Register new version in the changelog.

[youtubedl] / youtube_dl / extractor / daum.py

diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py
index 6033cd94a1b251d66e7a3f80034bc58b79fa4b55..934da765ee700712721281a85dd955c28405001e 100644 (file)
--- a/youtube_dl/extractor/daum.py
+++ b/youtube_dl/extractor/daum.py
@@ -5,16 +5,16 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

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

     compat_urllib_parse,
 )
 
 
 class DaumIE(InfoExtractor):
     compat_urllib_parse,
 )
 
 
 class DaumIE(InfoExtractor):

-    _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/.*?clipid=(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:v/|.*?clipid=)(?P<id>[^?#&]+)'

     IE_NAME = 'daum.net'
 
     IE_NAME = 'daum.net'
 

-    _TEST = {
+    _TESTS = [{

         'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
         'info_dict': {
             'id': '52554690',
         'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
         'info_dict': {
             'id': '52554690',


@@ -24,15 +24,21 @@ class DaumIE(InfoExtractor):
             'upload_date': '20130831',
             'duration': 3868,
         },
             'upload_date': '20130831',
             'duration': 3868,
         },

-    }
+    }, {
+        'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz',
+        'only_matching': True,
+    }, {
+        'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
+        'only_matching': True,
+    }]

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

-        video_id = mobj.group(1)
+        video_id = mobj.group('id')

         canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
         webpage = self._download_webpage(canonical_url, video_id)
         full_id = self._search_regex(
         canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
         webpage = self._download_webpage(canonical_url, video_id)
         full_id = self._search_regex(

-            r'<iframe src="http://videofarm.daum.net/controller/video/viewer/Video.html\?.*?vid=(.+?)[&"]',
+            r'src=["\']http://videofarm\.daum\.net/controller/video/viewer/Video\.html\?.*?vid=(.+?)[&"\']',

             webpage, 'full id')
         query = compat_urllib_parse.urlencode({'vid': full_id})
         info = self._download_xml(
             webpage, 'full id')
         query = compat_urllib_parse.urlencode({'vid': full_id})
         info = self._download_xml(


@@ -42,7 +48,6 @@ class DaumIE(InfoExtractor):
             'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
             video_id, 'Downloading video formats info')
 
             'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
             video_id, 'Downloading video formats info')
 

-        self.to_screen(u'%s: Getting video urls' % video_id)

         formats = []
         for format_el in urls.findall('result/output_list/output_list'):
             profile = format_el.attrib['profile']
         formats = []
         for format_el in urls.findall('result/output_list/output_list'):
             profile = format_el.attrib['profile']


@@ -52,7 +57,7 @@ class DaumIE(InfoExtractor):
             })
             url_doc = self._download_xml(
                 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
             })
             url_doc = self._download_xml(
                 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,

-                video_id, note=False)
+                video_id, note='Downloading video data for %s format' % profile)

             format_url = url_doc.find('result/url').text
             formats.append({
                 'url': format_url,
             format_url = url_doc.find('result/url').text
             formats.append({
                 'url': format_url,