aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2013-11-24 07:51:44 +0100
committerPhilipp Hagemeister <phihag@phihag.de>2013-11-24 07:51:44 +0100
commit0c7c19d6bc55a624532f2426d080aea51962cfe0 (patch)
tree3c826e18aa75534d471a8d7a47fa4bad1e31707b
parenteaaafc59c2f8ffaee4df06092a57f65eec1b6eaa (diff)
[clipfish] Add extractor (Fixes #1760)
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/clipfish.py53
2 files changed, 54 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 867734fa2..4c280fa5e 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -20,6 +20,7 @@ from .c56 import C56IE
from .canalplus import CanalplusIE
from .canalc2 import Canalc2IE
from .cinemassacre import CinemassacreIE
+from .clipfish import ClipfishIE
from .cnn import CNNIE
from .collegehumor import CollegeHumorIE
from .comedycentral import ComedyCentralIE
diff --git a/youtube_dl/extractor/clipfish.py b/youtube_dl/extractor/clipfish.py
new file mode 100644
index 000000000..95449da3c
--- /dev/null
+++ b/youtube_dl/extractor/clipfish.py
@@ -0,0 +1,53 @@
+import re
+import time
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+
+
+class ClipfishIE(InfoExtractor):
+ IE_NAME = u'clipfish'
+
+ _VALID_URL = r'^https?://(?:www\.)?clipfish\.de/.*?/video/(?P<id>[0-9]+)/'
+ _TEST = {
+ u'url': u'http://www.clipfish.de/special/supertalent/video/4028320/supertalent-2013-ivana-opacak-singt-nobodys-perfect/',
+ u'file': u'4028320.f4v',
+ u'md5': u'5e38bda8c329fbfb42be0386a3f5a382',
+ u'info_dict': {
+ u'title': u'Supertalent 2013: Ivana Opacak singt Nobody\'s Perfect',
+ u'duration': 399,
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group(1)
+
+ info_url = ('http://www.clipfish.de/devxml/videoinfo/%s?ts=%d' %
+ (video_id, int(time.time())))
+ info_xml = self._download_webpage(
+ info_url, video_id, note=u'Downloading info page')
+ doc = xml.etree.ElementTree.fromstring(info_xml)
+ title = doc.find('title').text
+ video_url = doc.find('filename').text
+ thumbnail = doc.find('imageurl').text
+ duration_str = doc.find('duration').text
+ m = re.match(
+ r'^(?P<hours>[0-9]+):(?P<minutes>[0-9]{2}):(?P<seconds>[0-9]{2}):(?P<ms>[0-9]*)$',
+ duration_str)
+ if m:
+ duration = (
+ (int(m.group('hours')) * 60 * 60) +
+ (int(m.group('minutes')) * 60) +
+ (int(m.group('seconds')))
+ )
+ else:
+ duration = None
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'url': video_url,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ }