]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/izlesene.py
debian/changelog: Annotate bugs to close.
[youtubedl] / 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 ..utils import (
8 determine_ext,
9 float_or_none,
10 get_element_by_id,
11 int_or_none,
12 parse_iso8601,
13 str_to_int,
14 )
15
16
17 class IzleseneIE(InfoExtractor):
18 _VALID_URL = r'''(?x)
19 https?://(?:(?:www|m)\.)?izlesene\.com/
20 (?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+)
21 '''
22 _TESTS = [
23 {
24 'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694',
25 'md5': '4384f9f0ea65086734b881085ee05ac2',
26 'info_dict': {
27 'id': '7599694',
28 'ext': 'mp4',
29 'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi',
30 'description': 'md5:253753e2655dde93f59f74b572454f6d',
31 'thumbnail': 're:^http://.*\.jpg',
32 'uploader_id': 'pelikzzle',
33 'timestamp': 1404302298,
34 'upload_date': '20140702',
35 'duration': 95.395,
36 'age_limit': 0,
37 }
38 },
39 {
40 'url': 'http://www.izlesene.com/video/tarkan-dortmund-2006-konseri/17997',
41 'md5': '97f09b6872bffa284cb7fa4f6910cb72',
42 'info_dict': {
43 'id': '17997',
44 'ext': 'mp4',
45 'title': 'Tarkan Dortmund 2006 Konseri',
46 'description': 'Tarkan Dortmund 2006 Konseri',
47 'thumbnail': 're:^http://.*\.jpg',
48 'uploader_id': 'parlayankiz',
49 'timestamp': 1163322193,
50 'upload_date': '20061112',
51 'duration': 253.666,
52 'age_limit': 0,
53 }
54 },
55 ]
56
57 def _real_extract(self, url):
58 video_id = self._match_id(url)
59
60 url = 'http://www.izlesene.com/video/%s' % video_id
61 webpage = self._download_webpage(url, video_id)
62
63 title = self._og_search_title(webpage)
64 description = self._og_search_description(webpage)
65 thumbnail = self._proto_relative_url(
66 self._og_search_thumbnail(webpage), scheme='http:')
67
68 uploader = self._html_search_regex(
69 r"adduserUsername\s*=\s*'([^']+)';",
70 webpage, 'uploader', fatal=False, default='')
71 timestamp = parse_iso8601(self._html_search_meta(
72 'uploadDate', webpage, 'upload date', fatal=False))
73
74 duration = float_or_none(self._html_search_regex(
75 r'"videoduration"\s*:\s*"([^"]+)"',
76 webpage, 'duration', fatal=False), scale=1000)
77
78 view_count = str_to_int(get_element_by_id('videoViewCount', webpage))
79 comment_count = self._html_search_regex(
80 r'comment_count\s*=\s*\'([^\']+)\';',
81 webpage, 'comment_count', fatal=False)
82
83 content_url = self._html_search_meta(
84 'contentURL', webpage, 'content URL', fatal=False)
85 ext = determine_ext(content_url, 'mp4')
86
87 # Might be empty for some videos.
88 streams = self._html_search_regex(
89 r'"qualitylevel"\s*:\s*"([^"]+)"',
90 webpage, 'streams', fatal=False, 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': 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': 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 }