Register new version in the changelog.

[youtubedl] / youtube_dl / extractor / internetvideoarchive.py

diff --git a/youtube_dl/extractor/internetvideoarchive.py b/youtube_dl/extractor/internetvideoarchive.py
index be8e05f539d7f64c301f7a63a488aedbf9d129cd..483cc6f9e62da3bc272ba66efc540b95c17116e7 100644 (file)
--- a/youtube_dl/extractor/internetvideoarchive.py
+++ b/youtube_dl/extractor/internetvideoarchive.py
@@ -1,12 +1,14 @@
+from __future__ import unicode_literals
+

 import re
 import re

-import xml.etree.ElementTree

 
 from .common import InfoExtractor
 
 from .common import InfoExtractor

-from ..utils import (
+from ..compat import (

     compat_urlparse,
     compat_urllib_parse,
     compat_urlparse,
     compat_urllib_parse,

+)
+from ..utils import (

     xpath_with_ns,
     xpath_with_ns,

-    determine_ext,

 )
 
 
 )
 
 


@@ -14,12 +16,13 @@ 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': 152,

         },
     }
 
         },
     }
 


@@ -31,7 +34,7 @@ class InternetVideoArchiveIE(InfoExtractor):
     def _clean_query(query):
         NEEDED_ARGS = ['publishedid', 'customerid']
         query_dic = compat_urlparse.parse_qs(query)
     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'
         # Other player ids return m3u8 urls
         cleaned_dic['playerid'] = '247'
         cleaned_dic['videokbrate'] = '100000'


@@ -43,36 +46,42 @@ 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
         # and http links (no m3u8 manifests)
         file_url = re.sub(r'(?<=\?)(.+)$',
         file_url = flashconfiguration.find('file').text
         file_url = file_url.replace('/playlist.aspx', '/mrssplaylist.aspx')
         # Replace some of the parameters in the query to get the best quality
         # and http links (no m3u8 manifests)
         file_url = re.sub(r'(?<=\?)(.+)$',

-            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'))
+                          lambda m: self._clean_query(m.group()),
+                          file_url)
+        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):

-            return xpath_with_ns(p,
-                {'media': 'http://search.yahoo.com/mrss/',
-                'jwplayer': 'http://developer.longtailvideo.com/trac/wiki/FlashFormats'})
+            return xpath_with_ns(
+                p,
+                {
+                    'media': 'http://search.yahoo.com/mrss/',
+                    'jwplayer': 'http://developer.longtailvideo.com/trac/wiki/FlashFormats',
+                }
+            )

         formats = []
         for content in item.findall(_bp('media:group/media:content')):
             attr = content.attrib
             f_url = attr['url']
         formats = []
         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,