1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
|
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
js_to_json,
url_or_none,
urljoin,
)
VALID_STREAMS = ('dash', )
class MxplayerIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?mxplayer\.in/movie/(?P<slug>[a-z0-9]+(?:-[a-z0-9]+)*)'
_TEST = {
'url': 'https://www.mxplayer.in/movie/watch-knock-knock-hindi-dubbed-movie-online-b9fa28df3bfb8758874735bbd7d2655a?watch=true',
'info_dict': {
'id': 'b9fa28df3bfb8758874735bbd7d2655a',
'ext': 'mp4',
'title': 'Knock Knock Movie | Watch 2015 Knock Knock Full Movie Online- MX Player',
'description': 'md5:b195ba93ff1987309cfa58e2839d2a5b'
},
'params': {
'skip_download': True,
'format': 'bestvideo'
}
}
def _get_best_stream_url(self, stream):
best_stream = list(filter(None, [v for k, v in stream.items()]))
return best_stream.pop(0) if len(best_stream) else None
def _get_stream_urls(self, video_dict):
stream_dict = video_dict.get('stream', {'provider': {}})
stream_provider = stream_dict.get('provider')
if not stream_dict[stream_provider]:
message = 'No stream provider found'
raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
streams = []
for stream_name, v in stream_dict[stream_provider].items():
if stream_name in VALID_STREAMS:
stream_url = self._get_best_stream_url(v)
if stream_url is None:
continue
streams.append((stream_name, stream_url))
return streams
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_slug = mobj.group('slug')
video_id = video_slug.split('-')[-1]
webpage = self._download_webpage(url, video_id)
window_state_json = self._html_search_regex(
r'(?s)<script>window\.state\s*[:=]\s(\{.+\})\n(\w+).*(</script>).*',
webpage, 'WindowState')
source = self._parse_json(js_to_json(window_state_json), video_id)
if not source:
raise ExtractorError('Cannot find source', expected=True)
config_dict = source['config']
video_dict = source['entities'][video_id]
stream_urls = self._get_stream_urls(video_dict)
title = self._og_search_title(webpage, fatal=True, default=video_dict['title'])
formats = []
headers = {'Referer': url}
for stream_name, stream_url in stream_urls:
if stream_name == 'dash':
format_url = url_or_none(urljoin(config_dict['videoCdnBaseUrl'], stream_url))
if not format_url:
continue
formats.extend(self._extract_mpd_formats(
format_url, video_id, mpd_id='dash', headers=headers))
self._sort_formats(formats)
info = {
'id': video_id,
'title': title,
'description': video_dict.get('description'),
'formats': formats
}
if video_dict.get('imageInfo'):
info['thumbnails'] = list(map(lambda i: dict(i, **{
'url': urljoin(config_dict['imageBaseUrl'], i['url'])
}), video_dict['imageInfo']))
if video_dict.get('webUrl'):
last_part = video_dict['webUrl'].split("/")[-1]
info['display_id'] = last_part.replace(video_id, "").rstrip("-")
return info
|
