from .common import InfoExtractor
from ..utils import (
- # This is used by the not implemented extractLiveStream method
- compat_urllib_parse,
-
ExtractorError,
unified_strdate,
)
return any(re.match(regex, url) for regex in (cls._EMISSION_URL, cls._VIDEOS_URL))
# TODO implement Live Stream
+ # from ..utils import compat_urllib_parse
# def extractLiveStream(self, url):
# video_lang = url.split('/')[-4]
# info = self.grep_webpage(
def _real_extract(self, url):
mobj = re.match(self._EMISSION_URL, url)
if mobj is not None:
- name = mobj.group('name')
lang = mobj.group('lang')
# This is not a real id, it can be for example AJT for the news
# http://www.arte.tv/guide/fr/emissions/AJT/arte-journal
def _extract_emission(self, url, video_id, lang):
"""Extract from www.arte.tv/guide"""
- if video_id.replace('-','').isdigit():
- json_url = 'http://org-www.arte.tv/papi/tvguide/videos/stream/player/F/%s_PLUS7-F/ALL/ALL.json' % video_id
- else:
- # We don't know the real id of the video, we have to search in the webpage
- webpage = self._download_webpage(url, video_id)
- json_url = self._html_search_regex(r'arte_vp_url="(.*?)"', webpage, 'json url')
+ webpage = self._download_webpage(url, video_id)
+ json_url = self._html_search_regex(r'arte_vp_url="(.*?)"', webpage, 'json url')
json_info = self._download_webpage(json_url, video_id, 'Downloading info json')
self.report_extraction(video_id)