Fix "invalid escape sequences" error on Python 3.6

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

diff --git a/youtube_dl/extractor/fktv.py b/youtube_dl/extractor/fktv.py
index c2aa23aa28f7c257d697ee2567f3b64848dfbcb8..2958452f470bca7f7322fa9dcdccca66f525cee0 100644 (file)
--- a/youtube_dl/extractor/fktv.py
+++ b/youtube_dl/extractor/fktv.py
@@ -1,17 +1,16 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     clean_html,
     determine_ext,
+    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',
@@ -20,23 +19,33 @@ class FKTVIE(InfoExtractor):
             'id': '1',
             'ext': 'mp4',
             'title': 'Folge 1 vom 10. April 2007',
+            'thumbnail': r're:^https?://.*\.jpg$',
         },
     }
 
     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'))
-        matchs = re.search(r'(?s)<video[^>]*poster="([^"]+)"[^>]*>(.*?)</video>', webpage)
-        if matchs:
-            poster, sources = matchs.groups()
-            urls = re.findall(r'(?s)<source[^>]*src="([^"]+)"[^>]*>', sources)
-            if sources:
-                formats = [{'url': url, 'format_id': determine_ext(url)} for url in urls]
-                return {
-                    'id': episode,
-                    'title': title,
-                    'formats': formats,
-                    'thumbnail': poster,
-                }
+        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)
+
+        return {
+            'id': episode,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail,
+        }