Merge pull request #7045 from remitamine/ign

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

diff --git a/youtube_dl/extractor/clipfish.py b/youtube_dl/extractor/clipfish.py
index 09dfaac6022782c248df0ce80d7ddcfc49bc8288..3a47f6fa4e1cdf734670ff64abb9aa4c02c94a6e 100644 (file)
--- a/youtube_dl/extractor/clipfish.py
+++ b/youtube_dl/extractor/clipfish.py
@@ -2,17 +2,13 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
-    ExtractorError,
     int_or_none,
-    js_to_json,
-    determine_ext,
+    unified_strdate,
 )
 
 
 class ClipfishIE(InfoExtractor):
-    IE_NAME = 'clipfish'
-
-    _VALID_URL = r'^https?://(?:www\.)?clipfish\.de/.*?/video/(?P<id>[0-9]+)/'
+    _VALID_URL = r'https?://(?:www\.)?clipfish\.de/(?:[^/]+/)+video/(?P<id>[0-9]+)'
     _TEST = {
         'url': 'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/',
         'md5': '79bc922f3e8a9097b3d68a93780fd475',
@@ -20,35 +16,47 @@ class ClipfishIE(InfoExtractor):
             'id': '3966754',
             'ext': 'mp4',
             'title': 'FIFA 14 - E3 2013 Trailer',
+            'description': 'Video zu FIFA 14: E3 2013 Trailer',
+            'upload_date': '20130611',
             'duration': 82,
+            'view_count': int,
         }
     }
 
     def _real_extract(self, url):
         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']
-
-        doc = self._download_xml(
-            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 = int_or_none(video_info['length'])
-        formats = [{'url': video_info['videourl']},{'url': video_url}]
-        self._sort_formats(formats)
+
+        video_info = self._download_json(
+            'http://www.clipfish.de/devapi/id/%s?format=json&apikey=hbbtv' % video_id,
+            video_id)['items'][0]
+
+        formats = []
+
+        m3u8_url = video_info.get('media_videourl_hls')
+        if m3u8_url:
+            formats.append({
+                'url': m3u8_url.replace('de.hls.fra.clipfish.de', 'hls.fra.clipfish.de'),
+                'ext': 'mp4',
+                'format_id': 'hls',
+            })
+
+        mp4_url = video_info.get('media_videourl')
+        if mp4_url:
+            formats.append({
+                'url': mp4_url,
+                'format_id': 'mp4',
+                'width': int_or_none(video_info.get('width')),
+                'height': int_or_none(video_info.get('height')),
+                'tbr': int_or_none(video_info.get('bitrate')),
+            })
 
         return {
             'id': video_id,
-            'title': title,
+            'title': video_info['title'],
+            'description': video_info.get('descr'),
             'formats': formats,
-            'thumbnail': thumbnail,
-            'duration': duration,
+            'thumbnail': video_info.get('media_content_thumbnail_large') or video_info.get('media_thumbnail'),
+            'duration': int_or_none(video_info.get('media_length')),
+            'upload_date': unified_strdate(video_info.get('pubDate')),
+            'view_count': int_or_none(video_info.get('media_views'))
         }