[youtube] Fix extraction.
[youtube-dl] / youtube_dl / extractor / clipsyndicate.py
1 from __future__ import unicode_literals
2
3 from .common import InfoExtractor
4 from ..utils import (
5     find_xpath_attr,
6     fix_xml_ampersands
7 )
8
9
10 class ClipsyndicateIE(InfoExtractor):
11     _VALID_URL = r'https?://(?:chic|www)\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
12
13     _TESTS = [{
14         'url': 'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe',
15         'md5': '4d7d549451bad625e0ff3d7bd56d776c',
16         'info_dict': {
17             'id': '4629301',
18             'ext': 'mp4',
19             'title': 'Brick Briscoe',
20             'duration': 612,
21             'thumbnail': r're:^https?://.+\.jpg',
22         },
23     }, {
24         'url': 'http://chic.clipsyndicate.com/video/play/5844117/shark_attack',
25         'only_matching': True,
26     }]
27
28     def _real_extract(self, url):
29         video_id = self._match_id(url)
30         js_player = self._download_webpage(
31             'http://eplayer.clipsyndicate.com/embed/player.js?va_id=%s' % video_id,
32             video_id, 'Downlaoding player')
33         # it includes a required token
34         flvars = self._search_regex(r'flvars: "(.*?)"', js_player, 'flvars')
35
36         pdoc = self._download_xml(
37             'http://eplayer.clipsyndicate.com/osmf/playlist?%s' % flvars,
38             video_id, 'Downloading video info',
39             transform_source=fix_xml_ampersands)
40
41         track_doc = pdoc.find('trackList/track')
42
43         def find_param(name):
44             node = find_xpath_attr(track_doc, './/param', 'name', name)
45             if node is not None:
46                 return node.attrib['value']
47
48         return {
49             'id': video_id,
50             'title': find_param('title'),
51             'url': track_doc.find('location').text,
52             'thumbnail': find_param('thumbnail'),
53             'duration': int(find_param('duration')),
54         }