]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vrt.py
bec7ab327008803f8609ea0e78e7d70577556940
   2 from __future__ 
import unicode_literals
 
   6 from .common 
import InfoExtractor
 
  13 class VRTIE(InfoExtractor
): 
  14     _VALID_URL 
= r
'https?://(?:deredactie|sporza|cobra(?:\.canvas)?)\.be/cm/(?:[^/]+/)+(?P<id>[^/]+)/*' 
  18             'url': 'http://deredactie.be/cm/vrtnieuws/videozone/programmas/journaal/EP_141025_JOL', 
  19             'md5': '4cebde1eb60a53782d4f3992cbd46ec8', 
  23                 'title': 'Het journaal L - 25/10/14', 
  25                 'timestamp': 1414271750.949, 
  26                 'upload_date': '20141025', 
  29             'skip': 'HTTP Error 404: Not Found', 
  33             'url': 'http://sporza.be/cm/sporza/videozone/programmas/extratime/EP_141020_Extra_time', 
  34             'md5': '11f53088da9bf8e7cfc42456697953ff', 
  38                 'title': 'Bekijk Extra Time van 20 oktober', 
  39                 'description': 'md5:83ac5415a4f1816c6a93f8138aef2426', 
  40                 'timestamp': 1413835980.560, 
  41                 'upload_date': '20141020', 
  44             'skip': 'HTTP Error 404: Not Found', 
  48             'url': 'http://cobra.be/cm/cobra/videozone/rubriek/film-videozone/141022-mv-ellis-cafecorsari', 
  49             'md5': '78a2b060a5083c4f055449a72477409d', 
  53                 'title': 'Bret Easton Ellis in Café Corsari', 
  54                 'description': 'md5:f699986e823f32fd6036c1855a724ee9', 
  55                 'timestamp': 1413967500.494, 
  56                 'upload_date': '20141022', 
  59             'skip': 'HTTP Error 404: Not Found', 
  63             'url': 'http://deredactie.be/cm/vrtnieuws/videozone/nieuws/cultuurenmedia/1.2622957', 
  64             'md5': 'b8b93da1df1cea6c8556255a796b7d61', 
  68                 'title': 'ROGUE ONE: A STAR WARS STORY Official Teaser Trailer', 
  69                 'description': 'md5:8e468944dce15567a786a67f74262583', 
  70                 'uploader': 'Star Wars', 
  71                 'uploader_id': 'starwars', 
  72                 'upload_date': '20160407', 
  74             'add_ie': ['Youtube'], 
  77             'url': 'http://cobra.canvas.be/cm/cobra/videozone/rubriek/film-videozone/1.2377055', 
  82                 'title': 'Cafe Derby', 
  83                 'description': 'Lenny Van Wesemael debuteert met de langspeelfilm Café Derby. Een waar gebeurd maar ook verzonnen verhaal.', 
  84                 'upload_date': '20150626', 
  85                 'timestamp': 1435305240.769, 
  89                 'skip_download': True, 
  94     def _real_extract(self
, url
): 
  95         video_id 
= self
._match
_id
(url
) 
  97         webpage 
= self
._download
_webpage
(url
, video_id
) 
  99         video_id 
= self
._search
_regex
( 
 100             r
'data-video-id="([^"]+)_[^"]+"', webpage
, 'video id', fatal
=False) 
 102         src 
= self
._search
_regex
( 
 103             r
'data-video-src="([^"]+)"', webpage
, 'video src', default
=None) 
 105         video_type 
= self
._search
_regex
( 
 106             r
'data-video-type="([^"]+)"', webpage
, 'video type', default
=None) 
 108         if video_type 
== 'YouTubeVideo': 
 109             return self
.url_result(src
, 'Youtube') 
 114             r
'data-video-iphone-server="(?P<server>[^"]+)"\s+data-video-iphone-path="(?P<path>[^"]+)"', 
 117             formats
.extend(self
._extract
_m
3u8_formats
( 
 118                 '%s/%s' % (mobj
.group('server'), mobj
.group('path')), 
 119                 video_id
, 'mp4', m3u8_id
='hls', fatal
=False)) 
 122             if determine_ext(src
) == 'm3u8': 
 123                 formats
.extend(self
._extract
_m
3u8_formats
( 
 124                     src
, video_id
, 'mp4', entry_protocol
='m3u8_native', 
 125                     m3u8_id
='hls', fatal
=False)) 
 126                 formats
.extend(self
._extract
_f
4m
_formats
( 
 127                     src
.replace('playlist.m3u8', 'manifest.f4m'), 
 128                     video_id
, f4m_id
='hds', fatal
=False)) 
 129                 if 'data-video-geoblocking="true"' not in webpage
: 
 130                     rtmp_formats 
= self
._extract
_smil
_formats
( 
 131                         src
.replace('playlist.m3u8', 'jwplayer.smil'), 
 132                         video_id
, fatal
=False) 
 133                     formats
.extend(rtmp_formats
) 
 134                     for rtmp_format 
in rtmp_formats
: 
 135                         rtmp_format_c 
= rtmp_format
.copy() 
 136                         rtmp_format_c
['url'] = '%s/%s' % (rtmp_format
['url'], rtmp_format
['play_path']) 
 137                         del rtmp_format_c
['play_path'] 
 138                         del rtmp_format_c
['ext'] 
 139                         http_format 
= rtmp_format_c
.copy() 
 141                             'url': rtmp_format_c
['url'].replace('rtmp://', 'http://').replace('vod.', 'download.').replace('/_definst_/', '/').replace('mp4:', ''), 
 142                             'format_id': rtmp_format
['format_id'].replace('rtmp', 'http'), 
 145                         rtsp_format 
= rtmp_format_c
.copy() 
 147                             'url': rtsp_format
['url'].replace('rtmp://', 'rtsp://'), 
 148                             'format_id': rtmp_format
['format_id'].replace('rtmp', 'rtsp'), 
 151                         formats
.extend([http_format
, rtsp_format
]) 
 153                 formats
.extend(self
._extract
_f
4m
_formats
( 
 154                     '%s/manifest.f4m' % src
, video_id
, f4m_id
='hds', fatal
=False)) 
 156         if not formats 
and 'data-video-geoblocking="true"' in webpage
: 
 157             self
.raise_geo_restricted('This video is only available in Belgium') 
 159         self
._sort
_formats
(formats
) 
 161         title 
= self
._og
_search
_title
(webpage
) 
 162         description 
= self
._og
_search
_description
(webpage
, default
=None) 
 163         thumbnail 
= self
._og
_search
_thumbnail
(webpage
) 
 164         timestamp 
= float_or_none(self
._search
_regex
( 
 165             r
'data-video-sitestat-pubdate="(\d+)"', webpage
, 'timestamp', fatal
=False), 1000) 
 166         duration 
= float_or_none(self
._search
_regex
( 
 167             r
'data-video-duration="(\d+)"', webpage
, 'duration', fatal
=False), 1000) 
 172             'description': description
, 
 173             'thumbnail': thumbnail
, 
 174             'timestamp': timestamp
, 
 175             'duration': duration
,