1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2025-01-08 14:17:54 +01:00

airvuz: add remaining attributes

This commit is contained in:
Diogo Lemos 2020-02-25 21:15:11 +00:00
parent 44e9793a97
commit 80a2c83998

View File

@ -2,28 +2,46 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import determine_ext
import re
class AirVuzIE(InfoExtractor): class AirVuzIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?airvuz\.com/video/(?:.+)?id=(?P<id>.+)' _VALID_URL = r'https?://(?:www\.)?airvuz\.com/video/(?P<display_id>.+)\?id=(?P<id>.+)'
_TEST = { _TEST = {
'url': 'https://www.airvuz.com/video/An-Imaginary-World?id=599e85c49282a717c50f2f7a', 'url': 'https://www.airvuz.com/video/An-Imaginary-World?id=599e85c49282a717c50f2f7a',
'info_dict': { 'info_dict': {
'id': '599e85c49282a717c50f2f7a', 'id': '599e85c49282a717c50f2f7a',
'ext': 'mp4', 'display_id': 'An-Imaginary-World',
'title': 'md5:7fc56270e7a70fa81a5935b72eacbe29', 'title': 'md5:7fc56270e7a70fa81a5935b72eacbe29',
'ext': 'mp4',
'thumbnail': r're:^https?://.*\.jpg$',
}, },
} }
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) groups = re.match(self._VALID_URL, url)
video_id = groups.group('id')
display_id = groups.group('display_id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = self._html_search_meta('og:title', webpage) title = self._og_search_title(webpage)
thumbnail = self._og_search_thumbnail(webpage)
description = self._og_search_description(webpage)
uploader = self._html_search_regex(r'class=(?:\'img-circle\'|"img-circle"|img-circle)[^>]+?alt=(?:"([^"]+?)"|\'([^\']+?)\'|([^\s"\'=<>`]+))', webpage, 'uploader', fatal=False) or self._html_search_regex(r'https?://(?:www\.)?airvuz\.com/user/([^>]*)', webpage, 'uploader', fatal=False)
video_url = self._html_search_regex(r'<meta[^>]+?(?:name|property)=(?:\'og:video:url\'|"og:video:url"|og:video:url)[^>]+?content=(?:"([^"]+?)"|\'([^\']+?)\'|([^\s"\'=<>`]+))', webpage, 'video_url') video_url = self._html_search_regex(r'<meta[^>]+?(?:name|property)=(?:\'og:video:url\'|"og:video:url"|og:video:url)[^>]+?content=(?:"([^"]+?)"|\'([^\']+?)\'|([^\s"\'=<>`]+))', webpage, 'video_url')
ext = determine_ext(video_url)
return { return {
'id': video_id, 'id': video_id,
'display_id': display_id,
'title': title, 'title': title,
'url': video_url, 'url': video_url,
'ext': ext,
'thumbnail': thumbnail,
'description': description,
'uploader': uploader,
} }