X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fdaum.py;h=9a94cf361170fee712fb6a5e11f139b8da7e3e81;hb=9f0ee2a3883ec6f6fdccba90085cb925aaa2f617;hp=9b4566999b3510a6728924a8115e9eb6fcb104e6;hpb=150f20828be552763dddce1c45b9a4e642cff599;p=youtube-dl

diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py
index 9b4566999..9a94cf361 100644
--- a/youtube_dl/extractor/daum.py
+++ b/youtube_dl/extractor/daum.py
@@ -1,45 +1,67 @@
 # encoding: utf-8
+
+from __future__ import unicode_literals
+
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
-    determine_ext,
 )
 
 
 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'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,
+        },
+    }, {
+        # Test for https://github.com/rg3/youtube-dl/issues/7949
+        'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=M1O35s8HPOo0&clipid=73147290',
+        'md5': 'c92d78bcee4424451f1667f275c1dc97',
+        'info_dict': {
+            'id': '73147290',
+            'ext': 'mp4',
+            'title': '싸이 - 나팔바지 [유희열의 스케치북] 299회 20151218',
+            'description': '싸이 - 나팔바지',
+            'upload_date': '20151219',
+            'duration': 232,
         },
-    }
+    }, {
+        '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)
-        video_id = mobj.group(1)
-        webpage = self._download_webpage(url, video_id)
-        full_id = self._search_regex(r'<link rel="video_src" href=".+?vid=(.+?)"',
-            webpage, u'full id')
+        video_id = mobj.group('id')
+        canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
+        webpage = self._download_webpage(canonical_url, video_id)
+        og_url = self._og_search_url(webpage, default=None) or self._search_regex(
+            r'<link[^>]+rel=(["\'])canonical\1[^>]+href=(["\'])(?P<url>.+?)\2',
+            webpage, 'canonical url', group='url')
+        full_id = self._search_regex(
+            r'tvpot\.daum\.net/v/([^/]+)', og_url, '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(
+            'Downloading video info')
+        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'))
+            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']
@@ -47,25 +69,21 @@ 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'))
+                video_id, note='Downloading video data for %s format' % profile)
             format_url = url_doc.find('result/url').text
             formats.append({
                 'url': format_url,
-                'ext': determine_ext(format_url),
                 '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