mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-02 17:22:31 +01:00
[freevideo] Simplify and raise error for foreigners (Fixes #4131)
This commit is contained in:
parent
11b28e93d3
commit
3deed1e91a
@ -1,49 +1,38 @@
|
|||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
import re
|
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
from ..utils import (
|
from ..utils import ExtractorError
|
||||||
ExtractorError,
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
class FreeVideoIE(InfoExtractor):
|
class FreeVideoIE(InfoExtractor):
|
||||||
_VALID_URL = r'^http://www.freevideo.cz/vase-videa/(?P<videoid>[^.]+)\.html$'
|
_VALID_URL = r'^http://www.freevideo.cz/vase-videa/(?P<id>[^.]+)\.html(?:$|[?#])'
|
||||||
|
|
||||||
_TEST = {
|
_TEST = {
|
||||||
'url': 'http://www.freevideo.cz/vase-videa/vysukany-zadecek-22033.html',
|
'url': 'http://www.freevideo.cz/vase-videa/vysukany-zadecek-22033.html',
|
||||||
'file': 'vysukany-zadecek-22033.mp4',
|
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
|
'id': 'vysukany-zadecek-22033',
|
||||||
|
'ext': 'mp4',
|
||||||
"title": "vysukany-zadecek-22033",
|
"title": "vysukany-zadecek-22033",
|
||||||
"age_limit": 18,
|
"age_limit": 18,
|
||||||
}
|
},
|
||||||
|
'skip': 'Blocked outside .cz',
|
||||||
}
|
}
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
mobj = re.match(self._VALID_URL, url)
|
video_id = self._match_id(url)
|
||||||
if mobj is None:
|
webpage, handle = self._download_webpage_handle(url, video_id)
|
||||||
raise ExtractorError('Invalid search query "%s"' % query)
|
if '//www.czechav.com/' in handle.geturl():
|
||||||
|
raise ExtractorError(
|
||||||
|
'Access to freevideo is blocked from your location',
|
||||||
|
expected=True)
|
||||||
|
|
||||||
video_id = mobj.group('videoid')
|
video_url = self._search_regex(
|
||||||
|
r'\s+url: "(http://[a-z0-9-]+.cdn.freevideo.cz/stream/.*?/video.mp4)"',
|
||||||
# Get webpage content
|
webpage, 'video URL')
|
||||||
webpage = self._download_webpage(url, video_id)
|
|
||||||
|
|
||||||
age_limit = self._rta_search(webpage)
|
|
||||||
if age_limit == 0:
|
|
||||||
# interpret 0 as mis-detection since this site is adult-content only.
|
|
||||||
# However, if we get non-0, assume the rtalabel started giving proper
|
|
||||||
# results
|
|
||||||
age_limit = 18
|
|
||||||
|
|
||||||
url = re.search(r'\s+url: "(http://[a-z0-9-]+.cdn.freevideo.cz/stream/.*/video.mp4)"', webpage)
|
|
||||||
if url is None:
|
|
||||||
raise ExtractorError('ERROR: unable to extract video url')
|
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'url': url.groups()[0],
|
'url': video_url,
|
||||||
'title': video_id,
|
'title': video_id,
|
||||||
'age_limit': age_limit,
|
'age_limit': 18,
|
||||||
}
|
}
|
||||||
|
Loading…
Reference in New Issue
Block a user