1
mirror of https://github.com/yt-dlp/yt-dlp synced 2024-12-20 18:15:54 +01:00

[arte] Add support for embedded videos (Fixes #2620)

This commit is contained in:
Philipp Hagemeister 2014-03-24 22:01:47 +01:00
parent 878d11ec29
commit 893f8832b5
3 changed files with 45 additions and 3 deletions

View File

@ -14,6 +14,7 @@ from .arte import (
ArteTVConcertIE, ArteTVConcertIE,
ArteTVFutureIE, ArteTVFutureIE,
ArteTVDDCIE, ArteTVDDCIE,
ArteTVEmbedIE,
) )
from .auengine import AUEngineIE from .auengine import AUEngineIE
from .bambuser import BambuserIE, BambuserChannelIE from .bambuser import BambuserIE, BambuserChannelIE

View File

@ -75,9 +75,7 @@ class ArteTVPlus7IE(InfoExtractor):
return self._extract_from_json_url(json_url, video_id, lang) return self._extract_from_json_url(json_url, video_id, lang)
def _extract_from_json_url(self, json_url, video_id, lang): def _extract_from_json_url(self, json_url, video_id, lang):
json_info = self._download_webpage(json_url, video_id, 'Downloading info json') info = self._download_json(json_url, video_id)
self.report_extraction(video_id)
info = json.loads(json_info)
player_info = info['videoJsonPlayer'] player_info = info['videoJsonPlayer']
info_dict = { info_dict = {
@ -99,6 +97,8 @@ class ArteTVPlus7IE(InfoExtractor):
l = 'F' l = 'F'
elif lang == 'de': elif lang == 'de':
l = 'A' l = 'A'
else:
l = lang
regexes = [r'VO?%s' % l, r'VO?.-ST%s' % l] regexes = [r'VO?%s' % l, r'VO?.-ST%s' % l]
return any(re.match(r, f['versionCode']) for r in regexes) return any(re.match(r, f['versionCode']) for r in regexes)
# Some formats may not be in the same language as the url # Some formats may not be in the same language as the url
@ -228,3 +228,22 @@ class ArteTVConcertIE(ArteTVPlus7IE):
'description': 'md5:486eb08f991552ade77439fe6d82c305', 'description': 'md5:486eb08f991552ade77439fe6d82c305',
}, },
} }
class ArteTVEmbedIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:embed'
_VALID_URL = r'''(?x)
http://www\.arte\.tv
/playerv2/embed\.php\?json_url=
(?P<json_url>
http://arte\.tv/papi/tvguide/videos/stream/player/
(?P<lang>[^/]+)/(?P<id>[^/]+)[^&]*
)
'''
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
lang = mobj.group('lang')
json_url = mobj.group('json_url')
return self._extract_from_json_url(json_url, video_id, lang)

View File

@ -197,6 +197,21 @@ class GenericIE(InfoExtractor):
'description': 'No description', 'description': 'No description',
}, },
}, },
# arte embed
{
'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
'md5': '7653032cbb25bf6c80d80f217055fa43',
'info_dict': {
'id': '048195-004_PLUS7-F',
'ext': 'flv',
'title': 'X:enius',
'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
'upload_date': '20140320',
},
'params': {
'skip_download': 'Requires rtmpdump'
}
},
] ]
def report_download_webpage(self, video_id): def report_download_webpage(self, video_id):
@ -525,6 +540,13 @@ class GenericIE(InfoExtractor):
if mobj is not None: if mobj is not None:
return self.url_result(mobj.group('url'), 'TED') return self.url_result(mobj.group('url'), 'TED')
# Look for embedded arte.tv player
mobj = re.search(
r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'ArteTVEmbed')
# Start with something easy: JW Player in SWFObject # Start with something easy: JW Player in SWFObject
mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
if mobj is None: if mobj is None: