Prepate to upload

[youtubedl] / youtube_dl / extractor / common.py

diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index fcdd0fd14a85a12690031b409058d932a3d4e4db..59b9d373951331ef5c02bb6ed80d0f28bfaf4c8f 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
 
             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"""
     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:
 
     def _parse_xml(self, xml_string, video_id, transform_source=None, fatal=True):
         if transform_source:


@@ -1013,7 +1025,7 @@ class InfoExtractor(object):
             })
 
         for e in json_ld:
             })
 
         for e in json_ld:

-            if e.get('@context') == 'http://schema.org':
+            if isinstance(e.get('@context'), compat_str) and re.match(r'^https?://schema.org/?$', e.get('@context')):

                 item_type = e.get('@type')
                 if expected_type is not None and expected_type != item_type:
                     return info
                 item_type = e.get('@type')
                 if expected_type is not None and expected_type != item_type:
                     return info


@@ -1694,22 +1706,24 @@ class InfoExtractor(object):
             })
         return subtitles
 
             })
         return subtitles
 

-    def _extract_xspf_playlist(self, playlist_url, playlist_id, fatal=True):
+    def _extract_xspf_playlist(self, xspf_url, playlist_id, fatal=True):

         xspf = self._download_xml(
         xspf = self._download_xml(

-            playlist_url, playlist_id, 'Downloading xpsf playlist',
+            xspf_url, playlist_id, 'Downloading xpsf playlist',

             'Unable to download xspf manifest', fatal=fatal)
         if xspf is False:
             return []
             '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, xspf_url=xspf_url,
+            xspf_base_url=base_url(xspf_url))

 
 

-    def _parse_xspf(self, playlist, playlist_id):
+    def _parse_xspf(self, xspf_doc, playlist_id, xspf_url=None, xspf_base_url=None):

         NS_MAP = {
             'xspf': 'http://xspf.org/ns/0/',
             's1': 'http://static.streamone.nl/player/ns/0',
         }
 
         entries = []
         NS_MAP = {
             'xspf': 'http://xspf.org/ns/0/',
             's1': 'http://static.streamone.nl/player/ns/0',
         }
 
         entries = []

-        for track in playlist.findall(xpath_with_ns('./xspf:trackList/xspf:track', NS_MAP)):
+        for track in xspf_doc.findall(xpath_with_ns('./xspf:trackList/xspf:track', NS_MAP)):

             title = xpath_text(
                 track, xpath_with_ns('./xspf:title', NS_MAP), 'title', default=playlist_id)
             description = xpath_text(
             title = xpath_text(
                 track, xpath_with_ns('./xspf:title', NS_MAP), 'title', default=playlist_id)
             description = xpath_text(


@@ -1719,12 +1733,18 @@ class InfoExtractor(object):
             duration = float_or_none(
                 xpath_text(track, xpath_with_ns('./xspf:duration', NS_MAP), 'duration'), 1000)
 
             duration = float_or_none(
                 xpath_text(track, xpath_with_ns('./xspf:duration', NS_MAP), 'duration'), 1000)
 

-            formats = [{
-                '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))),
-            } for location in track.findall(xpath_with_ns('./xspf:location', NS_MAP))]
+            formats = []
+            for location in track.findall(xpath_with_ns('./xspf:location', NS_MAP)):
+                format_url = urljoin(xspf_base_url, location.text)
+                if not format_url:
+                    continue
+                formats.append({
+                    'url': format_url,
+                    'manifest_url': xspf_url,
+                    '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))),
+                })

             self._sort_formats(formats)
 
             entries.append({
             self._sort_formats(formats)
 
             entries.append({


@@ -1738,18 +1758,18 @@ class InfoExtractor(object):
         return entries
 
     def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, formats_dict={}):
         return entries
 
     def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, formats_dict={}):

-        res = self._download_webpage_handle(
+        res = self._download_xml_handle(

             mpd_url, video_id,
             note=note or 'Downloading MPD manifest',
             errnote=errnote or 'Failed to download MPD manifest',
             fatal=fatal)
         if res is False:
             return []
             mpd_url, video_id,
             note=note or 'Downloading MPD manifest',
             errnote=errnote or 'Failed to download MPD manifest',
             fatal=fatal)
         if res is False:
             return []

-        mpd, urlh = res
+        mpd_doc, urlh = res

         mpd_base_url = base_url(urlh.geturl())
 
         return self._parse_mpd_formats(
         mpd_base_url = base_url(urlh.geturl())
 
         return self._parse_mpd_formats(

-            compat_etree_fromstring(mpd.encode('utf-8')), mpd_id, mpd_base_url,
+            mpd_doc, mpd_id=mpd_id, mpd_base_url=mpd_base_url,

             formats_dict=formats_dict, mpd_url=mpd_url)
 
     def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', formats_dict={}, mpd_url=None):
             formats_dict=formats_dict, mpd_url=mpd_url)
 
     def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', formats_dict={}, mpd_url=None):


@@ -2023,17 +2043,16 @@ class InfoExtractor(object):
         return formats
 
     def _extract_ism_formats(self, ism_url, video_id, ism_id=None, note=None, errnote=None, fatal=True):
         return formats
 
     def _extract_ism_formats(self, ism_url, video_id, ism_id=None, note=None, errnote=None, fatal=True):

-        res = self._download_webpage_handle(
+        res = self._download_xml_handle(

             ism_url, video_id,
             note=note or 'Downloading ISM manifest',
             errnote=errnote or 'Failed to download ISM manifest',
             fatal=fatal)
         if res is False:
             return []
             ism_url, video_id,
             note=note or 'Downloading ISM manifest',
             errnote=errnote or 'Failed to download ISM manifest',
             fatal=fatal)
         if res is False:
             return []

-        ism, urlh = res
+        ism_doc, urlh = res

 
 

-        return self._parse_ism_formats(
-            compat_etree_fromstring(ism.encode('utf-8')), urlh.geturl(), ism_id)
+        return self._parse_ism_formats(ism_doc, urlh.geturl(), ism_id)

 
     def _parse_ism_formats(self, ism_doc, ism_url, ism_id=None):
         """
 
     def _parse_ism_formats(self, ism_doc, ism_url, ism_id=None):
         """


@@ -2131,8 +2150,8 @@ class InfoExtractor(object):
         return formats
 
     def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8', mpd_id=None, preference=None):
         return formats
 
     def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8', mpd_id=None, preference=None):

-        def absolute_url(video_url):
-            return compat_urlparse.urljoin(base_url, video_url)
+        def absolute_url(item_url):
+            return urljoin(base_url, item_url)

 
         def parse_content_type(content_type):
             if not content_type:
 
         def parse_content_type(content_type):
             if not content_type:


@@ -2189,7 +2208,7 @@ class InfoExtractor(object):
             if src:
                 _, formats = _media_formats(src, media_type)
                 media_info['formats'].extend(formats)
             if src:
                 _, formats = _media_formats(src, media_type)
                 media_info['formats'].extend(formats)

-            media_info['thumbnail'] = media_attributes.get('poster')
+            media_info['thumbnail'] = absolute_url(media_attributes.get('poster'))

             if media_content:
                 for source_tag in re.findall(r'<source[^>]+>', media_content):
                     source_attributes = extract_attributes(source_tag)
             if media_content:
                 for source_tag in re.findall(r'<source[^>]+>', media_content):
                     source_attributes = extract_attributes(source_tag)