depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-23 01:08:10 +00:00
Code Issues Releases Wiki Activity

[DoodStream] Support more TLDs

Browse source 
* also fix title extraction
This commit is contained in:
dirkf 2022-06-04 09:26:41 +01:00
parent 3687a4f9bd
commit 9dd91758ae
1 changed files with 27 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

35
youtube_dl/extractor/doodstream.py
View file

@ -21,7 +21,7 @@ from .common import InfoExtractor
class DoodStreamIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dood\.(?:to|watch)/[ed]/(?P<id>[a-z0-9]+)'
_VALID_URL = r'https?://(?:www\.)?dood\.(?:to|watch|so|la|pm|sh|ws|one)/[ed]/(?P<id>[a-z0-9]+)'
_TESTS = [{
'url': 'http://dood.to/e/5s1wmbdacezb',
'md5': '4568b83b31e13242b3f1ff96c55f0595',
@ -61,11 +61,24 @@ class DoodStreamIE(InfoExtractor):
'info_dict': {
'id': 'is34uy8wvaet',
'ext': 'mp4',
'title': 'Akhanda (2021) Telugu DVDScr MP3 700MB - DoodStream',
'title': 'Akhanda (2021) Telugu DVDScr MP3 700MB',
'upload_date': '20211202',
'thumbnail': r're:https?://img\.doodcdn\.com?/[\w/]+\.jpg',
'filesize_approx': int,
'duration': 9886,
}
}, {
'url': 'https://dood.so/d/wlihoael8uog',
'md5': '2c14444c89788cc309738c1560abe278',
'info_dict': {
'id': 'wlihoael8uog',
'ext': 'mp4',
'title': 'VID 20220319 161659',
'thumbnail': r're:https?://img\.doodcdn\.com?/splash/rmpnhb8ckkk79cge\.jpg',
'upload_date': '20220319',
'filesize_approx': int,
'duration': 12.0,
}
}]
def _real_extract(self, url):
@ -76,11 +89,12 @@ class DoodStreamIE(InfoExtractor):
}
webpage = self._download_webpage(url, video_id, headers=headers)
title = self._html_search_meta(('og:title', 'twitter:title'), webpage, default=None)
if not title:
title = self._html_search_regex(r'<title\b[^>]*>([^<]+?)(?:\|\s+DoodStream\s*)?</title', webpage, 'title')
if title == 'Video not found':
raise ExtractorError(title, expected=True)
def get_title(html, fatal=False):
return self._html_search_regex(r'<title\b[^>]*>([^<]+?)(?:[|-]\s+DoodStream\s*)?</title', html, 'title', fatal=fatal)
title = get_title(webpage)
if title == 'Video not found':
raise ExtractorError(title, expected=True)
token = self._html_search_regex(r'''[?&]token=([a-z0-9]+)[&']''', webpage, 'token')
headers.update({
@ -100,7 +114,12 @@ class DoodStreamIE(InfoExtractor):
description = self._html_search_meta(
('og:description', 'description', 'twitter:description'), webpage, default=None)
webpage = self._download_webpage('https://dood.to/d/' + video_id, video_id, headers=headers, fatal=False)
webpage = self._download_webpage('https://dood.to/d/' + video_id, video_id, headers=headers, fatal=False) or ''
title = (
self._html_search_meta(('og:title', 'twitter:title'), webpage, default=None)
or get_title(webpage, fatal=(title is not None))
or title)
def get_class_text(x):
return clean_html(get_element_by_class(x, webpage))