summaryrefslogtreecommitdiffhomepage
diff options
context:
space:
mode:
authorPhilipp Hagemeister <[email protected]>2014-12-12 13:03:16 +0100
committerPhilipp Hagemeister <[email protected]>2014-12-12 13:03:16 +0100
commit0d2fb1d19342aa1f9ae2f9509ca3cdb819c6b8d1 (patch)
tree457bf717ba759663c911096975990e2c9ea6f306
parent82b34105d301f0aa6897b6695e390324e3722add (diff)
downloadyoutube-dl-0d2fb1d19342aa1f9ae2f9509ca3cdb819c6b8d1.tar.gz
youtube-dl-0d2fb1d19342aa1f9ae2f9509ca3cdb819c6b8d1.zip
[helsinki] Fix extraction
-rw-r--r--youtube_dl/extractor/helsinki.py37
1 files changed, 9 insertions, 28 deletions
diff --git a/youtube_dl/extractor/helsinki.py b/youtube_dl/extractor/helsinki.py
index 5268efa49..93107b306 100644
--- a/youtube_dl/extractor/helsinki.py
+++ b/youtube_dl/extractor/helsinki.py
@@ -2,9 +2,8 @@
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
+from ..utils import js_to_json
class HelsinkiIE(InfoExtractor):
@@ -24,39 +23,21 @@ class HelsinkiIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
- formats = []
-
- mobj = re.search(r'file=((\w+):[^&]+)', webpage)
- if mobj:
- formats.append({
- 'ext': mobj.group(2),
- 'play_path': mobj.group(1),
- 'url': 'rtmp://flashvideo.it.helsinki.fi/vod/',
- 'player_url': 'http://video.helsinki.fi/player.swf',
- 'format_note': 'sd',
- 'quality': 0,
- })
-
- mobj = re.search(r'hd\.file=((\w+):[^&]+)', webpage)
- if mobj:
- formats.append({
- 'ext': mobj.group(2),
- 'play_path': mobj.group(1),
- 'url': 'rtmp://flashvideo.it.helsinki.fi/vod/',
- 'player_url': 'http://video.helsinki.fi/player.swf',
- 'format_note': 'hd',
- 'quality': 1,
- })
+ params = self._parse_json(self._html_search_regex(
+ r'(?s)jwplayer\("player"\).setup\((\{.*?\})\);',
+ webpage, 'player code'), video_id, transform_source=js_to_json)
+ formats = [{
+ 'url': s['file'],
+ 'ext': 'mp4',
+ } for s in params['sources']]
self._sort_formats(formats)
return {
'id': video_id,
'title': self._og_search_title(webpage).replace('Video: ', ''),
'description': self._og_search_description(webpage),
- 'thumbnail': self._og_search_thumbnail(webpage),
'formats': formats,
}