fenix
/
ytdl-nightly
mirror of https://github.com/ytdl-org/ytdl-nightly.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[SBS] fixes due to website changes

This commit is contained in:
Seamus Phelan 2015-07-13 22:35:45 +10:00
parent 28fb109ed0
commit 75a40b2251
1 changed files with 13 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
youtube_dl/extractor/sbs.py
View File

@ -1,12 +1,8 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import remove_end
js_to_json,
remove_end,
)
class SBSIE(InfoExtractor): class SBSIE(InfoExtractor):
@ -34,18 +30,22 @@ class SBSIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(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( player_params = self._search_regex(
r'(?s)playerParams\.releaseUrls\s*=\s*(\{.*?\n\});\n', r'(?s)(playerParams.+?releaseUrls.+?\n)',
webpage, 'player') webpage, 'playerParams')
player = re.sub(r"'\s*\+\s*[\da-zA-Z_]+\s*\+\s*'", '', player) 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) description = self._html_search_meta('description', webpage)
thumbnail = self._og_search_thumbnail(webpage) thumbnail = self._og_search_thumbnail(webpage)