aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-07-23 11:41:05 +0200
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-07-23 11:41:05 +0200
commit67ae7b4760be259d82013fcabe3e0e4cd8f0a9df (patch)
tree2173ebfb9c4018cb8b32a73055dba36d60deb6b1
parentde48addae2ae61eded2992cae61d405647847f8e (diff)
downloadyoutube-dl-67ae7b4760be259d82013fcabe3e0e4cd8f0a9df.tar.xz
Fix BreakIE
Also detect videos that come from Youtube
-rw-r--r--youtube_dl/extractor/breakcom.py25
1 files changed, 15 insertions, 10 deletions
diff --git a/youtube_dl/extractor/breakcom.py b/youtube_dl/extractor/breakcom.py
index 34f555e89..53a898de3 100644
--- a/youtube_dl/extractor/breakcom.py
+++ b/youtube_dl/extractor/breakcom.py
@@ -1,6 +1,8 @@
import re
+import json
from .common import InfoExtractor
+from ..utils import determine_ext
class BreakIE(InfoExtractor):
@@ -17,17 +19,20 @@ class BreakIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1).split("-")[-1]
- webpage = self._download_webpage(url, video_id)
- video_url = re.search(r"videoPath: '(.+?)',",webpage).group(1)
- key = re.search(r"icon: '(.+?)',",webpage).group(1)
- final_url = str(video_url)+"?"+str(key)
- thumbnail_url = re.search(r"thumbnailURL: '(.+?)'",webpage).group(1)
- title = re.search(r"sVidTitle: '(.+)',",webpage).group(1)
- ext = video_url.split('.')[-1]
+ embed_url = 'http://www.break.com/embed/%s' % video_id
+ webpage = self._download_webpage(embed_url, video_id)
+ info_json = self._search_regex(r'var embedVars = ({.*?});', webpage,
+ u'info json', flags=re.DOTALL)
+ info = json.loads(info_json)
+ video_url = info['videoUri']
+ m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', video_url)
+ if m_youtube is not None:
+ return self.url_result(m_youtube.group(1), 'Youtube')
+ final_url = video_url + '?' + info['AuthToken']
return [{
'id': video_id,
'url': final_url,
- 'ext': ext,
- 'title': title,
- 'thumbnail': thumbnail_url,
+ 'ext': determine_ext(final_url),
+ 'title': info['contentName'],
+ 'thumbnail': info['thumbUri'],
}]