Imported Debian patch 2015.11.27.1-1.1

[youtubedl] / youtube_dl / extractor / zdf.py

diff --git a/youtube_dl/extractor/zdf.py b/youtube_dl/extractor/zdf.py
index 98f15177bd6665bd1c6b96a071d59d4b67e5d918..a795f56b37bbd710c895b0e255342057a5aa354f 100644 (file)
--- a/youtube_dl/extractor/zdf.py
+++ b/youtube_dl/extractor/zdf.py
@@ -9,6 +9,7 @@ from ..utils import (
     int_or_none,
     unified_strdate,
     OnDemandPagedList,
     int_or_none,
     unified_strdate,
     OnDemandPagedList,

+    xpath_text,

 )
 
 
 )
 
 


@@ -19,13 +20,11 @@ def extract_from_xml_url(ie, video_id, xml_url):
         errnote='Failed to download video info')
 
     title = doc.find('.//information/title').text
         errnote='Failed to download video info')
 
     title = doc.find('.//information/title').text

-    description = doc.find('.//information/detail').text
-    duration = int(doc.find('.//details/lengthSec').text)
-    uploader_node = doc.find('.//details/originChannelTitle')
-    uploader = None if uploader_node is None else uploader_node.text
-    uploader_id_node = doc.find('.//details/originChannelId')
-    uploader_id = None if uploader_id_node is None else uploader_id_node.text
-    upload_date = unified_strdate(doc.find('.//details/airtime').text)
+    description = xpath_text(doc, './/information/detail', 'description')
+    duration = int_or_none(xpath_text(doc, './/details/lengthSec', 'duration'))
+    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'))

 
     def xml_to_format(fnode):
         video_url = fnode.find('url').text
 
     def xml_to_format(fnode):
         video_url = fnode.find('url').text


@@ -40,15 +39,14 @@ def extract_from_xml_url(ie, video_id, xml_url):
         ext = format_m.group('container')
         proto = format_m.group('proto').lower()
 
         ext = format_m.group('container')
         proto = format_m.group('proto').lower()
 

-        quality = fnode.find('./quality').text
-        abr = int(fnode.find('./audioBitrate').text) // 1000
-        vbr_node = fnode.find('./videoBitrate')
-        vbr = None if vbr_node is None else int(vbr_node.text) // 1000
+        quality = xpath_text(fnode, './quality', 'quality')
+        abr = int_or_none(xpath_text(fnode, './audioBitrate', 'abr'), 1000)
+        vbr = int_or_none(xpath_text(fnode, './videoBitrate', 'vbr'), 1000)

 
 

-        width_node = fnode.find('./width')
-        width = None if width_node is None else int_or_none(width_node.text)
-        height_node = fnode.find('./height')
-        height = None if height_node is None else int_or_none(height_node.text)
+        width = int_or_none(xpath_text(fnode, './width', 'width'))
+        height = int_or_none(xpath_text(fnode, './height', 'height'))
+
+        filesize = int_or_none(xpath_text(fnode, './filesize', 'filesize'))

 
         format_note = ''
         if not format_note:
 
         format_note = ''
         if not format_note:


@@ -64,12 +62,31 @@ def extract_from_xml_url(ie, video_id, xml_url):
             'vbr': vbr,
             'width': width,
             'height': height,
             'vbr': vbr,
             'width': width,
             'height': height,

-            'filesize': int_or_none(fnode.find('./filesize').text),
+            'filesize': filesize,

             'format_note': format_note,
             'protocol': proto,
             '_available': is_available,
         }
 
             'format_note': format_note,
             'protocol': proto,
             '_available': is_available,
         }
 

+    def xml_to_thumbnails(fnode):
+        thumbnails = []
+        for node in fnode:
+            thumbnail_url = node.text
+            if not thumbnail_url:
+                continue
+            thumbnail = {
+                'url': thumbnail_url,
+            }
+            if 'key' in node.attrib:
+                m = re.match('^([0-9]+)x([0-9]+)$', node.attrib['key'])
+                if m:
+                    thumbnail['width'] = int(m.group(1))
+                    thumbnail['height'] = int(m.group(2))
+            thumbnails.append(thumbnail)
+        return thumbnails
+
+    thumbnails = xml_to_thumbnails(doc.findall('.//teaserimages/teaserimage'))
+

     format_nodes = doc.findall('.//formitaeten/formitaet')
     formats = list(filter(
         lambda f: f['_available'],
     format_nodes = doc.findall('.//formitaeten/formitaet')
     formats = list(filter(
         lambda f: f['_available'],


@@ -81,6 +98,7 @@ def extract_from_xml_url(ie, video_id, xml_url):
         'title': title,
         'description': description,
         'duration': duration,
         'title': title,
         'description': description,
         'duration': duration,

+        'thumbnails': thumbnails,

         'uploader': uploader,
         'uploader_id': uploader_id,
         'upload_date': upload_date,
         'uploader': uploader,
         'uploader_id': uploader_id,
         'upload_date': upload_date,