X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fbeeg.py;h=b38057f2f500f520829ff9c5d7324e66558eb356;hb=10952eb2cf2c86c841e46690a3bfa6a39c82d67d;hp=775f6be6b82e9aaf351a5b9b5cc1ce9e1540543d;hpb=2aebbccefceec3eb2cad147204123cb28b9d81d1;p=youtube-dl

diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py
index 775f6be6b..b38057f2f 100644
--- a/youtube_dl/extractor/beeg.py
+++ b/youtube_dl/extractor/beeg.py
@@ -9,12 +9,15 @@ class BeegIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)'
     _TEST = {
         'url': 'http://beeg.com/5416503',
-        'md5': '634526ae978711f6b748fe0dd6c11f57',
+        'md5': '1bff67111adb785c51d1b42959ec10e5',
         'info_dict': {
             'id': '5416503',
             'ext': 'mp4',
             'title': 'Sultry Striptease',
             'description': 'md5:6db3c6177972822aaba18652ff59c773',
+            'categories': list,  # NSFW
+            'thumbnail': 're:https?://.*\.jpg$',
+            'age_limit': 18,
         }
     }
 
@@ -24,25 +27,39 @@ class BeegIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        video_url = self._html_search_regex(r"'480p'\s*:\s*'([^']+)'", webpage, 'video URL')
+        quality_arr = self._search_regex(
+            r'(?s)var\s+qualityArr\s*=\s*{\s*(.+?)\s*}', webpage, 'quality formats')
+
+        formats = [{
+            'url': fmt[1],
+            'format_id': fmt[0],
+            'height': int(fmt[0][:-1]),
+        } for fmt in re.findall(r"'([^']+)'\s*:\s*'([^']+)'", quality_arr)]
+
+        self._sort_formats(formats)
+
+        title = self._html_search_regex(
+            r'<title>([^<]+)\s*-\s*beeg\.?</title>', webpage, 'title')
 
-        title = self._html_search_regex(r'<title>([^<]+)\s*-\s*beeg\.?</title>', webpage, 'title')
-        
         description = self._html_search_regex(
-            r'<meta name="description" content="([^"]*)"', webpage, 'description', fatal=False)
-        
+            r'<meta name="description" content="([^"]*)"',
+            webpage, 'description', fatal=False)
         thumbnail = self._html_search_regex(
-            r'\'previewer.url\'\s*:\s*"([^"]*)"', webpage, 'thumbnail', fatal=False)
+            r'\'previewer.url\'\s*:\s*"([^"]*)"',
+            webpage, 'thumbnail', fatal=False)
 
         categories_str = self._html_search_regex(
             r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
-        categories = categories_str.split(',')
+        categories = (
+            None if categories_str is None
+            else categories_str.split(','))
 
         return {
             'id': video_id,
-            'url': video_url,
             'title': title,
             'description': description,
             'thumbnail': thumbnail,
             'categories': categories,
+            'formats': formats,
+            'age_limit': 18,
         }