Imported Upstream version 2015.07.21

[youtubedl] / youtube_dl / extractor / radiofrance.py

diff --git a/youtube_dl/extractor/radiofrance.py b/youtube_dl/extractor/radiofrance.py
index 34652f6c11ca9668bce89cd4c908d0c363221218..09352ed8250819518be78e2d5cf8bb97108913e0 100644 (file)
--- a/youtube_dl/extractor/radiofrance.py
+++ b/youtube_dl/extractor/radiofrance.py
@@ -1,4 +1,6 @@
 # coding: utf-8
 # coding: utf-8

+from __future__ import unicode_literals
+

 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor


@@ -6,16 +8,17 @@ from .common import InfoExtractor
 
 class RadioFranceIE(InfoExtractor):
     _VALID_URL = r'^https?://maison\.radiofrance\.fr/radiovisions/(?P<id>[^?#]+)'
 
 class RadioFranceIE(InfoExtractor):
     _VALID_URL = r'^https?://maison\.radiofrance\.fr/radiovisions/(?P<id>[^?#]+)'

-    IE_NAME = u'radiofrance'
+    IE_NAME = 'radiofrance'

 
     _TEST = {
 
     _TEST = {

-        u'url': u'http://maison.radiofrance.fr/radiovisions/one-one',
-        u'file': u'one-one.ogg',
-        u'md5': u'bdbb28ace95ed0e04faab32ba3160daf',
-        u'info_dict': {
-            u"title": u"One to one",
-            u"description": u"Plutôt que d'imaginer la radio de demain comme technologie ou comme création de contenu, je veux montrer que quelles que soient ses évolutions, j'ai l'intime conviction que la radio continuera d'être un grand média de proximité pour les auditeurs.",
-            u"uploader": u"Thomas Hercouët",
+        'url': 'http://maison.radiofrance.fr/radiovisions/one-one',
+        'md5': 'bdbb28ace95ed0e04faab32ba3160daf',
+        'info_dict': {
+            'id': 'one-one',
+            'ext': 'ogg',
+            "title": "One to one",
+            "description": "Plutôt que d'imaginer la radio de demain comme technologie ou comme création de contenu, je veux montrer que quelles que soient ses évolutions, j'ai l'intime conviction que la radio continuera d'être un grand média de proximité pour les auditeurs.",
+            "uploader": "Thomas Hercouët",

         },
     }
 
         },
     }
 


@@ -24,27 +27,28 @@ class RadioFranceIE(InfoExtractor):
         video_id = m.group('id')
 
         webpage = self._download_webpage(url, video_id)
         video_id = m.group('id')
 
         webpage = self._download_webpage(url, video_id)

-        title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, u'title')
+        title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')

         description = self._html_search_regex(
             r'<div class="bloc_page_wrapper"><div class="text">(.*?)</div>',
         description = self._html_search_regex(
             r'<div class="bloc_page_wrapper"><div class="text">(.*?)</div>',

-            webpage, u'description', fatal=False)
+            webpage, 'description', fatal=False)

         uploader = self._html_search_regex(
             r'<div class="credit">&nbsp;&nbsp;&copy;&nbsp;(.*?)</div>',
         uploader = self._html_search_regex(
             r'<div class="credit">&nbsp;&nbsp;&copy;&nbsp;(.*?)</div>',

-            webpage, u'uploader', fatal=False)
+            webpage, 'uploader', fatal=False)

 
         formats_str = self._html_search_regex(
             r'class="jp-jplayer[^"]*" data-source="([^"]+)">',
 
         formats_str = self._html_search_regex(
             r'class="jp-jplayer[^"]*" data-source="([^"]+)">',

-            webpage, u'audio URLs')
+            webpage, 'audio URLs')

         formats = [
             {
                 'format_id': fm[0],
                 'url': fm[1],
                 'vcodec': 'none',
         formats = [
             {
                 'format_id': fm[0],
                 'url': fm[1],
                 'vcodec': 'none',

+                'preference': i,

             }
             }

-            for fm in
-            re.findall(r"([a-z0-9]+)\s*:\s*'([^']+)'", formats_str)
+            for i, fm in
+            enumerate(re.findall(r"([a-z0-9]+)\s*:\s*'([^']+)'", formats_str))

         ]
         ]

-        # No sorting, we don't know any more about these formats
+        self._sort_formats(formats)

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