R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[spiegel] use Spiegeltv extractor for embedded content on spiegel.de

Browse Source
This commit is contained in:
runningbits 2017-04-03 23:27:28 +02:00
parent e7a33a4eb3
commit e323cc688e
1 changed files with 15 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
youtube_dl/extractor/spiegel.py
View File

@ -14,7 +14,7 @@ from ..utils import (
class SpiegelIE(InfoExtractor): class SpiegelIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<id>[0-9]+)(?:-embed|-iframe)?(?:\.html)?(?:#.*)?$' _VALID_URL = r'https?://(?:www\.)?spiegel\.de/(?:video|sptv/spiegeltv)/[^/]*-(?P<id>[0-9]+)(?:-embed|-iframe)?(?:\.html)?(?:#.*)?$'
_TESTS = [{ _TESTS = [{
'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html', 'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html',
'md5': '2c2754212136f35fb4b19767d242f66e', 'md5': '2c2754212136f35fb4b19767d242f66e',
@ -47,6 +47,14 @@ class SpiegelIE(InfoExtractor):
'title': 'Fragen an Astronaut Alexander Gerst: "Bekommen Sie die Tageszeiten mit?"', 'title': 'Fragen an Astronaut Alexander Gerst: "Bekommen Sie die Tageszeiten mit?"',
'upload_date': '20140904', 'upload_date': '20140904',
} }
}, {
'url': 'http://www.spiegel.de/sptv/spiegeltv/spiegel-tv-ueber-russische-propaganda-a-1136559.html',
'info_dict': {
'id': 'putins-trollfabriken',
'ext': 'm4v',
'description': 'Propagandakrieg in den sozialen Medien',
'title': 'Putins Trollfabriken',
}
}, { }, {
'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-iframe.html', 'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-iframe.html',
'only_matching': True, 'only_matching': True,
@ -55,10 +63,13 @@ class SpiegelIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage, handle = self._download_webpage_handle(url, video_id) webpage, handle = self._download_webpage_handle(url, video_id)
webpage_url = handle.geturl()
if 'spiegel.de/sptv/' in webpage_url:
webpage_url = self._search_regex(r'<iframe[^>]+src="([^"]+spiegel.tv/[^"]+)"[^>]+></iframe>', webpage, 'embedded iframe')
# 302 to spiegel.tv, like http://www.spiegel.de/video/der-film-zum-wochenende-die-wahrheit-ueber-maenner-video-99003272.html # 302 to spiegel.tv, like http://www.spiegel.de/video/der-film-zum-wochenende-die-wahrheit-ueber-maenner-video-99003272.html
if SpiegeltvIE.suitable(handle.geturl()): if SpiegeltvIE.suitable(webpage_url):
return self.url_result(handle.geturl(), 'Spiegeltv') return self.url_result(webpage_url, 'Spiegeltv')
video_data = extract_attributes(self._search_regex(r'(<div[^>]+id="spVideoElements"[^>]+>)', webpage, 'video element', default='')) video_data = extract_attributes(self._search_regex(r'(<div[^>]+id="spVideoElements"[^>]+>)', webpage, 'video element', default=''))
@ -103,7 +114,7 @@ class SpiegelIE(InfoExtractor):
class SpiegelArticleIE(InfoExtractor): class SpiegelArticleIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spiegel\.de/(?!video/)[^?#]*?-(?P<id>[0-9]+)\.html' _VALID_URL = r'https?://(?:www\.)?spiegel\.de/(?!(?:video|sptv)/)[^?#]*?-(?P<id>[0-9]+)\.html'
IE_NAME = 'Spiegel:Article' IE_NAME = 'Spiegel:Article'
IE_DESC = 'Articles on spiegel.de' IE_DESC = 'Articles on spiegel.de'
_TESTS = [{ _TESTS = [{