Merge branch 'master' of https://github.com/rg3/youtube-dl

youtube_dl/extractor/zdf.py

@@ -85,6 +85,13 @@ class ZDFIE(InfoExtractor):
         uploader = xpath_text(doc, './/details/originChannelTitle', 'uploader')
         uploader_id = xpath_text(doc, './/details/originChannelId', 'uploader id')
         upload_date = unified_strdate(xpath_text(doc, './/details/airtime', 'upload date'))
+        subtitles = {}
+        captions_url = doc.find('.//caption/url')
+        if captions_url is not None:
+            subtitles['de'] = [{
+                'url': captions_url.text,
+                'ext': 'ttml',
+            }]
 
         def xml_to_thumbnails(fnode):
             thumbnails = []
@@ -190,6 +197,7 @@ class ZDFIE(InfoExtractor):
             'uploader_id': uploader_id,
             'upload_date': upload_date,
             'formats': formats,
+            'subtitles': subtitles,
         }
 
     def _real_extract(self, url):

youtube_dl/utils.py

@@ -2133,6 +2133,7 @@ def dfxp2srt(dfxp_data):
     _x = functools.partial(xpath_with_ns, ns_map={
         'ttml': 'http://www.w3.org/ns/ttml',
         'ttaf1': 'http://www.w3.org/2006/10/ttaf1',
+        'ttaf1_0604': 'http://www.w3.org/2006/04/ttaf1',
     })
 
     class TTMLPElementParser(object):
@@ -2159,7 +2160,7 @@ def dfxp2srt(dfxp_data):
 
     dfxp = compat_etree_fromstring(dfxp_data.encode('utf-8'))
     out = []
-    paras = dfxp.findall(_x('.//ttml:p')) or dfxp.findall(_x('.//ttaf1:p')) or dfxp.findall('.//p')
+    paras = dfxp.findall(_x('.//ttml:p')) or dfxp.findall(_x('.//ttaf1:p')) or dfxp.findall(_x('.//ttaf1_0604:p')) or dfxp.findall('.//p')
 
     if not paras:
         raise ValueError('Invalid dfxp/TTML subtitle')