X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Finternetvideoarchive.py;h=c137f4a5d96eaf9da7685bdb33858e8f42d7b8fa;hb=5f6a1245ffa9276c1af59b0835afeef67e2fb5b1;hp=5986459d6dfdf7358b7d7a2e4bc139a579a01265;hpb=f219743e33a9a640bfc3845d74282774e51e1ad4;p=youtube-dl

diff --git a/youtube_dl/extractor/internetvideoarchive.py b/youtube_dl/extractor/internetvideoarchive.py
index 5986459d6..c137f4a5d 100644
--- a/youtube_dl/extractor/internetvideoarchive.py
+++ b/youtube_dl/extractor/internetvideoarchive.py
@@ -1,12 +1,12 @@
+from __future__ import unicode_literals
+
 import re
-import xml.etree.ElementTree
 
 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 = {
-        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': 156,
+        '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,
         },
     }
 
@@ -31,7 +32,7 @@ class InternetVideoArchiveIE(InfoExtractor):
     def _clean_query(query):
         NEEDED_ARGS = ['publishedid', 'customerid']
         query_dic = compat_urlparse.parse_qs(query)
-        cleaned_dic = dict((k,v[0]) for (k,v) in query_dic.items() if k in NEEDED_ARGS)
+        cleaned_dic = dict((k, v[0]) for (k, v) in query_dic.items() if k in NEEDED_ARGS)
         # Other player ids return m3u8 urls
         cleaned_dic['playerid'] = '247'
         cleaned_dic['videokbrate'] = '100000'
@@ -43,9 +44,8 @@ class InternetVideoArchiveIE(InfoExtractor):
         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
@@ -53,9 +53,8 @@ class InternetVideoArchiveIE(InfoExtractor):
         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):
@@ -66,15 +65,19 @@ class InternetVideoArchiveIE(InfoExtractor):
         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({
+                'format_id': format_id,
                 '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'])
 
-        info = {
+        self._sort_formats(formats)
+
+        return {
             'id': video_id,
             'title': item.find('title').text,
             'formats': formats,
@@ -82,6 +85,3 @@ class InternetVideoArchiveIE(InfoExtractor):
             'description': item.find('description').text,
             'duration': int(attr['duration']),
         }
-        # TODO: Remove when #980 has been merged
-        info.update(formats[-1])
-        return info