Upstream/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-12 14:26:49 +01:00
Code Issues Packages Projects Releases Wiki Activity

[ntvru] add support for non relative file URLs(closes #23140)

Browse Source
This commit is contained in:
Remita Amine 2019-11-18 21:40:53 +01:00
parent 7e70620a34
commit f9c4a45210
1 changed files with 24 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
youtube_dl/extractor/ntvru.py
View File

@ -3,9 +3,10 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
clean_html,
xpath_text,
int_or_none, int_or_none,
strip_or_none,
unescapeHTML,
xpath_text,
) )
@ -47,10 +48,10 @@ class NTVRuIE(InfoExtractor):
'duration': 1496, 'duration': 1496,
}, },
}, { }, {
'url': 'http://www.ntv.ru/kino/Koma_film', 'url': 'https://www.ntv.ru/kino/Koma_film/m70281/o336036/video/',
'md5': 'f825770930937aa7e5aca0dc0d29319a', 'md5': 'e9c7cde24d9d3eaed545911a04e6d4f4',
'info_dict': { 'info_dict': {
'id': '1007609', 'id': '1126480',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Остросюжетный фильм «Кома»', 'title': 'Остросюжетный фильм «Кома»',
'description': 'Остросюжетный фильм «Кома»', 'description': 'Остросюжетный фильм «Кома»',
@ -68,6 +69,10 @@ class NTVRuIE(InfoExtractor):
'thumbnail': r're:^http://.*\.jpg', 'thumbnail': r're:^http://.*\.jpg',
'duration': 2590, 'duration': 2590,
}, },
}, {
# Schemeless file URL
'url': 'https://www.ntv.ru/video/1797442',
'only_matching': True,
}] }]
_VIDEO_ID_REGEXES = [ _VIDEO_ID_REGEXES = [
@ -96,37 +101,31 @@ def _real_extract(self, url):
'http://www.ntv.ru/vi%s/' % video_id, 'http://www.ntv.ru/vi%s/' % video_id,
video_id, 'Downloading video XML') video_id, 'Downloading video XML')
title = clean_html(xpath_text(player, './data/title', 'title', fatal=True)) title = strip_or_none(unescapeHTML(xpath_text(player, './data/title', 'title', fatal=True)))
description = clean_html(xpath_text(player, './data/description', 'description'))
video = player.find('./data/video') video = player.find('./data/video')
video_id = xpath_text(video, './id', 'video id')
thumbnail = xpath_text(video, './splash', 'thumbnail')
duration = int_or_none(xpath_text(video, './totaltime', 'duration'))
view_count = int_or_none(xpath_text(video, './views', 'view count'))
token = self._download_webpage(
'http://stat.ntv.ru/services/access/token',
video_id, 'Downloading access token')
formats = [] formats = []
for format_id in ['', 'hi', 'webm']: for format_id in ['', 'hi', 'webm']:
file_ = video.find('./%sfile' % format_id) file_ = xpath_text(video, './%sfile' % format_id)
if file_ is None: if not file_:
continue continue
size = video.find('./%ssize' % format_id) if file_.startswith('//'):
file_ = self._proto_relative_url(file_)
elif not file_.startswith('http'):
file_ = 'http://media.ntv.ru/vod/' + file_
formats.append({ formats.append({
'url': 'http://media2.ntv.ru/vod/%s&tok=%s' % (file_.text, token), 'url': file_,
'filesize': int_or_none(size.text if size is not None else None), 'filesize': int_or_none(xpath_text(video, './%ssize' % format_id)),
}) })
self._sort_formats(formats) self._sort_formats(formats)
return { return {
'id': video_id, 'id': xpath_text(video, './id'),
'title': title, 'title': title,
'description': description, 'description': strip_or_none(unescapeHTML(xpath_text(player, './data/description'))),
'thumbnail': thumbnail, 'thumbnail': xpath_text(video, './splash'),
'duration': duration, 'duration': int_or_none(xpath_text(video, './totaltime')),
'view_count': view_count, 'view_count': int_or_none(xpath_text(video, './views')),
'formats': formats, 'formats': formats,
} }