From 75a40b22511b4d4344cd6903e28429fa6c3991f1 Mon Sep 17 00:00:00 2001 From: Seamus Phelan Date: Mon, 13 Jul 2015 22:35:45 +1000 Subject: [PATCH] [SBS] fixes due to website changes --- youtube_dl/extractor/sbs.py | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/youtube_dl/extractor/sbs.py b/youtube_dl/extractor/sbs.py index d4bd1a0d7..ab4d1c884 100644 --- a/youtube_dl/extractor/sbs.py +++ b/youtube_dl/extractor/sbs.py @@ -1,12 +1,8 @@ # -*- coding: utf-8 -*- from __future__ import unicode_literals -import re from .common import InfoExtractor -from ..utils import ( - js_to_json, - remove_end, -) +from ..utils import remove_end class SBSIE(InfoExtractor): @@ -34,18 +30,22 @@ class SBSIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + # the video is in the following iframe + iframe_url = 'http://www.sbs.com.au/ondemand/video/single/' + video_id + '?context=web' + webpage = self._download_webpage(iframe_url, video_id) - player = self._search_regex( - r'(?s)playerParams\.releaseUrls\s*=\s*(\{.*?\n\});\n', - webpage, 'player') - player = re.sub(r"'\s*\+\s*[\da-zA-Z_]+\s*\+\s*'", '', player) + player_params = self._search_regex( + r'(?s)(playerParams.+?releaseUrls.+?\n)', + webpage, 'playerParams') + player_params_js = self._search_regex( + r'({.*})', + player_params, 'player_param_js') - release_urls = self._parse_json(js_to_json(player), video_id) + player_params_json = self._parse_json(player_params_js, video_id) - theplatform_url = release_urls.get('progressive') or release_urls['standard'] + theplatform_url = player_params_json.get('releaseUrls')['progressive'] or player_params_json.get('releaseUrls')['standard'] - title = remove_end(self._og_search_title(webpage), ' (The Feed)') + title = remove_end(self._og_search_title(webpage, default=video_id, fatal=False), ' (The Feed)') description = self._html_search_meta('description', webpage) thumbnail = self._og_search_thumbnail(webpage)