]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/clipfish.py
debian/control: Update list of extractors.
[youtubedl] / youtube_dl / extractor / clipfish.py
1 import re
2 import time
3 import xml.etree.ElementTree
4
5 from .common import InfoExtractor
6 from ..utils import ExtractorError
7
8
9 class ClipfishIE(InfoExtractor):
10 IE_NAME = u'clipfish'
11
12 _VALID_URL = r'^https?://(?:www\.)?clipfish\.de/.*?/video/(?P<id>[0-9]+)/'
13 _TEST = {
14 u'url': u'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/',
15 u'file': u'3966754.mp4',
16 u'md5': u'2521cd644e862936cf2e698206e47385',
17 u'info_dict': {
18 u'title': u'FIFA 14 - E3 2013 Trailer',
19 u'duration': 82,
20 },
21 u'skip': 'Blocked in the US'
22 }
23
24 def _real_extract(self, url):
25 mobj = re.match(self._VALID_URL, url)
26 video_id = mobj.group(1)
27
28 info_url = ('http://www.clipfish.de/devxml/videoinfo/%s?ts=%d' %
29 (video_id, int(time.time())))
30 doc = self._download_xml(
31 info_url, video_id, note=u'Downloading info page')
32 title = doc.find('title').text
33 video_url = doc.find('filename').text
34 if video_url is None:
35 xml_bytes = xml.etree.ElementTree.tostring(doc)
36 raise ExtractorError(u'Cannot find video URL in document %r' %
37 xml_bytes)
38 thumbnail = doc.find('imageurl').text
39 duration_str = doc.find('duration').text
40 m = re.match(
41 r'^(?P<hours>[0-9]+):(?P<minutes>[0-9]{2}):(?P<seconds>[0-9]{2}):(?P<ms>[0-9]*)$',
42 duration_str)
43 if m:
44 duration = (
45 (int(m.group('hours')) * 60 * 60) +
46 (int(m.group('minutes')) * 60) +
47 (int(m.group('seconds')))
48 )
49 else:
50 duration = None
51
52 return {
53 'id': video_id,
54 'title': title,
55 'url': video_url,
56 'thumbnail': thumbnail,
57 'duration': duration,
58 }