe | 36 | # DW documentaries, only last for one or two weeks |
ac88d231 YCH |
37 | 'url': 'http://www.dw.com/en/documentaries-welcome-to-the-90s-2016-05-21/e-19220158-9798', |
38 | 'md5': '56b6214ef463bfb9a3b71aeb886f3cf1', | |
39 | 'info_dict': { | |
40 | 'id': '19274438', | |
41 | 'ext': 'mp4', | |
42 | 'title': 'Welcome to the 90s – Hip Hop', | |
43 | 'description': 'Welcome to the 90s - The Golden Decade of Hip Hop', | |
44 | 'upload_date': '20160521', | |
45 | }, | |
6c0376fe | 46 | 'skip': 'Video removed', |
91d6aafb | 47 | }] |
c8868a9d | 48 | |
49 | def _real_extract(self, url): | |
36bb63e0 | 50 | media_id = self._match_id(url) |
51 | webpage = self._download_webpage(url, media_id) | |
c8868a9d | 52 | hidden_inputs = self._hidden_inputs(webpage) |
53 | title = hidden_inputs['media_title'] | |
ac88d231 | 54 | media_id = hidden_inputs.get('media_id') or media_id |
c8868a9d | 55 | |
d98b006b | 56 | direct_url = url_or_none(hidden_inputs.get('file_name')) |
57 | if direct_url: | |
58 | formats = [{'url': hidden_inputs['file_name']}] | |
59 | else: | |
91d6aafb | 60 | formats = self._extract_smil_formats( |
36bb63e0 | 61 | 'http://www.dw.com/smil/v-%s' % media_id, media_id, |
91d6aafb | 62 | transform_source=lambda s: s.replace( |
63 | 'rtmp://tv-od.dw.de/flash/', | |
64 | 'http://tv-download.dw.de/dwtv_video/flv/')) | |
d98b006b | 65 | self._sort_formats(formats) |
91d6aafb | 66 | |
ac88d231 YCH |
67 | upload_date = hidden_inputs.get('display_date') |
68 | if not upload_date: | |
69 | upload_date = self._html_search_regex( | |
70 | r'<span[^>]+class="date">([0-9.]+)\s*\|', webpage, | |
71 | 'upload date', default=None) | |
72 | upload_date = unified_strdate(upload_date) | |
73 | ||
c8868a9d | 74 | return { |
36bb63e0 | 75 | 'id': media_id, |
c8868a9d | 76 | 'title': title, |
77 | 'description': self._og_search_description(webpage), | |
78 | 'thumbnail': hidden_inputs.get('preview_image'), | |
79 | 'duration': int_or_none(hidden_inputs.get('file_duration')), | |
ac88d231 | 80 | 'upload_date': upload_date, |
c8868a9d | 81 | 'formats': formats, |
82 | } | |
36bb63e0 | 83 | |
84 | ||
85 | class DWArticleIE(InfoExtractor): | |
86 | IE_NAME = 'dw:article' | |
87 | _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+a-(?P<id>\d+)' | |
88 | _TEST = { | |
89 | 'url': 'http://www.dw.com/en/no-hope-limited-options-for-refugees-in-idomeni/a-19111009', | |
90 | 'md5': '8ca657f9d068bbef74d6fc38b97fc869', | |
91 | 'info_dict': { | |
92 | 'id': '19105868', | |
93 | 'ext': 'mp4', | |
94 | 'title': 'The harsh life of refugees in Idomeni', | |
95 | 'description': 'md5:196015cc7e48ebf474db9399420043c7', | |
96 | 'upload_date': '20160310', | |
97 | } | |
98 | } | |
99 | ||
100 | def _real_extract(self, url): | |
101 | article_id = self._match_id(url) | |
102 | webpage = self._download_webpage(url, article_id) | |
103 | hidden_inputs = self._hidden_inputs(webpage) | |
104 | media_id = hidden_inputs['media_id'] | |
105 | media_path = self._search_regex(r'href="([^"]+av-%s)"\s+class="overlayLink"' % media_id, webpage, 'media url') | |
106 | media_url = compat_urlparse.urljoin(url, media_path) | |
107 | return self.url_result(media_url, 'DW', media_id) |