github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[arte] add support for downloading from http://liveweb.arte.tv (fixes #1014)

Browse source
This commit is contained in:
Jaime Marquínez Ferrándiz 2013-08-03 19:07:04 +02:00
parent f5791ed136
commit 70c4c03cb8
1 changed files with 27 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

28
youtube_dl/extractor/arte.py
View file

@ -17,13 +17,14 @@ class ArteTvIE(InfoExtractor):
""" """
_EMISSION_URL = r'(?:http://)?www\.arte.tv/guide/(?P<lang>fr|de)/(?:(?:sendungen|emissions)/)?(?P<id>.*?)/(?P<name>.*?)(\?.*)?' _EMISSION_URL = r'(?:http://)?www\.arte.tv/guide/(?P<lang>fr|de)/(?:(?:sendungen|emissions)/)?(?P<id>.*?)/(?P<name>.*?)(\?.*)?'
_VIDEOS_URL = r'(?:http://)?videos.arte.tv/(?P<lang>fr|de)/.*-(?P<id>.*?).html' _VIDEOS_URL = r'(?:http://)?videos.arte.tv/(?P<lang>fr|de)/.*-(?P<id>.*?).html'
_LIVEWEB_URL = r'(?:http://)?liveweb.arte.tv/(?P<lang>fr|de)/(?P<subpage>.+?)/(?P<name>.+)'
_LIVE_URL = r'index-[0-9]+\.html$' _LIVE_URL = r'index-[0-9]+\.html$'
IE_NAME = u'arte.tv' IE_NAME = u'arte.tv'
@classmethod @classmethod
def suitable(cls, url): def suitable(cls, url):
return any(re.match(regex, url) for regex in (cls._EMISSION_URL, cls._VIDEOS_URL)) return any(re.match(regex, url) for regex in (cls._EMISSION_URL, cls._VIDEOS_URL, cls._LIVEWEB_URL))
# TODO implement Live Stream # TODO implement Live Stream
# from ..utils import compat_urllib_parse # from ..utils import compat_urllib_parse
@ -68,6 +69,12 @@ def _real_extract(self, url):
lang = mobj.group('lang') lang = mobj.group('lang')
return self._extract_video(url, id, lang) return self._extract_video(url, id, lang)
mobj = re.match(self._LIVEWEB_URL, url)
if mobj is not None:
name = mobj.group('name')
lang = mobj.group('lang')
return self._extract_liveweb(url, name, lang)
if re.search(self._LIVE_URL, video_id) is not None: if re.search(self._LIVE_URL, video_id) is not None:
raise ExtractorError(u'Arte live streams are not yet supported, sorry') raise ExtractorError(u'Arte live streams are not yet supported, sorry')
# self.extractLiveStream(url) # self.extractLiveStream(url)
@ -146,3 +153,22 @@ def _key(m):
'url': video_url, 'url': video_url,
'ext': 'flv', 'ext': 'flv',
} }
def _extract_liveweb(self, url, name, lang):
"""Extract form http://liveweb.arte.tv/"""
webpage = self._download_webpage(url, name)
video_id = self._search_regex(r'eventId=(\d+?)("|&)', webpage, u'event id')
config_xml = self._download_webpage('http://download.liveweb.arte.tv/o21/liveweb/events/event-%s.xml' % video_id,
video_id, u'Downloading information')
config_doc = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8'))
event_doc = config_doc.find('event')
url_node = event_doc.find('video').find('urlHd')
if url_node is None:
url_node = video_doc.find('urlSd')
return {'id': video_id,
'title': event_doc.find('name%s' % lang.capitalize()).text,
'url': url_node.text.replace('MP4', 'mp4'),
'ext': 'flv',
'thumbnail': self._og_search_thumbnail(webpage),
}