|
|
@ -4,6 +4,10 @@ from __future__ import unicode_literals
|
|
|
|
import re
|
|
|
|
import re
|
|
|
|
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
|
|
|
from .common import InfoExtractor
|
|
|
|
|
|
|
|
from ..compat import (
|
|
|
|
|
|
|
|
compat_parse_qs,
|
|
|
|
|
|
|
|
compat_urllib_parse_urlparse,
|
|
|
|
|
|
|
|
)
|
|
|
|
from ..utils import (
|
|
|
|
from ..utils import (
|
|
|
|
find_xpath_attr,
|
|
|
|
find_xpath_attr,
|
|
|
|
unified_strdate,
|
|
|
|
unified_strdate,
|
|
|
@ -77,7 +81,13 @@ class ArteTVPlus7IE(InfoExtractor):
|
|
|
|
def _extract_from_webpage(self, webpage, video_id, lang):
|
|
|
|
def _extract_from_webpage(self, webpage, video_id, lang):
|
|
|
|
json_url = self._html_search_regex(
|
|
|
|
json_url = self._html_search_regex(
|
|
|
|
[r'arte_vp_url=["\'](.*?)["\']', r'data-url=["\']([^"]+)["\']'],
|
|
|
|
[r'arte_vp_url=["\'](.*?)["\']', r'data-url=["\']([^"]+)["\']'],
|
|
|
|
webpage, 'json vp url')
|
|
|
|
webpage, 'json vp url', default=None)
|
|
|
|
|
|
|
|
if not json_url:
|
|
|
|
|
|
|
|
iframe_url = self._html_search_regex(
|
|
|
|
|
|
|
|
r'<iframe[^>]+src=(["\'])(?P<url>.+\bjson_url=.+?)\1',
|
|
|
|
|
|
|
|
webpage, 'iframe url', group='iframe url')
|
|
|
|
|
|
|
|
json_url = compat_parse_qs(
|
|
|
|
|
|
|
|
compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0]
|
|
|
|
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):
|
|
|
|