From d3a1c7191731ba391167f3b3b04e08982349be8c Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Wed, 22 Jan 2014 02:16:40 +0100 Subject: [PATCH] [ringtv] Fix and add news extraction --- youtube_dl/extractor/ringtv.py | 53 +++++++++++++++++++--------------- 1 file changed, 30 insertions(+), 23 deletions(-) diff --git a/youtube_dl/extractor/ringtv.py b/youtube_dl/extractor/ringtv.py index 1b08c3167..9fbdb9fcb 100644 --- a/youtube_dl/extractor/ringtv.py +++ b/youtube_dl/extractor/ringtv.py @@ -1,37 +1,44 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor class RingTVIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:www\.)?ringtv\.craveonline\.com/videos/video/([^/]+)' + _VALID_URL = r'(?:http://)?(?:www\.)?ringtv\.craveonline\.com/(?Pnews|videos/video)/(?P[^/?#]+)' _TEST = { - u"url": u"http://ringtv.craveonline.com/videos/video/746619-canelo-alvarez-talks-about-mayweather-showdown", - u"file": u"746619.mp4", - u"md5": u"7c46b4057d22de32e0a539f017e64ad3", - u"info_dict": { - u"title": u"Canelo Alvarez talks about Mayweather showdown", - u"description": u"Saul \\\"Canelo\\\" Alvarez spoke to the media about his Sept. 14 showdown with Floyd Mayweather after their kick-off presser in NYC. Canelo is motivated and confident that he will have the speed and gameplan to beat the pound-for-pound king." + "url": "http://ringtv.craveonline.com/news/310833-luis-collazo-says-victor-ortiz-better-not-quit-on-jan-30", + "file": "857645.mp4", + "md5": "d25945f5df41cdca2d2587165ac28720", + "info_dict": { + "title": 'Video: Luis Collazo says Victor Ortiz "better not quit on Jan. 30" - Ring TV', + "description": 'Luis Collazo is excited about his Jan. 30 showdown with fellow former welterweight titleholder Victor Ortiz at Barclays Center in his hometown of Brooklyn. The SuperBowl week fight headlines a Golden Boy Live! card on Fox Sports 1.', } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1).split('-')[0] + video_id = mobj.group('id').split('-')[0] webpage = self._download_webpage(url, video_id) - title = self._search_regex(r'(.+?)', - webpage, 'video title').replace(' | RingTV','') - description = self._search_regex(r'
(.+?)
', - webpage, 'Description') - final_url = "http://ringtv.craveonline.springboardplatform.com/storage/ringtv.craveonline.com/conversion/%s.mp4" %(str(video_id)) - thumbnail_url = "http://ringtv.craveonline.springboardplatform.com/storage/ringtv.craveonline.com/snapshots/%s.jpg" %(str(video_id)) - ext = final_url.split('.')[-1] - return [{ - 'id' : video_id, - 'url' : final_url, - 'ext' : ext, - 'title' : title, - 'thumbnail' : thumbnail_url, - 'description' : description, - }] + + if mobj.group('type') == 'news': + video_id = self._search_regex( + r'''(?x)]+src="http://cms\.springboardplatform\.com/ + embed_iframe/[0-9]+/video/([0-9]+)/''', + webpage, 'real video ID') + title = self._og_search_title(webpage) + description = self._html_search_regex( + r'addthis:description="([^"]+)"', + webpage, 'description', fatal=False) + final_url = "http://ringtv.craveonline.springboardplatform.com/storage/ringtv.craveonline.com/conversion/%s.mp4" % video_id + thumbnail_url = "http://ringtv.craveonline.springboardplatform.com/storage/ringtv.craveonline.com/snapshots/%s.jpg" % video_id + + return { + 'id': video_id, + 'url': final_url, + 'title': title, + 'thumbnail': thumbnail_url, + 'description': description, + }