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 # no og:title
26 'url': 'https://streamango.com/embed/foqebrpftarclpob/asdf_asd_2_mp4',
27 'info_dict': {
28 'id': 'foqebrpftarclpob',
29 'ext': 'mp4',
30 'title': 'foqebrpftarclpob',
31 },
32 'params': {
33 'skip_download': True,
34 },
35 }, {
36 'url': 'https://streamango.com/embed/clapasobsptpkdfe/20170315_150006_mp4',
37 'only_matching': True,
38 }]
39
40 def _real_extract(self, url):
41 video_id = self._match_id(url)
42
43 webpage = self._download_webpage(url, video_id)
44
45 title = self._og_search_title(webpage, default=video_id)
46
47 formats = []
48 for format_ in re.findall(r'({[^}]*\bsrc\s*:\s*[^}]*})', webpage):
49 video = self._parse_json(
50 format_, video_id, transform_source=js_to_json, fatal=False)
51 if not video:
52 continue
53 src = video.get('src')
54 if not src:
55 continue
56 ext = determine_ext(src, default_ext=None)
57 if video.get('type') == 'application/dash+xml' or ext == 'mpd':
58 formats.extend(self._extract_mpd_formats(
59 src, video_id, mpd_id='dash', fatal=False))
60 else:
61 formats.append({
62 'url': src,
63 'ext': ext or 'mp4',
64 'width': int_or_none(video.get('width')),
65 'height': int_or_none(video.get('height')),
66 'tbr': int_or_none(video.get('bitrate')),
67 })
68 self._sort_formats(formats)
69
70 return {
71 'id': video_id,
72 'url': url,
73 'title': title,
74 'formats': formats,
75 }
|
