From: Philipp Hagemeister <phihag@phihag.de>
Date: Mon, 9 Jun 2014 21:06:25 +0000 (+0200)
Subject: [Vulture] Add support for vulture.com
X-Git-Url: http://git.oshgnacknak.de/?a=commitdiff_plain;h=826ec77fb2843357601e795e812fe04bfd6990d1;p=youtube-dl

[Vulture] Add support for vulture.com
---

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 15a42ce44..45cc479e2 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -332,6 +332,7 @@ from .viki import VikiIE
 from .vk import VKIE
 from .vube import VubeIE
 from .vuclip import VuClipIE
+from .vulture import VultureIE
 from .washingtonpost import WashingtonPostIE
 from .wat import WatIE
 from .wdr import (
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 34d55297c..3105b47ab 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -668,6 +668,14 @@ class GenericIE(InfoExtractor):
             url = unescapeHTML(mobj.group('url'))
             return self.url_result(url)
 
+        # Look for embedded vulture.com player
+        mobj = re.search(
+            r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
+            webpage)
+        if mobj is not None:
+            url = unescapeHTML(mobj.group('url'))
+            return self.url_result(url, ie='Vulture')
+
         # Start with something easy: JW Player in SWFObject
         found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
         if not found:
diff --git a/youtube_dl/extractor/vulture.py b/youtube_dl/extractor/vulture.py
new file mode 100644
index 000000000..1eb24a3d6
--- /dev/null
+++ b/youtube_dl/extractor/vulture.py
@@ -0,0 +1,69 @@
+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,
+        }