[ringtv] Fix and add news extraction
This commit is contained in:
parent
af1588c05f
commit
d3a1c71917
1 changed files with 30 additions and 23 deletions
|
@ -1,37 +1,44 @@
|
||||||
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
import re
|
import re
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
|
|
||||||
|
|
||||||
class RingTVIE(InfoExtractor):
|
class RingTVIE(InfoExtractor):
|
||||||
_VALID_URL = r'(?:http://)?(?:www\.)?ringtv\.craveonline\.com/videos/video/([^/]+)'
|
_VALID_URL = r'(?:http://)?(?:www\.)?ringtv\.craveonline\.com/(?P<type>news|videos/video)/(?P<id>[^/?#]+)'
|
||||||
_TEST = {
|
_TEST = {
|
||||||
u"url": u"http://ringtv.craveonline.com/videos/video/746619-canelo-alvarez-talks-about-mayweather-showdown",
|
"url": "http://ringtv.craveonline.com/news/310833-luis-collazo-says-victor-ortiz-better-not-quit-on-jan-30",
|
||||||
u"file": u"746619.mp4",
|
"file": "857645.mp4",
|
||||||
u"md5": u"7c46b4057d22de32e0a539f017e64ad3",
|
"md5": "d25945f5df41cdca2d2587165ac28720",
|
||||||
u"info_dict": {
|
"info_dict": {
|
||||||
u"title": u"Canelo Alvarez talks about Mayweather showdown",
|
"title": 'Video: Luis Collazo says Victor Ortiz "better not quit on Jan. 30" - Ring TV',
|
||||||
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."
|
"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):
|
def _real_extract(self, url):
|
||||||
mobj = re.match(self._VALID_URL, 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)
|
webpage = self._download_webpage(url, video_id)
|
||||||
title = self._search_regex(r'<title>(.+?)</title>',
|
|
||||||
webpage, 'video title').replace(' | RingTV','')
|
if mobj.group('type') == 'news':
|
||||||
description = self._search_regex(r'<div class="blurb">(.+?)</div>',
|
video_id = self._search_regex(
|
||||||
webpage, 'Description')
|
r'''(?x)<iframe[^>]+src="http://cms\.springboardplatform\.com/
|
||||||
final_url = "http://ringtv.craveonline.springboardplatform.com/storage/ringtv.craveonline.com/conversion/%s.mp4" %(str(video_id))
|
embed_iframe/[0-9]+/video/([0-9]+)/''',
|
||||||
thumbnail_url = "http://ringtv.craveonline.springboardplatform.com/storage/ringtv.craveonline.com/snapshots/%s.jpg" %(str(video_id))
|
webpage, 'real video ID')
|
||||||
ext = final_url.split('.')[-1]
|
title = self._og_search_title(webpage)
|
||||||
return [{
|
description = self._html_search_regex(
|
||||||
'id' : video_id,
|
r'addthis:description="([^"]+)"',
|
||||||
'url' : final_url,
|
webpage, 'description', fatal=False)
|
||||||
'ext' : ext,
|
final_url = "http://ringtv.craveonline.springboardplatform.com/storage/ringtv.craveonline.com/conversion/%s.mp4" % video_id
|
||||||
'title' : title,
|
thumbnail_url = "http://ringtv.craveonline.springboardplatform.com/storage/ringtv.craveonline.com/snapshots/%s.jpg" % video_id
|
||||||
'thumbnail' : thumbnail_url,
|
|
||||||
'description' : description,
|
return {
|
||||||
}]
|
'id': video_id,
|
||||||
|
'url': final_url,
|
||||||
|
'title': title,
|
||||||
|
'thumbnail': thumbnail_url,
|
||||||
|
'description': description,
|
||||||
|
}
|
||||||
|
|
||||||
|
|
Loading…
Reference in a new issue