[youtube] Fix extraction.

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

diff --git a/youtube_dl/extractor/cracked.py b/youtube_dl/extractor/cracked.py
index 37c0f7ffb6244caa67ad1f73d3756710cb884706..f77a68ecedf74bc5192fbc475848f6b1a1234315 100644 (file)
--- a/youtube_dl/extractor/cracked.py
+++ b/youtube_dl/extractor/cracked.py
@@ -1,46 +1,90 @@
-# coding: utf-8
 from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
+from .youtube import YoutubeIE
+from ..utils import (
+    parse_iso8601,
+    str_to_int,
+)
 
-class CrackedIE(InfoExtractor):
-    _VALID_URL = r'http?://.*?\.cracked\.com/video_+(?P<id>.*)_.*'
-    _TEST = {
-        'url': 'http://www.cracked.com/video_18803_4-social-criticisms-hidden-in-sonic-hedgehog-games.html',
 
+class CrackedIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?cracked\.com/video_(?P<id>\d+)_[\da-z-]+\.html'
+    _TESTS = [{
+        'url': 'http://www.cracked.com/video_19070_if-animal-actors-got-e21-true-hollywood-stories.html',
+        'md5': '89b90b9824e3806ca95072c4d78f13f7',
         'info_dict': {
-            'id': '18803',
+            'id': '19070',
             'ext': 'mp4',
-            'title': "4 Social Criticisms Hidden in 'Sonic the Hedgehog' Games | Cracked.com",
-            'height': 375,
-            'width': 666,
-
-
+            'title': 'If Animal Actors Got E! True Hollywood Stories',
+            'timestamp': 1404954000,
+            'upload_date': '20140710',
+        }
+    }, {
+        # youtube embed
+        'url': 'http://www.cracked.com/video_19006_4-plot-holes-you-didnt-notice-in-your-favorite-movies.html',
+        'md5': 'ccd52866b50bde63a6ef3b35016ba8c7',
+        'info_dict': {
+            'id': 'EjI00A3rZD0',
+            'ext': 'mp4',
+            'title': "4 Plot Holes You Didn't Notice in Your Favorite Movies - The Spit Take",
+            'description': 'md5:c603708c718b796fe6079e2b3351ffc7',
+            'upload_date': '20140725',
+            'uploader_id': 'Cracked',
+            'uploader': 'Cracked',
         }
-    }
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
-        title = self._search_regex(r'<title>(.*?)</title>',webpage,'title')
-        video_url = self._search_regex(r'var CK_vidSrc = "+(.*)"',webpage,'url')
-        width = self._search_regex(r'width="(.*?)"',webpage,'width')
-        height = re.findall(r'height="(.*?)"',webpage)[1]
 
+        youtube_url = YoutubeIE._extract_url(webpage)
+        if youtube_url:
+            return self.url_result(youtube_url, ie=YoutubeIE.ie_key())
 
+        video_url = self._html_search_regex(
+            [r'var\s+CK_vidSrc\s*=\s*"([^"]+)"', r'<video\s+src="([^"]+)"'],
+            webpage, 'video URL')
 
+        title = self._search_regex(
+            [r'property="?og:title"?\s+content="([^"]+)"', r'class="?title"?>([^<]+)'],
+            webpage, 'title')
 
-        return {
-            'url':video_url,
-            'id': video_id,
-            'ext':'mp4',
-            'title':title,
-            'height':int(height),
-            'width':int(width)
+        description = self._search_regex(
+            r'name="?(?:og:)?description"?\s+content="([^"]+)"',
+            webpage, 'description', default=None)
+
+        timestamp = self._html_search_regex(
+            r'"date"\s*:\s*"([^"]+)"', webpage, 'upload date', fatal=False)
+        if timestamp:
+            timestamp = parse_iso8601(timestamp[:-6])
+
+        view_count = str_to_int(self._html_search_regex(
+            r'<span\s+class="?views"? id="?viewCounts"?>([\d,\.]+) Views</span>',
+            webpage, 'view count', fatal=False))
+        comment_count = str_to_int(self._html_search_regex(
+            r'<span\s+id="?commentCounts"?>([\d,\.]+)</span>',
+            webpage, 'comment count', fatal=False))
 
+        m = re.search(r'_(?P<width>\d+)X(?P<height>\d+)\.mp4$', video_url)
+        if m:
+            width = int(m.group('width'))
+            height = int(m.group('height'))
+        else:
+            width = height = None
 
-        }
\ No newline at end of file
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'description': description,
+            'timestamp': timestamp,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'height': height,
+            'width': width,
+        }