]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/indavideo.py
12fb5e8e1dcb1e5dfba8057a1496edcbe0f61f82
[youtubedl] / youtube_dl / extractor / indavideo.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from ..utils import (
6 int_or_none,
7 parse_age_limit,
8 parse_iso8601,
9 )
10
11
12 class IndavideoEmbedIE(InfoExtractor):
13 _VALID_URL = r'https?://(?:(?:embed\.)?indavideo\.hu/player/video/|assets\.indavideo\.hu/swf/player\.swf\?.*\b(?:v(?:ID|id))=)(?P<id>[\da-f]+)'
14 _TESTS = [{
15 'url': 'http://indavideo.hu/player/video/1bdc3c6d80/',
16 'md5': 'f79b009c66194acacd40712a6778acfa',
17 'info_dict': {
18 'id': '1837039',
19 'ext': 'mp4',
20 'title': 'Cicatánc',
21 'description': '',
22 'thumbnail': 're:^https?://.*\.jpg$',
23 'uploader': 'cukiajanlo',
24 'uploader_id': '83729',
25 'timestamp': 1439193826,
26 'upload_date': '20150810',
27 'duration': 72,
28 'age_limit': 0,
29 'tags': ['tánc', 'cica', 'cuki', 'cukiajanlo', 'newsroom'],
30 },
31 }, {
32 'url': 'http://embed.indavideo.hu/player/video/1bdc3c6d80?autostart=1&hide=1',
33 'only_matching': True,
34 }, {
35 'url': 'http://assets.indavideo.hu/swf/player.swf?v=fe25e500&vID=1bdc3c6d80&autostart=1&hide=1&i=1',
36 'only_matching': True,
37 }]
38
39 def _real_extract(self, url):
40 video_id = self._match_id(url)
41
42 video = self._download_json(
43 'http://amfphp.indavideo.hu/SYm0json.php/player.playerHandler.getVideoData/%s' % video_id,
44 video_id)['data']
45
46 title = video['title']
47
48 video_urls = video.get('video_files', [])
49 video_file = video.get('video_file')
50 if video:
51 video_urls.append(video_file)
52 video_urls = list(set(video_urls))
53
54 video_prefix = video_urls[0].rsplit('/', 1)[0]
55
56 for flv_file in video.get('flv_files', []):
57 flv_url = '%s/%s' % (video_prefix, flv_file)
58 if flv_url not in video_urls:
59 video_urls.append(flv_url)
60
61 formats = [{
62 'url': video_url,
63 'height': self._search_regex(r'\.(\d{3,4})\.mp4$', video_url, 'height', default=None),
64 } for video_url in video_urls]
65 self._sort_formats(formats)
66
67 timestamp = video.get('date')
68 if timestamp:
69 # upload date is in CEST
70 timestamp = parse_iso8601(timestamp + ' +0200', ' ')
71
72 thumbnails = [{
73 'url': self._proto_relative_url(thumbnail)
74 } for thumbnail in video.get('thumbnails', [])]
75
76 tags = [tag['title'] for tag in video.get('tags', [])]
77
78 return {
79 'id': video.get('id') or video_id,
80 'title': title,
81 'description': video.get('description'),
82 'thumbnails': thumbnails,
83 'uploader': video.get('user_name'),
84 'uploader_id': video.get('user_id'),
85 'timestamp': timestamp,
86 'duration': int_or_none(video.get('length')),
87 'age_limit': parse_age_limit(video.get('age_limit')),
88 'tags': tags,
89 'formats': formats,
90 }
91
92
93 class IndavideoIE(InfoExtractor):
94 _VALID_URL = r'https?://(?:.+?\.)?indavideo\.hu/video/(?P<id>[^/#?]+)'
95 _TESTS = [{
96 'url': 'http://indavideo.hu/video/Vicces_cica_1',
97 'md5': '8c82244ba85d2a2310275b318eb51eac',
98 'info_dict': {
99 'id': '1335611',
100 'display_id': 'Vicces_cica_1',
101 'ext': 'mp4',
102 'title': 'Vicces cica',
103 'description': 'Játszik a tablettel. :D',
104 'thumbnail': 're:^https?://.*\.jpg$',
105 'uploader': 'Jet_Pack',
106 'uploader_id': '491217',
107 'timestamp': 1390821212,
108 'upload_date': '20140127',
109 'duration': 7,
110 'age_limit': 0,
111 'tags': ['vicces', 'macska', 'cica', 'ügyes', 'nevetés', 'játszik', 'Cukiság', 'Jet_Pack'],
112 },
113 }, {
114 'url': 'http://index.indavideo.hu/video/2015_0728_beregszasz',
115 'only_matching': True,
116 }, {
117 'url': 'http://auto.indavideo.hu/video/Sajat_utanfutoban_a_kis_tacsko',
118 'only_matching': True,
119 }, {
120 'url': 'http://erotika.indavideo.hu/video/Amator_tini_punci',
121 'only_matching': True,
122 }, {
123 'url': 'http://film.indavideo.hu/video/f_hrom_nagymamm_volt',
124 'only_matching': True,
125 }, {
126 'url': 'http://palyazat.indavideo.hu/video/Embertelen_dal_Dodgem_egyuttes',
127 'only_matching': True,
128 }]
129
130 def _real_extract(self, url):
131 display_id = self._match_id(url)
132
133 webpage = self._download_webpage(url, display_id)
134 embed_url = self._search_regex(
135 r'<link[^>]+rel="video_src"[^>]+href="(.+?)"', webpage, 'embed url')
136
137 return {
138 '_type': 'url_transparent',
139 'ie_key': 'IndavideoEmbed',
140 'url': embed_url,
141 'display_id': display_id,
142 }