]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/izlesene.py
Prepare for upload.
[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 get_element_by_id,
9 parse_iso8601,
10 determine_ext,
11 int_or_none,
12 float_or_none,
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': 1404298698,
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': 1163318593,
50 'upload_date': '20061112',
51 'duration': 253.666,
52 'age_limit': 0,
53 }
54 },
55 ]
56
57 def _real_extract(self, url):
58 mobj = re.match(self._VALID_URL, url)
59 video_id = mobj.group('id')
60 url = 'http://www.izlesene.com/video/%s' % video_id
61
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, default='')
72 timestamp = parse_iso8601(self._html_search_meta(
73 'uploadDate', webpage, 'upload date', fatal=False))
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 family_friendly = self._html_search_meta(
85 'isFamilyFriendly', webpage, 'age limit', fatal=False)
86
87 content_url = self._html_search_meta(
88 'contentURL', webpage, 'content URL', fatal=False)
89 ext = determine_ext(content_url, 'mp4')
90
91 # Might be empty for some videos.
92 streams = self._html_search_regex(
93 r'"qualitylevel"\s*:\s*"([^"]+)"',
94 webpage, 'streams', fatal=False, default='')
95
96 formats = []
97 if streams:
98 for stream in streams.split('|'):
99 quality, url = re.search(r'\[(\w+)\](.+)', stream).groups()
100 formats.append({
101 'format_id': '%sp' % quality if quality else 'sd',
102 'url': url,
103 'ext': ext,
104 })
105 else:
106 stream_url = self._search_regex(
107 r'"streamurl"\s?:\s?"([^"]+)"', webpage, 'stream URL')
108 formats.append({
109 'format_id': 'sd',
110 'url': stream_url,
111 'ext': ext,
112 })
113
114 return {
115 'id': video_id,
116 'title': title,
117 'description': description,
118 'thumbnail': thumbnail,
119 'uploader_id': uploader,
120 'timestamp': timestamp,
121 'duration': duration,
122 'view_count': int_or_none(view_count),
123 'comment_count': int_or_none(comment_count),
124 'age_limit': 18 if family_friendly == 'False' else 0,
125 'formats': formats,
126 }