]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/musicplayon.py
Imported Upstream version 2014.12.01
[youtubedl] / youtube_dl / extractor / musicplayon.py
1 # encoding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import int_or_none
8
9
10 class MusicPlayOnIE(InfoExtractor):
11 _VALID_URL = r'https?://(?:.+?\.)?musicplayon\.com/play(?:-touch)?\?(?:v|pl=100&play)=(?P<id>\d+)'
12
13 _TEST = {
14 'url': 'http://en.musicplayon.com/play?v=433377',
15 'info_dict': {
16 'id': '433377',
17 'ext': 'mp4',
18 'title': 'Rick Ross - Interview On Chelsea Lately (2014)',
19 'description': 'Rick Ross Interview On Chelsea Lately',
20 'duration': 342,
21 'uploader': 'ultrafish',
22 },
23 'params': {
24 # m3u8 download
25 'skip_download': True,
26 },
27 }
28
29 def _real_extract(self, url):
30 mobj = re.match(self._VALID_URL, url)
31 video_id = mobj.group('id')
32
33 page = self._download_webpage(url, video_id)
34
35 title = self._og_search_title(page)
36 description = self._og_search_description(page)
37 thumbnail = self._og_search_thumbnail(page)
38 duration = self._html_search_meta('video:duration', page, 'duration', fatal=False)
39 view_count = self._og_search_property('count', page, fatal=False)
40 uploader = self._html_search_regex(
41 r'<div>by&nbsp;<a href="[^"]+" class="purple">([^<]+)</a></div>', page, 'uploader', fatal=False)
42
43 formats = [
44 {
45 'url': 'http://media0-eu-nl.musicplayon.com/stream-mobile?id=%s&type=.mp4' % video_id,
46 'ext': 'mp4',
47 }
48 ]
49
50 manifest = self._download_webpage(
51 'http://en.musicplayon.com/manifest.m3u8?v=%s' % video_id, video_id, 'Downloading manifest')
52
53 for entry in manifest.split('#')[1:]:
54 if entry.startswith('EXT-X-STREAM-INF:'):
55 meta, url, _ = entry.split('\n')
56 params = dict(param.split('=') for param in meta.split(',')[1:])
57 formats.append({
58 'url': url,
59 'ext': 'mp4',
60 'tbr': int(params['BANDWIDTH']),
61 'width': int(params['RESOLUTION'].split('x')[1]),
62 'height': int(params['RESOLUTION'].split('x')[-1]),
63 'format_note': params['NAME'].replace('"', '').strip(),
64 })
65
66 return {
67 'id': video_id,
68 'title': title,
69 'description': description,
70 'thumbnail': thumbnail,
71 'uploader': uploader,
72 'duration': int_or_none(duration),
73 'view_count': int_or_none(view_count),
74 'formats': formats,
75 }