]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/spiegel.py
2 from __future__
import unicode_literals
6 from . common
import InfoExtractor
7 from . nexx
import NexxEmbedIE
8 from . spiegeltv
import SpiegeltvIE
9 from .. compat
import compat_urlparse
13 get_element_by_attribute
,
17 class SpiegelIE ( InfoExtractor
):
18 _VALID_URL
= r
'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<id>[0-9]+)(?:-embed|-iframe)?(?:\.html)?(?:#.*)?$'
20 'url' : 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html' ,
21 'md5' : '2c2754212136f35fb4b19767d242f66e' ,
25 'title' : 'Vulkanausbruch in Ecuador: Der "Feuerschlund" ist wieder aktiv' ,
26 'description' : 'md5:8029d8310232196eb235d27575a8b9f4' ,
28 'upload_date' : '20130311' ,
31 'url' : 'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html' ,
32 'md5' : 'f2cdf638d7aa47654e251e1aee360af1' ,
36 'title' : 'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers' ,
37 'description' : 'md5:c2322b65e58f385a820c10fa03b2d088' ,
39 'upload_date' : '20131115' ,
42 'url' : 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-embed.html' ,
43 'md5' : 'd8eeca6bfc8f1cd6f490eb1f44695d51' ,
47 'description' : 'SPIEGEL ONLINE-Nutzer durften den deutschen Astronauten Alexander Gerst über sein Leben auf der ISS-Station befragen. Hier kommen seine Antworten auf die besten sechs Fragen.' ,
48 'title' : 'Fragen an Astronaut Alexander Gerst: "Bekommen Sie die Tageszeiten mit?"' ,
49 'upload_date' : '20140904' ,
52 'url' : 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-iframe.html' ,
53 'only_matching' : True ,
56 def _real_extract ( self
, url
):
57 video_id
= self
._ match
_ id
( url
)
58 webpage
, handle
= self
._ download
_ webpage
_ handle
( url
, video_id
)
60 # 302 to spiegel.tv, like http://www.spiegel.de/video/der-film-zum-wochenende-die-wahrheit-ueber-maenner-video-99003272.html
61 if SpiegeltvIE
. suitable ( handle
. geturl ()):
62 return self
. url_result ( handle
. geturl (), 'Spiegeltv' )
64 video_data
= extract_attributes ( self
._ search
_ regex
( r
'(<div[^>]+id="spVideoElements"[^>]+>)' , webpage
, 'video element' , default
= '' ))
66 title
= video_data
. get ( 'data-video-title' ) or get_element_by_attribute ( 'class' , 'module-title' , webpage
)
67 description
= video_data
. get ( 'data-video-teaser' ) or self
._ html
_ search
_ meta
( 'description' , webpage
, 'description' )
69 base_url
= self
._ search
_ regex
(
70 [ r
'server\s*:\s*(["\' ])( ?P
< url
>.+ ?
) \
1 ', r' var\s
+ server\s
*= \s
* "(?P<url>[^" ]+) \" '],
71 webpage, ' server URL
', group=' url
')
73 xml_url = base_url + video_id + ' . xml
'
74 idoc = self._download_xml(xml_url, video_id)
78 if n.tag.startswith(' type ') and n.tag != ' type6
':
79 format_id = n.tag.rpartition(' type ')[2]
80 video_url = base_url + n.find(' ./ filename
').text
82 ' format_id
': format_id,
84 ' width
': int(n.find(' ./ width
').text),
85 ' height
': int(n.find(' ./ height
').text),
86 ' abr
': int(n.find(' ./ audiobitrate
').text),
87 ' vbr
': int(n.find(' ./ videobitrate
').text),
88 ' vcodec
': n.find(' ./ codec
').text,
91 duration = float(idoc[0].findall(' ./ duration
')[0].text)
93 self._check_formats(formats, video_id)
94 self._sort_formats(formats)
99 ' description
': description.strip() if description else None,
100 ' duration
': duration,
101 ' upload_date
': unified_strdate(video_data.get(' data
- video
- date
')),
106 class SpiegelArticleIE(InfoExtractor):
107 _VALID_URL = r' https?
://( ?
: www\
.) ?spiegel\
. de
/( ?
! video
/)[ ^?
#]*?-(?P<id>[0-9]+)\.html'
108 IE_NAME
= 'Spiegel:Article'
109 IE_DESC
= 'Articles on spiegel.de'
111 'url' : 'http://www.spiegel.de/sport/sonst/badminton-wm-die-randsportart-soll-populaerer-werden-a-987092.html' ,
115 'title' : 'Faszination Badminton: Nennt es bloß nicht Federball' ,
116 'description' : 're:^Patrick Kämnitz gehört.{100,}' ,
117 'upload_date' : '20140825' ,
120 'url' : 'http://www.spiegel.de/wissenschaft/weltall/astronaut-alexander-gerst-antwortet-spiegel-online-lesern-a-989876.html' ,
127 'url' : 'http://www.spiegel.de/sptv/spiegeltv/spiegel-tv-ueber-schnellste-katapult-achterbahn-der-welt-taron-a-1137884.html' ,
131 'title' : 'Nervenkitzel Achterbahn' ,
132 'alt_title' : 'Karussellbauer in Deutschland' ,
133 'description' : 'md5:ffe7b1cc59a01f585e0569949aef73cc' ,
134 'release_year' : 2005 ,
135 'creator' : 'SPIEGEL TV' ,
136 'thumbnail' : r
're:^https?://.*\.jpg$' ,
138 'timestamp' : 1394021479 ,
139 'upload_date' : '20140305' ,
142 'format' : 'bestvideo' ,
143 'skip_download' : True ,
147 def _real_extract ( self
, url
):
148 video_id
= self
._ match
_ id
( url
)
149 webpage
= self
._ download
_ webpage
( url
, video_id
)
151 # Single video on top of the page
152 video_link
= self
._ search
_ regex
(
153 r
'<a href="([^"]+)" onclick="return spOpenVideo\(this,' , webpage
,
154 'video page URL' , default
= None )
156 video_url
= compat_urlparse
. urljoin (
157 self
. http_scheme () + '//spiegel.de/' , video_link
)
158 return self
. url_result ( video_url
)
160 # Multiple embedded videos
162 r
'<div class="vid_holder[0-9]+.*?</div>\s*.*?url\s*=\s*"([^"]+)"' ,
165 self
. url_result ( compat_urlparse
. urljoin (
166 self
. http_scheme () + '//spiegel.de/' , embed_path
))
167 for embed_path
in embeds
]
169 return self
. playlist_result ( entries
)
171 return self
. playlist_from_matches (
172 NexxEmbedIE
._ extract
_u rls
( webpage
), ie
= NexxEmbedIE
. ie_key ())