Imported Upstream version 2014.11.21

[youtubedl] / youtube_dl / extractor / internetvideoarchive.py

diff --git a/youtube_dl/extractor/internetvideoarchive.py b/youtube_dl/extractor/internetvideoarchive.py
index be8e05f539d7f64c301f7a63a488aedbf9d129cd..53f9a5f7587bcf36d9d4a63f6cfa36d90496dd28 100644 (file)
--- a/youtube_dl/extractor/internetvideoarchive.py
+++ b/youtube_dl/extractor/internetvideoarchive.py
@@ -1,12 +1,12 @@
+from __future__ import unicode_literals
+

 import re
 import re

-import xml.etree.ElementTree

 
 from .common import InfoExtractor
 from ..utils import (
     compat_urlparse,
     compat_urllib_parse,
     xpath_with_ns,
 
 from .common import InfoExtractor
 from ..utils import (
     compat_urlparse,
     compat_urllib_parse,
     xpath_with_ns,

-    determine_ext,

 )
 
 
 )
 
 


@@ -14,12 +14,13 @@ class InternetVideoArchiveIE(InfoExtractor):
     _VALID_URL = r'https?://video\.internetvideoarchive\.net/flash/players/.*?\?.*?publishedid.*?'
 
     _TEST = {
     _VALID_URL = r'https?://video\.internetvideoarchive\.net/flash/players/.*?\?.*?publishedid.*?'
 
     _TEST = {

-        u'url': u'http://video.internetvideoarchive.net/flash/players/flashconfiguration.aspx?customerid=69249&publishedid=452693&playerid=247',
-        u'file': u'452693.mp4',
-        u'info_dict': {
-            u'title': u'SKYFALL',
-            u'description': u'In SKYFALL, Bond\'s loyalty to M is tested as her past comes back to haunt her. As MI6 comes under attack, 007 must track down and destroy the threat, no matter how personal the cost.',
-            u'duration': 153,
+        'url': 'http://video.internetvideoarchive.net/flash/players/flashconfiguration.aspx?customerid=69249&publishedid=452693&playerid=247',
+        'info_dict': {
+            'id': '452693',
+            'ext': 'mp4',
+            'title': 'SKYFALL',
+            'description': 'In SKYFALL, Bond\'s loyalty to M is tested as her past comes back to haunt her. As MI6 comes under attack, 007 must track down and destroy the threat, no matter how personal the cost.',
+            'duration': 149,

         },
     }
 
         },
     }
 


@@ -43,9 +44,8 @@ class InternetVideoArchiveIE(InfoExtractor):
         video_id = query_dic['publishedid'][0]
         url = self._build_url(query)
 
         video_id = query_dic['publishedid'][0]
         url = self._build_url(query)
 

-        flashconfiguration_xml = self._download_webpage(url, video_id,
-            u'Downloading flash configuration')
-        flashconfiguration = xml.etree.ElementTree.fromstring(flashconfiguration_xml.encode('utf-8'))
+        flashconfiguration = self._download_xml(url, video_id,
+            'Downloading flash configuration')

         file_url = flashconfiguration.find('file').text
         file_url = file_url.replace('/playlist.aspx', '/mrssplaylist.aspx')
         # Replace some of the parameters in the query to get the best quality
         file_url = flashconfiguration.find('file').text
         file_url = file_url.replace('/playlist.aspx', '/mrssplaylist.aspx')
         # Replace some of the parameters in the query to get the best quality


@@ -53,9 +53,8 @@ class InternetVideoArchiveIE(InfoExtractor):
         file_url = re.sub(r'(?<=\?)(.+)$',
             lambda m: self._clean_query(m.group()),
             file_url)
         file_url = re.sub(r'(?<=\?)(.+)$',
             lambda m: self._clean_query(m.group()),
             file_url)

-        info_xml = self._download_webpage(file_url, video_id,
-            u'Downloading video info')
-        info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
+        info = self._download_xml(file_url, video_id,
+            'Downloading video info')

         item = info.find('channel/item')
 
         def _bp(p):
         item = info.find('channel/item')
 
         def _bp(p):


@@ -66,13 +65,17 @@ class InternetVideoArchiveIE(InfoExtractor):
         for content in item.findall(_bp('media:group/media:content')):
             attr = content.attrib
             f_url = attr['url']
         for content in item.findall(_bp('media:group/media:content')):
             attr = content.attrib
             f_url = attr['url']

+            width = int(attr['width'])
+            bitrate = int(attr['bitrate'])
+            format_id = '%d-%dk' % (width, bitrate)

             formats.append({
             formats.append({

+                'format_id': format_id,

                 'url': f_url,
                 'url': f_url,

-                'ext': determine_ext(f_url),
-                'width': int(attr['width']),
-                'bitrate': int(attr['bitrate']),
+                'width': width,
+                'tbr': bitrate,

             })
             })

-        formats = sorted(formats, key=lambda f: f['bitrate'])
+
+        self._sort_formats(formats)

 
         return {
             'id': video_id,
 
         return {
             'id': video_id,