[vulture] Remove the extractor
authorYen Chi Hsuan <yan12125@gmail.com>
Fri, 10 Jun 2016 05:13:59 +0000 (13:13 +0800)
committerYen Chi Hsuan <yan12125@gmail.com>
Fri, 10 Jun 2016 05:13:59 +0000 (13:13 +0800)
The first 10 URLs in google search "site:http://video.vulture.com/video"
is dead. I guess Vulture does not host videos on their own anymore.

youtube_dl/extractor/extractors.py
youtube_dl/extractor/vulture.py [deleted file]

index 0789e4a6ea965dcb3667e0bd64f893e7461aa954..38708294a363fdeaaa75784566b8407890a396cf 100644 (file)
@@ -958,7 +958,6 @@ from .vporn import VpornIE
 from .vrt import VRTIE
 from .vube import VubeIE
 from .vuclip import VuClipIE
-from .vulture import VultureIE
 from .walla import WallaIE
 from .washingtonpost import (
     WashingtonPostIE,
diff --git a/youtube_dl/extractor/vulture.py b/youtube_dl/extractor/vulture.py
deleted file mode 100644 (file)
index faa167e..0000000
+++ /dev/null
@@ -1,69 +0,0 @@
-from __future__ import unicode_literals
-
-import json
-import os.path
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    parse_iso8601,
-)
-
-
-class VultureIE(InfoExtractor):
-    IE_NAME = 'vulture.com'
-    _VALID_URL = r'https?://video\.vulture\.com/video/(?P<display_id>[^/]+)/'
-    _TEST = {
-        'url': 'http://video.vulture.com/video/Mindy-Kaling-s-Harvard-Speech/player?layout=compact&read_more=1',
-        'md5': '8d997845642a2b5152820f7257871bc8',
-        'info_dict': {
-            'id': '6GHRQL3RV7MSD1H4',
-            'ext': 'mp4',
-            'title': 'kaling-speech-2-MAGNIFY STANDARD CONTAINER REVISED',
-            'uploader_id': 'Sarah',
-            'thumbnail': 're:^http://.*\.jpg$',
-            'timestamp': 1401288564,
-            'upload_date': '20140528',
-            'description': 'Uplifting and witty, as predicted.',
-            'duration': 1015,
-        }
-    }
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        display_id = mobj.group('display_id')
-
-        webpage = self._download_webpage(url, display_id)
-        query_string = self._search_regex(
-            r"queryString\s*=\s*'([^']+)'", webpage, 'query string')
-        video_id = self._search_regex(
-            r'content=([^&]+)', query_string, 'video ID')
-        query_url = 'http://video.vulture.com/embed/player/container/1000/1000/?%s' % query_string
-
-        query_webpage = self._download_webpage(
-            query_url, display_id, note='Downloading query page')
-        params_json = self._search_regex(
-            r'(?sm)new MagnifyEmbeddablePlayer\({.*?contentItem:\s*(\{.*?\})\n?,\n',
-            query_webpage,
-            'player params')
-        params = json.loads(params_json)
-
-        upload_timestamp = parse_iso8601(params['posted'].replace(' ', 'T'))
-        uploader_id = params.get('user', {}).get('handle')
-
-        media_item = params['media_item']
-        title = os.path.splitext(media_item['title'])[0]
-        duration = int_or_none(media_item.get('duration_seconds'))
-
-        return {
-            'id': video_id,
-            'display_id': display_id,
-            'url': media_item['pipeline_xid'],
-            'title': title,
-            'timestamp': upload_timestamp,
-            'thumbnail': params.get('thumbnail_url'),
-            'uploader_id': uploader_id,
-            'description': params.get('description'),
-            'duration': duration,
-        }