Fix "invalid escape sequences" error on Python 3.6

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

diff --git a/youtube_dl/extractor/dumpert.py b/youtube_dl/extractor/dumpert.py
index 52d07deac008cccbe769d3e23641410c48e8d112..c9fc9b5a9df65cd8681ce8e0933473ea9658202d 100644 (file)
--- a/youtube_dl/extractor/dumpert.py
+++ b/youtube_dl/extractor/dumpert.py
@@ -2,46 +2,68 @@
 from __future__ import unicode_literals
 
 import base64
+import re
 
 from .common import InfoExtractor
+from ..utils import (
+    qualities,
+    sanitized_Request,
+)
 
 
 class DumpertIE(InfoExtractor):
-    _VALID_URL = (r'https?://(?:www\.)?dumpert\.nl/mediabase/'
-                  r'(?P<id>[0-9]+/[0-9a-zA-Z]+)/?.*')
-    _TEST = {
+    _VALID_URL = r'(?P<protocol>https?)://(?:www\.)?dumpert\.nl/(?:mediabase|embed)/(?P<id>[0-9]+/[0-9a-zA-Z]+)'
+    _TESTS = [{
         'url': 'http://www.dumpert.nl/mediabase/6646981/951bc60f/',
         'md5': '1b9318d7d5054e7dcb9dc7654f21d643',
         'info_dict': {
             'id': '6646981/951bc60f',
             'ext': 'mp4',
             'title': 'Ik heb nieuws voor je',
-            'description': 'Niet schrikken hoor'
+            'description': 'Niet schrikken hoor',
+            'thumbnail': r're:^https?://.*\.jpg$',
         }
-    }
+    }, {
+        'url': 'http://www.dumpert.nl/embed/6675421/dc440fe7/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        protocol = mobj.group('protocol')
 
-        title = self._html_search_meta('title', webpage)
-        description = self._html_search_meta('description', webpage)
+        url = '%s://www.dumpert.nl/mediabase/%s' % (protocol, video_id)
+        req = sanitized_Request(url)
+        req.add_header('Cookie', 'nsfw=1; cpc=10')
+        webpage = self._download_webpage(req, video_id)
 
-        files_base64 = self._html_search_regex(r'data-files="(.*?)"',
-                                               webpage,
-                                               'files')
-        files_json = base64.b64decode(files_base64).decode('iso-8859-1')
-        files = self._parse_json(files_json, video_id)
+        files_base64 = self._search_regex(
+            r'data-files="([^"]+)"', webpage, 'data files')
 
-        format_names = ['flv', 'mobile', 'tablet', '720p']
-        formats = [{'format_id': name,
-                    'url': files[name].replace(r'\/', '/')}
-                   for name in format_names
-                   if name in files]
+        files = self._parse_json(
+            base64.b64decode(files_base64.encode('utf-8')).decode('utf-8'),
+            video_id)
+
+        quality = qualities(['flv', 'mobile', 'tablet', '720p'])
+
+        formats = [{
+            'url': video_url,
+            'format_id': format_id,
+            'quality': quality(format_id),
+        } for format_id, video_url in files.items() if format_id != 'still']
+        self._sort_formats(formats)
+
+        title = self._html_search_meta(
+            'title', webpage) or self._og_search_title(webpage)
+        description = self._html_search_meta(
+            'description', webpage) or self._og_search_description(webpage)
+        thumbnail = files.get('still') or self._og_search_thumbnail(webpage)
 
         return {
             'id': video_id,
             'title': title,
             'description': description,
+            'thumbnail': thumbnail,
             'formats': formats
         }