From 2ef6fcb5d812278db13768fb461239cbfafbbe6f Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sat, 23 Aug 2014 15:20:49 +0200 Subject: [PATCH] [sbs] Add new extractor (Fixes #3566) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/generic.py | 7 ++++ youtube_dl/extractor/sbs.py | 56 ++++++++++++++++++++++++++++++++ 3 files changed, 64 insertions(+) create mode 100644 youtube_dl/extractor/sbs.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 5fe3d39b1..ddcf2e414 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -276,6 +276,7 @@ from .rutube import ( from .rutv import RUTVIE from .sapo import SapoIE from .savefrom import SaveFromIE +from .sbs import SBSIE from .scivee import SciVeeIE from .screencast import ScreencastIE from .servingsys import ServingSysIE diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 2ff691b45..62b1da25e 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -731,6 +731,13 @@ class GenericIE(InfoExtractor): if mobj is not None: return self.url_result(mobj.group('url'), 'Yahoo') + # Look for embedded sbs.com.au player + mobj = re.search( + r']+?src=(["\'])(?Phttps?://(?:www\.)sbs\.com\.au/ondemand/video/single/.+?)\1', + webpage) + if mobj is not None: + return self.url_result(mobj.group('url'), 'SBS') + # Start with something easy: JW Player in SWFObject found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) if not found: diff --git a/youtube_dl/extractor/sbs.py b/youtube_dl/extractor/sbs.py new file mode 100644 index 000000000..34058fd4b --- /dev/null +++ b/youtube_dl/extractor/sbs.py @@ -0,0 +1,56 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +import json +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[0-9]+)/' + + _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': 'flv', + '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'], + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + + release_urls_json = js_to_json(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')) + + 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, + }