mirror of
https://github.com/ytdl-org/youtube-dl
synced 2024-11-05 19:17:07 +01:00
[vodlocker] Fix extraction (Closes #8231)
This commit is contained in:
parent
11c60089a8
commit
fbd90643cb
@ -5,12 +5,13 @@ from .common import InfoExtractor
|
|||||||
from ..compat import compat_urllib_parse
|
from ..compat import compat_urllib_parse
|
||||||
from ..utils import (
|
from ..utils import (
|
||||||
ExtractorError,
|
ExtractorError,
|
||||||
|
NO_DEFAULT,
|
||||||
sanitized_Request,
|
sanitized_Request,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
class VodlockerIE(InfoExtractor):
|
class VodlockerIE(InfoExtractor):
|
||||||
_VALID_URL = r'https?://(?:www\.)?vodlocker\.com/(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
|
_VALID_URL = r'https?://(?:www\.)?vodlocker\.(?:com|city)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
|
||||||
|
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'http://vodlocker.com/e8wvyzz4sl42',
|
'url': 'http://vodlocker.com/e8wvyzz4sl42',
|
||||||
@ -43,16 +44,31 @@ class VodlockerIE(InfoExtractor):
|
|||||||
webpage = self._download_webpage(
|
webpage = self._download_webpage(
|
||||||
req, video_id, 'Downloading video page')
|
req, video_id, 'Downloading video page')
|
||||||
|
|
||||||
|
def extract_file_url(html, default=NO_DEFAULT):
|
||||||
|
return self._search_regex(
|
||||||
|
r'file:\s*"(http[^\"]+)",', html, 'file url', default=default)
|
||||||
|
|
||||||
|
video_url = extract_file_url(webpage, default=None)
|
||||||
|
|
||||||
|
if not video_url:
|
||||||
|
embed_url = self._search_regex(
|
||||||
|
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?vodlocker\.(?:com|city)/embed-.+?)\1',
|
||||||
|
webpage, 'embed url', group='url')
|
||||||
|
embed_webpage = self._download_webpage(
|
||||||
|
embed_url, video_id, 'Downloading embed webpage')
|
||||||
|
video_url = extract_file_url(embed_webpage)
|
||||||
|
thumbnail_webpage = embed_webpage
|
||||||
|
else:
|
||||||
|
thumbnail_webpage = webpage
|
||||||
|
|
||||||
title = self._search_regex(
|
title = self._search_regex(
|
||||||
r'id="file_title".*?>\s*(.*?)\s*<(?:br|span)', webpage, 'title')
|
r'id="file_title".*?>\s*(.*?)\s*<(?:br|span)', webpage, 'title')
|
||||||
thumbnail = self._search_regex(
|
thumbnail = self._search_regex(
|
||||||
r'image:\s*"(http[^\"]+)",', webpage, 'thumbnail')
|
r'image:\s*"(http[^\"]+)",', thumbnail_webpage, 'thumbnail', fatal=False)
|
||||||
url = self._search_regex(
|
|
||||||
r'file:\s*"(http[^\"]+)",', webpage, 'file url')
|
|
||||||
|
|
||||||
formats = [{
|
formats = [{
|
||||||
'format_id': 'sd',
|
'format_id': 'sd',
|
||||||
'url': url,
|
'url': video_url,
|
||||||
}]
|
}]
|
||||||
|
|
||||||
return {
|
return {
|
||||||
|
Loading…
Reference in New Issue
Block a user