Merge tag 'upstream/2014.12.01'

[youtubedl] / youtube_dl / extractor / daum.py

diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py
index a804e83bdc637fa79fa85c6e65f1eecaafe9e3a9..45d66e2e663fa376cec8f4fc7931e84006ee30b9 100644 (file)
--- a/youtube_dl/extractor/daum.py
+++ b/youtube_dl/extractor/daum.py
@@ -1,47 +1,53 @@
 # encoding: utf-8
 # encoding: utf-8

+
+from __future__ import unicode_literals
+

 import re
 import re

-import xml.etree.ElementTree

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

-    determine_ext,

 )
 
 
 class DaumIE(InfoExtractor):
 )
 
 
 class DaumIE(InfoExtractor):

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

 
 

-    _TEST = {
-        u'url': u'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
-        u'file': u'52554690.mp4',
-        u'info_dict': {
-            u'title': u'DOTA 2GETHER 시즌2 6회 - 2부',
-            u'description': u'DOTA 2GETHER 시즌2 6회 - 2부',
-            u'upload_date': u'20130831',
-            u'duration': 3868,
+    _TESTS = [{
+        'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
+        'info_dict': {
+            'id': '52554690',
+            'ext': 'mp4',
+            'title': 'DOTA 2GETHER 시즌2 6회 - 2부',
+            'description': 'DOTA 2GETHER 시즌2 6회 - 2부',
+            '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)
         canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
         webpage = self._download_webpage(canonical_url, video_id)

-        full_id = self._search_regex(r'<link rel="video_src" href=".+?vid=(.+?)"',
-            webpage, u'full id')
+        full_id = self._search_regex(
+            r'<iframe src="http://videofarm.daum.net/controller/video/viewer/Video.html\?.*?vid=(.+?)[&"]',
+            webpage, 'full id')

         query = compat_urllib_parse.urlencode({'vid': full_id})
         query = compat_urllib_parse.urlencode({'vid': full_id})

-        info_xml = self._download_webpage(
+        info = self._download_xml(

             'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
             'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,

-            u'Downloading video info')
-        urls_xml = self._download_webpage(
+            'Downloading video info')
+        urls = self._download_xml(

             'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
             'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,

-            video_id, u'Downloading video formats info')
-        info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
-        urls = xml.etree.ElementTree.fromstring(urls_xml.encode('utf-8'))
+            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']


@@ -49,18 +55,16 @@ class DaumIE(InfoExtractor):
                 'vid': full_id,
                 'profile': profile,
             })
                 'vid': full_id,
                 'profile': profile,
             })

-            url_xml = self._download_webpage(
+            url_doc = self._download_xml(

                 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
                 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,

-                video_id, note=False)
-            url_doc = xml.etree.ElementTree.fromstring(url_xml.encode('utf-8'))
+                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,

-                'ext': determine_ext(format_url),

                 'format_id': profile,
             })
 
                 'format_id': profile,
             })
 

-        info = {
+        return {

             'id': video_id,
             'title': info.find('TITLE').text,
             'formats': formats,
             'id': video_id,
             'title': info.find('TITLE').text,
             'formats': formats,


@@ -69,6 +73,3 @@ class DaumIE(InfoExtractor):
             'duration': int(info.find('DURATION').text),
             'upload_date': info.find('REGDTTM').text[:8],
         }
             'duration': int(info.find('DURATION').text),
             'upload_date': info.find('REGDTTM').text[:8],
         }

-        # TODO: Remove when #980 has been merged
-        info.update(formats[-1])
-        return info