[clipfish] extract mp4 video link

[youtube-dl] / youtube_dl / extractor / clipfish.py

diff --git a/youtube_dl/extractor/clipfish.py b/youtube_dl/extractor/clipfish.py
index 5f0b5602f8fb59a50a956b2a3366b304841060b9..09dfaac6022782c248df0ce80d7ddcfc49bc8288 100644 (file)
--- a/youtube_dl/extractor/clipfish.py
+++ b/youtube_dl/extractor/clipfish.py
@@ -1,51 +1,54 @@
-import re
-import time
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    js_to_json,
+    determine_ext,
+)
 
 
 class ClipfishIE(InfoExtractor):
-    IE_NAME = u'clipfish'
+    IE_NAME = '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,
+        'url': 'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/',
+        'md5': '79bc922f3e8a9097b3d68a93780fd475',
+        'info_dict': {
+            'id': '3966754',
+            'ext': 'mp4',
+            'title': 'FIFA 14 - E3 2013 Trailer',
+            'duration': 82,
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        video_info = self._parse_json(
+            js_to_json(self._html_search_regex('var videoObject = ({[^}]+?})', webpage, 'videoObject')),
+            video_id
+        )
+        info_url = self._parse_json(
+            js_to_json(self._html_search_regex('var globalFlashvars = ({[^}]+?})', webpage, 'globalFlashvars')),
+            video_id
+        )['data']
 
-        info_url = ('http://www.clipfish.de/devxml/videoinfo/%s?ts=%d' %
-                    (video_id, int(time.time())))
         doc = self._download_xml(
-            info_url, video_id, note=u'Downloading info page')
+            info_url, video_id, note='Downloading info page')
         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
+        duration = int_or_none(video_info['length'])
+        formats = [{'url': video_info['videourl']},{'url': video_url}]
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
             'title': title,
-            'url': video_url,
+            'formats': formats,
             'thumbnail': thumbnail,
             'duration': duration,
         }