mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-22 02:15:12 +00:00
[tele5] Fix extraction (closes #24553)
This commit is contained in:
parent
4e7b5bba5f
commit
6a6e1a0cd8
1 changed files with 53 additions and 8 deletions
|
@ -1,9 +1,19 @@
|
|||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .jwplatform import JWPlatformIE
|
||||
from .nexx import NexxIE
|
||||
from ..compat import compat_urlparse
|
||||
from ..compat import (
|
||||
compat_str,
|
||||
compat_urlparse,
|
||||
)
|
||||
from ..utils import (
|
||||
NO_DEFAULT,
|
||||
try_get,
|
||||
)
|
||||
|
||||
|
||||
class Tele5IE(InfoExtractor):
|
||||
|
@ -44,14 +54,49 @@ def _real_extract(self, url):
|
|||
qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
|
||||
video_id = (qs.get('vid') or qs.get('ve_id') or [None])[0]
|
||||
|
||||
if not video_id:
|
||||
NEXX_ID_RE = r'\d{6,}'
|
||||
JWPLATFORM_ID_RE = r'[a-zA-Z0-9]{8}'
|
||||
|
||||
def nexx_result(nexx_id):
|
||||
return self.url_result(
|
||||
'https://api.nexx.cloud/v3/759/videos/byid/%s' % nexx_id,
|
||||
ie=NexxIE.ie_key(), video_id=nexx_id)
|
||||
|
||||
nexx_id = jwplatform_id = None
|
||||
|
||||
if video_id:
|
||||
if re.match(NEXX_ID_RE, video_id):
|
||||
return nexx_result(video_id)
|
||||
elif re.match(JWPLATFORM_ID_RE, video_id):
|
||||
jwplatform_id = video_id
|
||||
|
||||
if not nexx_id:
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
video_id = self._html_search_regex(
|
||||
(r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](\d+)',
|
||||
r'\s+id\s*=\s*["\']player_(\d{6,})',
|
||||
r'\bdata-id\s*=\s*["\'](\d{6,})'), webpage, 'video id')
|
||||
|
||||
def extract_id(pattern, name, default=NO_DEFAULT):
|
||||
return self._html_search_regex(
|
||||
(r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](%s)' % pattern,
|
||||
r'\s+id\s*=\s*["\']player_(%s)' % pattern,
|
||||
r'\bdata-id\s*=\s*["\'](%s)' % pattern), webpage, name,
|
||||
default=default)
|
||||
|
||||
nexx_id = extract_id(NEXX_ID_RE, 'nexx id', default=None)
|
||||
if nexx_id:
|
||||
return nexx_result(nexx_id)
|
||||
|
||||
if not jwplatform_id:
|
||||
jwplatform_id = extract_id(JWPLATFORM_ID_RE, 'jwplatform id')
|
||||
|
||||
media = self._download_json(
|
||||
'https://cdn.jwplayer.com/v2/media/' + jwplatform_id,
|
||||
display_id)
|
||||
nexx_id = try_get(
|
||||
media, lambda x: x['playlist'][0]['nexx_id'], compat_str)
|
||||
|
||||
if nexx_id:
|
||||
return nexx_result(nexx_id)
|
||||
|
||||
return self.url_result(
|
||||
'https://api.nexx.cloud/v3/759/videos/byid/%s' % video_id,
|
||||
ie=NexxIE.ie_key(), video_id=video_id)
|
||||
'jwplatform:%s' % jwplatform_id, ie=JWPlatformIE.ie_key(),
|
||||
video_id=jwplatform_id)
|
||||
|
|
Loading…
Reference in a new issue