from .common import InfoExtractor
from ..utils import (
- # This is used by the not implemented extractLiveStream method
- compat_urllib_parse,
-
ExtractorError,
+ find_xpath_attr,
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"""
- json_url = 'http://org-www.arte.tv/papi/tvguide/videos/stream/player/F/%s_PLUS7-F/ALL/ALL.json' % video_id
+ 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)
l = 'F'
elif lang == 'de':
l = 'A'
- regexes = [r'VO?%s' % l, r'V%s-ST.' % l]
+ regexes = [r'VO?%s' % l, r'VO?.-ST%s' % l]
return any(re.match(r, f['versionCode']) for r in regexes)
# Some formats may not be in the same language as the url
formats = filter(_match_lang, formats)
ref_xml_url = ref_xml_url.replace('.html', ',view,asPlayerXml.xml')
ref_xml = self._download_webpage(ref_xml_url, video_id, note=u'Downloading metadata')
ref_xml_doc = xml.etree.ElementTree.fromstring(ref_xml)
- config_node = ref_xml_doc.find('.//video[@lang="%s"]' % lang)
+ config_node = find_xpath_attr(ref_xml_doc, './/video', 'lang', lang)
config_xml_url = config_node.attrib['ref']
config_xml = self._download_webpage(config_xml_url, video_id, note=u'Downloading configuration')