[extractor/common] Add _download_xml_handle

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

diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index ff62b5cf3c122eb267007599532f96e7cb178717..a507785097a3e0e336f8dd5d912fe0c90fa4b613 100644 (file)
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -644,19 +644,31 @@ class InfoExtractor(object):
             content, _ = res
             return content
 
+    def _download_xml_handle(
+            self, url_or_request, video_id, note='Downloading XML',
+            errnote='Unable to download XML', transform_source=None,
+            fatal=True, encoding=None, data=None, headers={}, query={}):
+        """Return a tuple (xml as an xml.etree.ElementTree.Element, URL handle)"""
+        res = self._download_webpage_handle(
+            url_or_request, video_id, note, errnote, fatal=fatal,
+            encoding=encoding, data=data, headers=headers, query=query)
+        if res is False:
+            return res
+        xml_string, urlh = res
+        return self._parse_xml(
+            xml_string, video_id, transform_source=transform_source,
+            fatal=fatal), urlh
+
     def _download_xml(self, url_or_request, video_id,
                       note='Downloading XML', errnote='Unable to download XML',
                       transform_source=None, fatal=True, encoding=None,
                       data=None, headers={}, query={}):
         """Return the xml as an xml.etree.ElementTree.Element"""
-        xml_string = self._download_webpage(
-            url_or_request, video_id, note, errnote, fatal=fatal,
-            encoding=encoding, data=data, headers=headers, query=query)
-        if xml_string is False:
-            return xml_string
-        return self._parse_xml(
-            xml_string, video_id, transform_source=transform_source,
-            fatal=fatal)
+        res = self._download_xml_handle(
+            url_or_request, video_id, note=note, errnote=errnote,
+            transform_source=transform_source, fatal=fatal, encoding=encoding,
+            data=data, headers=headers, query=query)
+        return res if res is False else res[0]
 
     def _parse_xml(self, xml_string, video_id, transform_source=None, fatal=True):
         if transform_source:
@@ -1700,9 +1712,9 @@ class InfoExtractor(object):
             'Unable to download xspf manifest', fatal=fatal)
         if xspf is False:
             return []
-        return self._parse_xspf(xspf, playlist_id)
+        return self._parse_xspf(xspf, playlist_id, base_url(playlist_url))
 
-    def _parse_xspf(self, playlist, playlist_id):
+    def _parse_xspf(self, playlist, playlist_id, playlist_base_url=''):
         NS_MAP = {
             'xspf': 'http://xspf.org/ns/0/',
             's1': 'http://static.streamone.nl/player/ns/0',
@@ -1720,7 +1732,7 @@ class InfoExtractor(object):
                 xpath_text(track, xpath_with_ns('./xspf:duration', NS_MAP), 'duration'), 1000)
 
             formats = [{
-                'url': location.text,
+                'url': urljoin(playlist_base_url, location.text),
                 'format_id': location.get(xpath_with_ns('s1:label', NS_MAP)),
                 'width': int_or_none(location.get(xpath_with_ns('s1:width', NS_MAP))),
                 'height': int_or_none(location.get(xpath_with_ns('s1:height', NS_MAP))),
@@ -2353,7 +2365,10 @@ class InfoExtractor(object):
                 for track in tracks:
                     if not isinstance(track, dict):
                         continue
-                    if track.get('kind') != 'captions':
+                    track_kind = track.get('kind')
+                    if not track_kind or not isinstance(track_kind, compat_str):
+                        continue
+                    if track_kind.lower() not in ('captions', 'subtitles'):
                         continue
                     track_url = urljoin(base_url, track.get('file'))
                     if not track_url: