X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fdaum.py;h=4876ecb4812710e2509eec8fc19f00dac60d2fde;hb=dabc127362ddfe88996e72b7e0d5cd2e4f239c98;hp=9b4566999b3510a6728924a8115e9eb6fcb104e6;hpb=150f20828be552763dddce1c45b9a4e642cff599;p=youtube-dl

diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py
index 9b4566999..4876ecb48 100644
--- a/youtube_dl/extractor/daum.py
+++ b/youtube_dl/extractor/daum.py
@@ -1,6 +1,5 @@
 # encoding: utf-8
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
@@ -10,7 +9,7 @@ from ..utils import (
 
 
 class DaumIE(InfoExtractor):
-    _VALID_URL = r'https?://tvpot\.daum\.net/.*?clipid=(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/.*?clipid=(?P<id>\d+)'
     IE_NAME = u'daum.net'
 
     _TEST = {
@@ -18,6 +17,7 @@ class DaumIE(InfoExtractor):
         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,
         },
@@ -26,18 +26,18 @@ class DaumIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group(1)
-        webpage = self._download_webpage(url, video_id)
-        full_id = self._search_regex(r'<link rel="video_src" href=".+?vid=(.+?)"',
+        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=(.+?)[&"]',
             webpage, u'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,
             u'Downloading video info')
-        urls_xml = self._download_webpage(
+        urls = self._download_xml(
             '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'))
 
         self.to_screen(u'%s: Getting video urls' % video_id)
         formats = []
@@ -47,10 +47,9 @@ class DaumIE(InfoExtractor):
                 '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,
                 video_id, note=False)
-            url_doc = xml.etree.ElementTree.fromstring(url_xml.encode('utf-8'))
             format_url = url_doc.find('result/url').text
             formats.append({
                 'url': format_url,
@@ -58,14 +57,12 @@ class DaumIE(InfoExtractor):
                 'format_id': profile,
             })
 
-        info = {
+        return {
             'id': video_id,
             'title': info.find('TITLE').text,
             'formats': formats,
             'thumbnail': self._og_search_thumbnail(webpage),
+            'description': info.find('CONTENTS').text,
             '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