1
0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-22 09:27:01 +00:00
youtube-dl/youtube_dl/extractor/sbs.py

60 lines
2.1 KiB
Python
Raw Normal View History

2014-08-23 13:20:49 +00:00
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
js_to_json,
remove_end,
)
class SBSIE(InfoExtractor):
IE_DESC = 'sbs.com.au'
_VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/ondemand/video/(?:single/)?(?P<id>[0-9]+)'
2014-08-23 13:20:49 +00:00
_TESTS = [{
# Original URL is handled by the generic IE which finds the iframe:
# http://www.sbs.com.au/thefeed/blog/2014/08/21/dingo-conservation
'url': 'http://www.sbs.com.au/ondemand/video/single/320403011771/?source=drupal&vertical=thefeed',
'md5': '3150cf278965eeabb5b4cea1c963fe0a',
'info_dict': {
'id': '320403011771',
'ext': 'mp4',
2014-08-23 13:20:49 +00:00
'title': 'Dingo Conservation',
'description': 'Dingoes are on the brink of extinction; most of the animals we think are dingoes are in fact crossbred with wild dogs. This family run a dingo conservation park to prevent their extinction',
'thumbnail': 're:http://.*\.jpg',
},
'add_ies': ['generic'],
2014-11-23 20:39:15 +00:00
}, {
'url': 'http://www.sbs.com.au/ondemand/video/320403011771/Dingo-Conservation-The-Feed',
'only_matching': True,
2014-08-23 13:20:49 +00:00
}]
def _real_extract(self, url):
2015-05-16 15:07:29 +00:00
video_id = self._match_id(url)
2014-08-23 13:20:49 +00:00
webpage = self._download_webpage(url, video_id)
2015-05-16 15:07:29 +00:00
player = self._search_regex(
2014-08-23 13:20:49 +00:00
r'(?s)playerParams\.releaseUrls\s*=\s*(\{.*?\n\});\n',
2015-05-16 15:07:29 +00:00
webpage, 'player')
player = re.sub(r"'\s*\+\s*[\da-zA-Z_]+\s*\+\s*'", '', player)
release_urls = self._parse_json(js_to_json(player), video_id)
theplatform_url = release_urls.get('progressive') or release_urls['standard']
2014-08-23 13:20:49 +00:00
title = remove_end(self._og_search_title(webpage), ' (The Feed)')
description = self._html_search_meta('description', webpage)
thumbnail = self._og_search_thumbnail(webpage)
return {
'_type': 'url_transparent',
'id': video_id,
'url': theplatform_url,
'title': title,
'description': description,
'thumbnail': thumbnail,
}