X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ffktv.py;h=a3a2915998dc1cc2fca8f5ccdf6cec6cac0d528b;hb=0f56bd2178d887adb2d5c61da44343d228eed504;hp=289cbb8c87a374d82f41f2d9840f57f6c4de63dd;hpb=577380396171ba096240bfb3101f8151e32b587a;p=youtube-dl

diff --git a/youtube_dl/extractor/fktv.py b/youtube_dl/extractor/fktv.py
index 289cbb8c8..a3a291599 100644
--- a/youtube_dl/extractor/fktv.py
+++ b/youtube_dl/extractor/fktv.py
@@ -1,18 +1,16 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     clean_html,
     determine_ext,
-    ExtractorError,
+    js_to_json,
 )
 
 
 class FKTVIE(InfoExtractor):
     IE_NAME = 'fernsehkritik.tv'
-    _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<id>[0-9]+)(?:/.*)?'
+    _VALID_URL = r'https?://(?:www\.)?fernsehkritik\.tv/folge-(?P<id>[0-9]+)(?:/.*)?'
 
     _TEST = {
         'url': 'http://fernsehkritik.tv/folge-1',
@@ -28,21 +26,26 @@ class FKTVIE(InfoExtractor):
     def _real_extract(self, url):
         episode = self._match_id(url)
 
-        webpage = self._download_webpage('http://fernsehkritik.tv/folge-%s/play' % episode, episode)
-        title = clean_html(self._html_search_regex('<h3>([^<]+)</h3>', webpage, 'title'))
-        matches = re.search(r'(?s)<video[^>]+(?:poster="([^"]+)")?[^>]*>(.*)</video>', webpage)
-        if matches is None:
-            raise ExtractorError('Unable to extract the video')
-
-        poster, sources = matches.groups()
-        if poster is None:
-            self.report_warning('unable to extract thumbnail')
+        webpage = self._download_webpage(
+            'http://fernsehkritik.tv/folge-%s/play' % episode, episode)
+        title = clean_html(self._html_search_regex(
+            '<h3>([^<]+)</h3>', webpage, 'title'))
+        thumbnail = self._search_regex(r'POSTER\s*=\s*"([^"]+)', webpage, 'thumbnail', fatal=False)
+        sources = self._parse_json(self._search_regex(r'(?s)MEDIA\s*=\s*(\[.+?\]);', webpage, 'media'), episode, js_to_json)
+
+        formats = []
+        for source in sources:
+            furl = source.get('src')
+            if furl:
+                formats.append({
+                    'url': furl,
+                    'format_id': determine_ext(furl),
+                })
+        self._sort_formats(formats)
 
-        urls = re.findall(r'<source[^>]+src="([^"]+)"', sources)
-        formats = [{'url': url, 'format_id': determine_ext(url)} for url in urls]
         return {
             'id': episode,
             'title': title,
             'formats': formats,
-            'thumbnail': poster,
+            'thumbnail': thumbnail,
         }