Merge pull request #3927 from qrtt1/master

[youtube-dl] / youtube_dl / extractor / tvp.py

diff --git a/youtube_dl/extractor/tvp.py b/youtube_dl/extractor/tvp.py
index 63fb57bbe453749b065fcff1b62292df3b0c8ec0..a645800057fc6dc88850885cba7737243c95574e 100644 (file)
--- a/youtube_dl/extractor/tvp.py
+++ b/youtube_dl/extractor/tvp.py
@@ -1,60 +1,37 @@
-# encoding: utf-8
-import re
-import json
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import (
-    determine_ext,
-    ExtractorError,
-    RegexNotFoundError,
-)
+
 
 class TvpIE(InfoExtractor):
-    IE_NAME = u'tvp.pl'
+    IE_NAME = 'tvp.pl'
     _VALID_URL = r'https?://www\.tvp\.pl/.*?wideo/(?P<date>\d+)/(?P<id>\d+)'
-    _INFO_URL = 'http://www.tvp.pl/pub/stat/videofileinfo?video_id=%s'
-
 
     _TEST = {
-        u'url': u'http://www.tvp.pl/warszawa/magazyny/campusnews/wideo/31102013/12878238',
-        u'file': u'31.10.2013-12878238.wmv',
-        u'info_dict': {
-            u'title': u'31.10.2013',
-            u'description': u'31.10.2013',
+        'url': 'http://www.tvp.pl/warszawa/magazyny/campusnews/wideo/31102013/12878238',
+        'md5': '148408967a6a468953c0a75cbdaf0d7a',
+        'info_dict': {
+            'id': '12878238',
+            'ext': 'wmv',
+            'title': '31.10.2013 - Odcinek 2',
+            'description': '31.10.2013 - Odcinek 2',
         },
+        'skip': 'Download has to use same server IP as extraction. Therefore, a good (load-balancing) DNS resolver will make the download fail.'
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        webpage = self._download_webpage(url, video_id, "Downloading video webpage")
-        json_params = self._download_webpage(self._INFO_URL % video_id, video_id, "Downloading video metadata")
-
-        try:
-            params = json.loads(json_params)
-        except:
-            raise ExtractorError(u'Invalid JSON')
-
-        self.report_extraction(video_id)
-        try:
-            video_url = params['video_url']
-        except KeyError:
-            raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
-
-        try:
-            title = self._og_search_title(webpage)
-        except RegexNotFoundError:
-            title = video_id
-        info = {
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        json_url = 'http://www.tvp.pl/pub/stat/videofileinfo?video_id=%s' % video_id
+        params = self._download_json(
+            json_url, video_id, "Downloading video metadata")
+        video_url = params['video_url']
+
+        return {
             'id': video_id,
-            'title': title,
+            'title': self._og_search_title(webpage),
             'ext': 'wmv',
             'url': video_url,
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
         }
-        try:
-            info['description'] = self._og_search_description(webpage)
-            info['thumbnail'] = self._og_search_thumbnail(webpage)
-        except RegexNotFoundError:
-            pass
-
-        return info