0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-27 01:31:07 +00:00
yt-dlp/yt_dlp/extractor/xstream.py
sepro add96eb9f8
[cleanup] Add more ruff rules ()
Authored by: seproDev

Reviewed-by: bashonly <88596187+bashonly@users.noreply.github.com>
Reviewed-by: Simon Sawicki <contact@grub4k.xyz>
2024-06-12 01:09:58 +02:00

114 lines
3.8 KiB
Python

import re
from .common import InfoExtractor
from ..utils import (
find_xpath_attr,
int_or_none,
parse_iso8601,
xpath_text,
xpath_with_ns,
)
class XstreamIE(InfoExtractor):
_VALID_URL = r'''(?x)
(?:
xstream:|
https?://frontend\.xstream\.(?:dk|net)/
)
(?P<partner_id>[^/]+)
(?:
:|
/feed/video/\?.*?\bid=
)
(?P<id>\d+)
'''
_TESTS = [{
'url': 'http://frontend.xstream.dk/btno/feed/video/?platform=web&id=86588',
'md5': 'd7d17e3337dc80de6d3a540aefbe441b',
'info_dict': {
'id': '86588',
'ext': 'mov',
'title': 'Otto Wollertsen',
'description': 'Vestlendingen Otto Fredrik Wollertsen',
'timestamp': 1430473209,
'upload_date': '20150501',
},
}, {
'url': 'http://frontend.xstream.dk/ap/feed/video/?platform=web&id=21039',
'only_matching': True,
}]
def _extract_video_info(self, partner_id, video_id):
data = self._download_xml(
f'http://frontend.xstream.dk/{partner_id}/feed/video/?platform=web&id={video_id}',
video_id)
NS_MAP = {
'atom': 'http://www.w3.org/2005/Atom',
'xt': 'http://xstream.dk/',
'media': 'http://search.yahoo.com/mrss/',
}
entry = data.find(xpath_with_ns('./atom:entry', NS_MAP))
title = xpath_text(
entry, xpath_with_ns('./atom:title', NS_MAP), 'title')
description = xpath_text(
entry, xpath_with_ns('./atom:summary', NS_MAP), 'description')
timestamp = parse_iso8601(xpath_text(
entry, xpath_with_ns('./atom:published', NS_MAP), 'upload date'))
formats = []
media_group = entry.find(xpath_with_ns('./media:group', NS_MAP))
for media_content in media_group.findall(xpath_with_ns('./media:content', NS_MAP)):
media_url = media_content.get('url')
if not media_url:
continue
tbr = int_or_none(media_content.get('bitrate'))
mobj = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', media_url)
if mobj:
formats.append({
'url': mobj.group('url'),
'play_path': 'mp4:{}'.format(mobj.group('playpath')),
'app': mobj.group('app'),
'ext': 'flv',
'tbr': tbr,
'format_id': 'rtmp-%d' % tbr,
})
else:
formats.append({
'url': media_url,
'tbr': tbr,
})
link = find_xpath_attr(
entry, xpath_with_ns('./atom:link', NS_MAP), 'rel', 'original')
if link is not None:
formats.append({
'url': link.get('href'),
'format_id': link.get('rel'),
'quality': 1,
})
thumbnails = [{
'url': splash.get('url'),
'width': int_or_none(splash.get('width')),
'height': int_or_none(splash.get('height')),
} for splash in media_group.findall(xpath_with_ns('./xt:splash', NS_MAP))]
return {
'id': video_id,
'title': title,
'description': description,
'timestamp': timestamp,
'formats': formats,
'thumbnails': thumbnails,
}
def _real_extract(self, url):
mobj = self._match_valid_url(url)
partner_id = mobj.group('partner_id')
video_id = mobj.group('id')
return self._extract_video_info(partner_id, video_id)