]>
Commit | Line | Data |
---|---|---|
0d933b2a AL |
1 | # coding: utf-8 |
2 | from __future__ import unicode_literals | |
45ead916 | 3 | |
e66ab17a | 4 | import base64 |
1eb867f3 | 5 | import re |
e66ab17a | 6 | import xml.etree.ElementTree |
1eb867f3 | 7 | import zlib |
0d933b2a AL |
8 | |
9 | from .common import InfoExtractor | |
45ead916 | 10 | from ..utils import int_or_none |
0d933b2a | 11 | |
e66ab17a | 12 | |
0d933b2a AL |
13 | class VimpleIE(InfoExtractor): |
14 | IE_DESC = 'Vimple.ru' | |
e66ab17a | 15 | _VALID_URL = r'https?://(player.vimple.ru/iframe|vimple.ru)/(?P<id>[a-f0-9]{10,})' |
0d933b2a AL |
16 | _TESTS = [ |
17 | { | |
a4c3f486 JMF |
18 | 'url': 'http://vimple.ru/c0f6b1687dcd4000a97ebe70068039cf', |
19 | 'md5': '2e750a330ed211d3fd41821c6ad9a279', | |
0d933b2a | 20 | 'info_dict': { |
a4c3f486 | 21 | 'id': 'c0f6b1687dcd4000a97ebe70068039cf', |
e66ab17a | 22 | 'ext': 'mp4', |
a4c3f486 JMF |
23 | 'title': 'Sunset', |
24 | 'duration': 20, | |
25 | 'thumbnail': 're:https?://.*?\.jpg', | |
e66ab17a AL |
26 | }, |
27 | }, | |
0d933b2a | 28 | ] |
e66ab17a | 29 | |
0d933b2a AL |
30 | def _real_extract(self, url): |
31 | mobj = re.match(self._VALID_URL, url) | |
32 | video_id = mobj.group('id') | |
e66ab17a | 33 | |
0d933b2a AL |
34 | iframe_url = 'http://player.vimple.ru/iframe/%s' % video_id |
35 | ||
1eb867f3 PH |
36 | iframe = self._download_webpage( |
37 | iframe_url, video_id, | |
38 | note='Downloading iframe', errnote='unable to fetch iframe') | |
39 | player_url = self._html_search_regex( | |
40 | r'"(http://player.vimple.ru/flash/.+?)"', iframe, 'player url') | |
e66ab17a | 41 | |
1eb867f3 PH |
42 | player = self._request_webpage( |
43 | player_url, video_id, note='Downloading swf player').read() | |
0d933b2a | 44 | |
0d933b2a AL |
45 | player = zlib.decompress(player[8:]) |
46 | ||
cb437dc2 | 47 | xml_pieces = re.findall(b'([a-zA-Z0-9 =+/]{500})', player) |
0d933b2a | 48 | xml_pieces = [piece[1:-1] for piece in xml_pieces] |
e66ab17a | 49 | |
0d933b2a AL |
50 | xml_data = b''.join(xml_pieces) |
51 | xml_data = base64.b64decode(xml_data) | |
e66ab17a | 52 | |
0d933b2a | 53 | xml_data = xml.etree.ElementTree.fromstring(xml_data) |
e66ab17a | 54 | |
0d933b2a AL |
55 | video = xml_data.find('Video') |
56 | quality = video.get('quality') | |
57 | q_tag = video.find(quality.capitalize()) | |
58 | ||
59 | formats = [ | |
60 | { | |
61 | 'url': q_tag.get('url'), | |
62 | 'tbr': int(q_tag.get('bitrate')), | |
63 | 'filesize': int(q_tag.get('filesize')), | |
64 | 'format_id': quality, | |
65 | }, | |
66 | ] | |
67 | ||
68 | return { | |
69 | 'id': video_id, | |
70 | 'title': video.find('Title').text, | |
71 | 'formats': formats, | |
72 | 'thumbnail': video.find('Poster').get('url'), | |
45ead916 | 73 | 'duration': int_or_none(video.get('duration')), |
0d933b2a AL |
74 | 'webpage_url': video.find('Share').get('videoPageUrl'), |
75 | } |