X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fsbs.py;h=d4bd1a0d72624e65bc9a5890f371b492451a9486;hb=b5597738d4de35fd6f2be7bf1cb6a32c754d873f;hp=34058fd4bc12652ed5332103c81fd83e344d5efd;hpb=2ef6fcb5d812278db13768fb461239cbfafbbe6f;p=youtube-dl diff --git a/youtube_dl/extractor/sbs.py b/youtube_dl/extractor/sbs.py index 34058fd4b..d4bd1a0d7 100644 --- a/youtube_dl/extractor/sbs.py +++ b/youtube_dl/extractor/sbs.py @@ -1,7 +1,6 @@ # -*- coding: utf-8 -*- from __future__ import unicode_literals -import json import re from .common import InfoExtractor from ..utils import ( @@ -12,7 +11,7 @@ from ..utils import ( class SBSIE(InfoExtractor): IE_DESC = 'sbs.com.au' - _VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/ondemand/video/single/(?P[0-9]+)/' + _VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/ondemand/video/(?:single/)?(?P[0-9]+)' _TESTS = [{ # Original URL is handled by the generic IE which finds the iframe: @@ -21,25 +20,30 @@ class SBSIE(InfoExtractor): 'md5': '3150cf278965eeabb5b4cea1c963fe0a', 'info_dict': { 'id': '320403011771', - 'ext': 'flv', + 'ext': 'mp4', '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'], + }, { + 'url': 'http://www.sbs.com.au/ondemand/video/320403011771/Dingo-Conservation-The-Feed', + 'only_matching': True, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) - release_urls_json = js_to_json(self._search_regex( + player = self._search_regex( r'(?s)playerParams\.releaseUrls\s*=\s*(\{.*?\n\});\n', - webpage, '')) - release_urls = json.loads(release_urls_json) - theplatform_url = ( - release_urls.get('progressive') or release_urls.get('standard')) + 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'] title = remove_end(self._og_search_title(webpage), ' (The Feed)') description = self._html_search_meta('description', webpage) @@ -49,7 +53,6 @@ class SBSIE(InfoExtractor): '_type': 'url_transparent', 'id': video_id, 'url': theplatform_url, - 'title': title, 'description': description, 'thumbnail': thumbnail,