Fix "invalid escape sequences" error on Python 3.6

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

diff --git a/youtube_dl/extractor/mdr.py b/youtube_dl/extractor/mdr.py
index a566c6a2c333a8c9b7ba62d094cb659f838761ea..6e4290aadd6e0d3543d5b48d5df39577032437e2 100644 (file)
--- a/youtube_dl/extractor/mdr.py
+++ b/youtube_dl/extractor/mdr.py
@@ -14,10 +14,10 @@ from ..utils import (
 
 class MDRIE(InfoExtractor):
     IE_DESC = 'MDR.DE and KiKA'
-    _VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z]+(?P<id>\d+)(?:_.+?)?\.html'
+    _VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z]+-?(?P<id>\d+)(?:_.+?)?\.html'
 
     _TESTS = [{
-        # MDR regularily deletes its videos
+        # MDR regularly deletes its videos
         'url': 'http://www.mdr.de/fakt/video189002.html',
         'only_matching': True,
     }, {
@@ -49,8 +49,8 @@ class MDRIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Beutolomäus und der geheime Weihnachtswunsch',
             'description': 'md5:b69d32d7b2c55cbe86945ab309d39bbd',
-            'timestamp': 1419047100,
-            'upload_date': '20141220',
+            'timestamp': 1450950000,
+            'upload_date': '20151224',
             'duration': 4628,
             'uploader': 'KIKA',
         },
@@ -60,6 +60,9 @@ class MDRIE(InfoExtractor):
     }, {
         'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/einzelsendung2534.html',
         'only_matching': True,
+    }, {
+        'url': 'http://www.mdr.de/mediathek/mdr-videos/a/video-1334.html',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -68,8 +71,8 @@ class MDRIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         data_url = self._search_regex(
-            r'dataURL\s*:\s*(["\'])(?P<url>/.+/(?:video|audio)[0-9]+-avCustom\.xml)\1',
-            webpage, 'data url', group='url')
+            r'(?:dataURL|playerXml(?:["\'])?)\s*:\s*(["\'])(?P<url>.+/(?:video|audio)-?[0-9]+-avCustom\.xml)\1',
+            webpage, 'data url', group='url').replace(r'\/', '/')
 
         doc = self._download_xml(
             compat_urlparse.urljoin(url, data_url), video_id)
@@ -96,8 +99,6 @@ class MDRIE(InfoExtractor):
                 vbr = int_or_none(xpath_text(asset, './bitrateVideo', 'vbr'), 1000)
                 abr = int_or_none(xpath_text(asset, './bitrateAudio', 'abr'), 1000)
 
-                url_formats = []
-
                 ext = determine_ext(url_el.text)
                 if ext == 'm3u8':
                     url_formats = self._extract_m3u8_formats(
@@ -130,7 +131,10 @@ class MDRIE(InfoExtractor):
                             'height': height,
                         })
 
-                    url_formats.append(f)
+                    url_formats = [f]
+
+                if not url_formats:
+                    continue
 
                 if not vbr:
                     for f in url_formats:
@@ -142,8 +146,8 @@ class MDRIE(InfoExtractor):
                             'vcodec': 'none',
                         })
 
-                if url_formats:
-                    formats.extend(url_formats)
+                formats.extend(url_formats)
+
         self._sort_formats(formats)
 
         description = xpath_text(doc, './broadcast/broadcastDescription', 'description')