Imported Upstream version 2014.07.15

[youtubedl] / youtube_dl / extractor / ninegag.py

diff --git a/youtube_dl/extractor/ninegag.py b/youtube_dl/extractor/ninegag.py
index ea986c00e7b1170e883978b82cfde8f0e22d8dd0..33daa0dec327dea3f691f5dccab5b6b312d79e4f 100644 (file)
--- a/youtube_dl/extractor/ninegag.py
+++ b/youtube_dl/extractor/ninegag.py
@@ -1,43 +1,68 @@
-import json
+from __future__ import unicode_literals
+

 import re
 import re

+import json

 
 from .common import InfoExtractor
 
 from .common import InfoExtractor

+from ..utils import str_to_int

 
 
 class NineGagIE(InfoExtractor):
     IE_NAME = '9gag'
 
 
 class NineGagIE(InfoExtractor):
     IE_NAME = '9gag'

-    _VALID_URL = r'^https?://(?:www\.)?9gag\.tv/v/(?P<id>[0-9]+)'
-
-    _TEST = {
-        u"url": u"http://9gag.tv/v/1912",
-        u"file": u"1912.mp4",
-        u"info_dict": {
-            u"description": u"This 3-minute video will make you smile and then make you feel untalented and insignificant. Anyway, you should share this awesomeness. (Thanks, Dino!)",
-            u"title": u"\"People Are Awesome 2013\" Is Absolutely Awesome"
+    _VALID_URL = r'''(?x)^https?://(?:www\.)?9gag\.tv/
+        (?:
+            v/(?P<numid>[0-9]+)|
+            p/(?P<id>[a-zA-Z0-9]+)/(?P<display_id>[^?#/]+)
+        )
+    '''
+
+    _TESTS = [{
+        "url": "http://9gag.tv/v/1912",
+        "info_dict": {
+            "id": "1912",
+            "ext": "mp4",
+            "description": "This 3-minute video will make you smile and then make you feel untalented and insignificant. Anyway, you should share this awesomeness. (Thanks, Dino!)",
+            "title": "\"People Are Awesome 2013\" Is Absolutely Awesome",
+            "view_count": int,
+            "thumbnail": "re:^https?://",
+        },
+        'add_ie': ['Youtube']
+    },
+    {
+        'url': 'http://9gag.tv/p/KklwM/alternate-banned-opening-scene-of-gravity?ref=fsidebar',
+        'info_dict': {
+            'id': 'KklwM',
+            'ext': 'mp4',
+            'display_id': 'alternate-banned-opening-scene-of-gravity',
+            "description": "While Gravity was a pretty awesome movie already, YouTuber Krishna Shenoi came up with a way to improve upon it, introducing a much better solution to Sandra Bullock's seemingly endless tumble in space. The ending is priceless.",
+            'title': "Banned Opening Scene Of \"Gravity\" That Changes The Whole Movie",

         },
         },

-        u'add_ie': [u'Youtube']
-    }
+    }]

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

-        video_id = mobj.group('id')
+        video_id = mobj.group('numid') or mobj.group('id')
+        display_id = mobj.group('display_id') or video_id
+
+        webpage = self._download_webpage(url, display_id)

 
 

-        webpage = self._download_webpage(url, video_id)
-        data_json = self._html_search_regex(r'''(?x)
-            <div\s*id="tv-video"\s*data-video-source="youtube"\s*
-                data-video-meta="([^"]+)"''', webpage, u'video metadata')
+        post_view = json.loads(self._html_search_regex(
+            r'var postView = new app\.PostView\({\s*post:\s*({.+?}),\s*posts:\s*prefetchedCurrentPost', webpage, 'post view'))

 
 

-        data = json.loads(data_json)
+        youtube_id = post_view['videoExternalId']
+        title = post_view['title']
+        description = post_view['description']
+        view_count = str_to_int(post_view['externalView'])
+        thumbnail = post_view.get('thumbnail_700w') or post_view.get('ogImageUrl') or post_view.get('thumbnail_300w')

 
         return {
             '_type': 'url_transparent',
 
         return {
             '_type': 'url_transparent',

-            'url': data['youtubeVideoId'],
+            'url': youtube_id,

             'ie_key': 'Youtube',
             'id': video_id,
             'ie_key': 'Youtube',
             'id': video_id,

-            'title': data['title'],
-            'description': data['description'],
-            'view_count': int(data['view_count']),
-            'like_count': int(data['statistic']['like']),
-            'dislike_count': int(data['statistic']['dislike']),
-            'thumbnail': data['thumbnail_url'],
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'view_count': view_count,
+            'thumbnail': thumbnail,

         }
         }