]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/streamango.py
New upstream version 2017.05.18.1
[youtubedl] / youtube_dl / extractor / streamango.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import (
8 determine_ext,
9 int_or_none,
10 js_to_json,
11 )
12
13
14 class StreamangoIE(InfoExtractor):
15 _VALID_URL = r'https?://(?:www\.)?streamango\.com/(?:f|embed)/(?P<id>[^/?#&]+)'
16 _TESTS = [{
17 'url': 'https://streamango.com/f/clapasobsptpkdfe/20170315_150006_mp4',
18 'md5': 'e992787515a182f55e38fc97588d802a',
19 'info_dict': {
20 'id': 'clapasobsptpkdfe',
21 'ext': 'mp4',
22 'title': '20170315_150006.mp4',
23 }
24 }, {
25 'url': 'https://streamango.com/embed/clapasobsptpkdfe/20170315_150006_mp4',
26 'only_matching': True,
27 }]
28
29 def _real_extract(self, url):
30 video_id = self._match_id(url)
31
32 webpage = self._download_webpage(url, video_id)
33
34 title = self._og_search_title(webpage)
35
36 formats = []
37 for format_ in re.findall(r'({[^}]*\bsrc\s*:\s*[^}]*})', webpage):
38 video = self._parse_json(
39 format_, video_id, transform_source=js_to_json, fatal=False)
40 if not video:
41 continue
42 src = video.get('src')
43 if not src:
44 continue
45 ext = determine_ext(src, default_ext=None)
46 if video.get('type') == 'application/dash+xml' or ext == 'mpd':
47 formats.extend(self._extract_mpd_formats(
48 src, video_id, mpd_id='dash', fatal=False))
49 else:
50 formats.append({
51 'url': src,
52 'ext': ext or 'mp4',
53 'width': int_or_none(video.get('width')),
54 'height': int_or_none(video.get('height')),
55 'tbr': int_or_none(video.get('bitrate')),
56 })
57 self._sort_formats(formats)
58
59 return {
60 'id': video_id,
61 'url': url,
62 'title': title,
63 'formats': formats,
64 }