New upstream version 2019.07.02

[youtubedl] / youtube_dl / extractor / naver.py

diff --git a/youtube_dl/extractor/naver.py b/youtube_dl/extractor/naver.py
index 055070ff54fd8990c2e58ab1d6df037b19f3a029..bb3d944133d6a1e2685779b86a7565ad9b0985f0 100644 (file)
--- a/youtube_dl/extractor/naver.py
+++ b/youtube_dl/extractor/naver.py
@@ -1,8 +1,6 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
 # coding: utf-8
 from __future__ import unicode_literals
 

-import re
-

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


@@ -12,10 +10,10 @@ from ..utils import (
 
 
 class NaverIE(InfoExtractor):
 
 
 class NaverIE(InfoExtractor):

-    _VALID_URL = r'https?://(?:m\.)?tvcast\.naver\.com/v/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:m\.)?tv(?:cast)?\.naver\.com/v/(?P<id>\d+)'

 
     _TESTS = [{
 
     _TESTS = [{

-        'url': 'http://tvcast.naver.com/v/81652',
+        'url': 'http://tv.naver.com/v/81652',

         'info_dict': {
             'id': '81652',
             'ext': 'mp4',
         'info_dict': {
             'id': '81652',
             'ext': 'mp4',


@@ -24,7 +22,7 @@ class NaverIE(InfoExtractor):
             'upload_date': '20130903',
         },
     }, {
             'upload_date': '20130903',
         },
     }, {

-        'url': 'http://tvcast.naver.com/v/395837',
+        'url': 'http://tv.naver.com/v/395837',

         'md5': '638ed4c12012c458fefcddfd01f173cd',
         'info_dict': {
             'id': '395837',
         'md5': '638ed4c12012c458fefcddfd01f173cd',
         'info_dict': {
             'id': '395837',


@@ -34,15 +32,23 @@ class NaverIE(InfoExtractor):
             'upload_date': '20150519',
         },
         'skip': 'Georestricted',
             'upload_date': '20150519',
         },
         'skip': 'Georestricted',

+    }, {
+        'url': 'http://tvcast.naver.com/v/81652',
+        'only_matching': True,

     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 

-        m_id = re.search(r'var rmcPlayer = new nhn.rmcnmv.RMCVideoPlayer\("(.+?)", "(.+?)"',
-                         webpage)
-        if m_id is None:
+        vid = self._search_regex(
+            r'videoId["\']\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage,
+            'video id', fatal=None, group='value')
+        in_key = self._search_regex(
+            r'inKey["\']\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage,
+            'key', default=None, group='value')
+
+        if not vid or not in_key:

             error = self._html_search_regex(
                 r'(?s)<div class="(?:nation_error|nation_box|error_box)">\s*(?:<!--.*?-->)?\s*<p class="[^"]+">(?P<msg>.+?)</p>\s*</div>',
                 webpage, 'error', default=None)
             error = self._html_search_regex(
                 r'(?s)<div class="(?:nation_error|nation_box|error_box)">\s*(?:<!--.*?-->)?\s*<p class="[^"]+">(?P<msg>.+?)</p>\s*</div>',
                 webpage, 'error', default=None)


@@ -50,9 +56,9 @@ class NaverIE(InfoExtractor):
                 raise ExtractorError(error, expected=True)
             raise ExtractorError('couldn\'t extract vid and key')
         video_data = self._download_json(
                 raise ExtractorError(error, expected=True)
             raise ExtractorError('couldn\'t extract vid and key')
         video_data = self._download_json(

-            'http://play.rmcnmv.naver.com/vod/play/v2.0/' + m_id.group(1),
+            'http://play.rmcnmv.naver.com/vod/play/v2.0/' + vid,

             video_id, query={
             video_id, query={

-                'key': m_id.group(2),
+                'key': in_key,

             })
         meta = video_data['meta']
         title = meta['subject']
             })
         meta = video_data['meta']
         title = meta['subject']