X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fhellporno.py;h=fae4251034da29dd252557f86528531b8fcb9235;hb=HEAD;hp=06f85127f206fb6303a6a1a112e4f38d166cbea3;hpb=6a1c4fbfcb57c138b8ace305127c2654844e8099;p=youtube-dl

diff --git a/youtube_dl/extractor/hellporno.py b/youtube_dl/extractor/hellporno.py
index 06f85127f..fae425103 100644
--- a/youtube_dl/extractor/hellporno.py
+++ b/youtube_dl/extractor/hellporno.py
@@ -1,56 +1,76 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    merge_dicts,
+    remove_end,
+    unified_timestamp,
+)
+
 
 class HellPornoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?hellporno\.com/videos/(?P<display_id>[^/]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?hellporno\.(?:com/videos|net/v)/(?P<id>[^/]+)'
+    _TESTS = [{
         'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/',
-        'md5': '1fee339c610d2049699ef2aa699439f1',
+        'md5': 'f0a46ebc0bed0c72ae8fe4629f7de5f3',
         'info_dict': {
             'id': '149116',
+            'display_id': 'dixie-is-posing-with-naked-ass-very-erotic',
             'ext': 'mp4',
             'title': 'Dixie is posing with naked ass very erotic',
-            'description': 'md5:5ba02cbf31eff820147b3cc25306d89a',
-            'categories': list,  # NSFW
-            'thumbnail': 're:https?://.*\.jpg$',
+            'description': 'md5:9a72922749354edb1c4b6e540ad3d215',
+            'categories': list,
+            'thumbnail': r're:https?://.*\.jpg$',
+            'duration': 240,
+            'timestamp': 1398762720,
+            'upload_date': '20140429',
+            'view_count': int,
             'age_limit': 18,
-        }
-    }
+        },
+    }, {
+        'url': 'http://hellporno.net/v/186271/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        webpage = self._download_webpage(url, 'main')
-
-        video_id = self._html_search_regex(r'video_id:\s*\'([^\']+)\'', webpage, 'id')
-
-        video_url = self._html_search_regex(r'video_url:\s*\'([^\']+)\'', webpage, 'video_url')
-
-        ext = self._html_search_regex(r'postfix:\s*\'([^\']+)\'', webpage, 'ext')[1:]
+        display_id = self._match_id(url)
 
-        title = self._html_search_regex(
-            r'<title>([^<]+)\s*-\s*Hell Porno</title>', webpage, 'title')
+        webpage = self._download_webpage(url, display_id)
 
-        description = self._html_search_meta('description', webpage, 'description', fatal=False)
+        title = remove_end(self._html_search_regex(
+            r'<title>([^<]+)</title>', webpage, 'title'), ' - Hell Porno')
 
-        thumbnail = self._html_search_regex(
-            r'preview_url:\s*\'([^\']+)\'',
-            webpage, 'thumbnail', fatal=False)
+        info = self._parse_html5_media_entries(url, webpage, display_id)[0]
+        self._sort_formats(info['formats'])
 
-        categories_str = self._html_search_regex(
-            r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
-        categories = (
-            None if categories_str is None
-            else categories_str.split(','))
+        video_id = self._search_regex(
+            (r'chs_object\s*=\s*["\'](\d+)',
+             r'params\[["\']video_id["\']\]\s*=\s*(\d+)'), webpage, 'video id',
+            default=display_id)
+        description = self._search_regex(
+            r'class=["\']desc_video_view_v2[^>]+>([^<]+)', webpage,
+            'description', fatal=False)
+        categories = [
+            c.strip()
+            for c in self._html_search_meta(
+                'keywords', webpage, 'categories', default='').split(',')
+            if c.strip()]
+        duration = int_or_none(self._og_search_property(
+            'video:duration', webpage, fatal=False))
+        timestamp = unified_timestamp(self._og_search_property(
+            'video:release_date', webpage, fatal=False))
+        view_count = int_or_none(self._search_regex(
+            r'>Views\s+(\d+)', webpage, 'view count', fatal=False))
 
-        return {
+        return merge_dicts(info, {
             'id': video_id,
-            'url': video_url,
+            'display_id': display_id,
             'title': title,
-            'ext': ext,
             'description': description,
-            'thumbnail': thumbnail,
             'categories': categories,
+            'duration': duration,
+            'timestamp': timestamp,
+            'view_count': view_count,
             'age_limit': 18,
-        }
+        })