debian/NEWS: Add link to my webpage to give more details.

[youtubedl] / youtube_dl / extractor / daum.py

diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py
index a804e83bdc637fa79fa85c6e65f1eecaafe9e3a9..4876ecb4812710e2509eec8fc19f00dac60d2fde 100644 (file)
--- a/youtube_dl/extractor/daum.py
+++ b/youtube_dl/extractor/daum.py
@@ -1,6 +1,5 @@
 # encoding: utf-8
 import re
 # encoding: utf-8
 import re

-import xml.etree.ElementTree

 
 from .common import InfoExtractor
 from ..utils import (
 
 from .common import InfoExtractor
 from ..utils import (


@@ -10,7 +9,7 @@ from ..utils import (
 
 
 class DaumIE(InfoExtractor):
 
 
 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 = {
     IE_NAME = u'daum.net'
 
     _TEST = {


@@ -29,17 +28,16 @@ class DaumIE(InfoExtractor):
         video_id = mobj.group(1)
         canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
         webpage = self._download_webpage(canonical_url, video_id)
         video_id = mobj.group(1)
         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=(.+?)"',
+        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})
             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')
             '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')
             '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 = []
 
         self.to_screen(u'%s: Getting video urls' % video_id)
         formats = []


@@ -49,10 +47,9 @@ 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,
                 video_id, note=False)
                 '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,
             format_url = url_doc.find('result/url').text
             formats.append({
                 'url': format_url,


@@ -60,7 +57,7 @@ class DaumIE(InfoExtractor):
                 '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 +66,3 @@ 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