]> git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/izlesene.py
Merge remote-tracking branch 'yan12125/download-dash-segments' (#5886)
[youtube-dl] / youtube_dl / extractor / izlesene.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..compat import compat_urllib_parse_unquote
8 from ..utils import (
9     determine_ext,
10     float_or_none,
11     get_element_by_id,
12     int_or_none,
13     parse_iso8601,
14     str_to_int,
15 )
16
17
18 class IzleseneIE(InfoExtractor):
19     _VALID_URL = r'''(?x)
20         https?://(?:(?:www|m)\.)?izlesene\.com/
21         (?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+)
22         '''
23     _TESTS = [
24         {
25             'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694',
26             'md5': '4384f9f0ea65086734b881085ee05ac2',
27             'info_dict': {
28                 'id': '7599694',
29                 'ext': 'mp4',
30                 'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi',
31                 'description': 'md5:253753e2655dde93f59f74b572454f6d',
32                 'thumbnail': 're:^http://.*\.jpg',
33                 'uploader_id': 'pelikzzle',
34                 'timestamp': int,
35                 'upload_date': '20140702',
36                 'duration': 95.395,
37                 'age_limit': 0,
38             }
39         },
40         {
41             'url': 'http://www.izlesene.com/video/tarkan-dortmund-2006-konseri/17997',
42             'md5': '97f09b6872bffa284cb7fa4f6910cb72',
43             'info_dict': {
44                 'id': '17997',
45                 'ext': 'mp4',
46                 'title': 'Tarkan Dortmund 2006 Konseri',
47                 'description': 'Tarkan Dortmund 2006 Konseri',
48                 'thumbnail': 're:^http://.*\.jpg',
49                 'uploader_id': 'parlayankiz',
50                 'timestamp': int,
51                 'upload_date': '20061112',
52                 'duration': 253.666,
53                 'age_limit': 0,
54             }
55         },
56     ]
57
58     def _real_extract(self, url):
59         video_id = self._match_id(url)
60
61         url = 'http://www.izlesene.com/video/%s' % video_id
62         webpage = self._download_webpage(url, video_id)
63
64         title = self._og_search_title(webpage)
65         description = self._og_search_description(webpage)
66         thumbnail = self._proto_relative_url(
67             self._og_search_thumbnail(webpage), scheme='http:')
68
69         uploader = self._html_search_regex(
70             r"adduserUsername\s*=\s*'([^']+)';",
71             webpage, 'uploader', fatal=False)
72         timestamp = parse_iso8601(self._html_search_meta(
73             'uploadDate', webpage, 'upload date'))
74
75         duration = float_or_none(self._html_search_regex(
76             r'"videoduration"\s*:\s*"([^"]+)"',
77             webpage, 'duration', fatal=False), scale=1000)
78
79         view_count = str_to_int(get_element_by_id('videoViewCount', webpage))
80         comment_count = self._html_search_regex(
81             r'comment_count\s*=\s*\'([^\']+)\';',
82             webpage, 'comment_count', fatal=False)
83
84         content_url = self._html_search_meta(
85             'contentURL', webpage, 'content URL', fatal=False)
86         ext = determine_ext(content_url, 'mp4')
87
88         # Might be empty for some videos.
89         streams = self._html_search_regex(
90             r'"qualitylevel"\s*:\s*"([^"]+)"', webpage, 'streams', default='')
91
92         formats = []
93         if streams:
94             for stream in streams.split('|'):
95                 quality, url = re.search(r'\[(\w+)\](.+)', stream).groups()
96                 formats.append({
97                     'format_id': '%sp' % quality if quality else 'sd',
98                     'url': compat_urllib_parse_unquote(url),
99                     'ext': ext,
100                 })
101         else:
102             stream_url = self._search_regex(
103                 r'"streamurl"\s*:\s*"([^"]+)"', webpage, 'stream URL')
104             formats.append({
105                 'format_id': 'sd',
106                 'url': compat_urllib_parse_unquote(stream_url),
107                 'ext': ext,
108             })
109
110         return {
111             'id': video_id,
112             'title': title,
113             'description': description,
114             'thumbnail': thumbnail,
115             'uploader_id': uploader,
116             'timestamp': timestamp,
117             'duration': duration,
118             'view_count': int_or_none(view_count),
119             'comment_count': int_or_none(comment_count),
120             'age_limit': self._family_friendly_search(webpage),
121             'formats': formats,
122         }