X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcliphunter.py;h=f2ca7a337df88aab5ba7f7b070537b7b9fec3172;hb=HEAD;hp=9c90e2f9801536c431de707ffaa9f422f52ad35b;hpb=008af8660b7d0075882ac7d22c03dca67b5e64f1;p=youtube-dl

diff --git a/youtube_dl/extractor/cliphunter.py b/youtube_dl/extractor/cliphunter.py
index 9c90e2f98..f2ca7a337 100644
--- a/youtube_dl/extractor/cliphunter.py
+++ b/youtube_dl/extractor/cliphunter.py
@@ -1,69 +1,79 @@
-import re
-import string
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
-    determine_ext,
-    ExtractorError,
-)
-
-translation_table = (
-    '\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\x0c\r\x0e\x0f\x10\x11\x12'
-    '\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !"#:%.\'=)*+,-./0123'
-    '456789:;</>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]&_`hbcevofhdjknamoutsstupwrli{'
-    '|}~\x7f\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f'
-    '\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1'
-    '\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3'
-    '\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5'
-    '\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7'
-    '\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9'
-    '\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb'
-    '\xfc\xfd\xfe\xff'
+    int_or_none,
+    url_or_none,
 )
 
 
 class CliphunterIE(InfoExtractor):
-    """Information Extractor for Cliphunter"""
-    IE_NAME = u'cliphunter'
+    IE_NAME = 'cliphunter'
 
-    _VALID_URL = (r'(?:http://)?(?:www\.)?cliphunter\.com/w/'
-                  '(?P<id>[0-9]+)/'
-                  '(?P<seo>.+?)(?:\?.*)?')
+    _VALID_URL = r'''(?x)https?://(?:www\.)?cliphunter\.com/w/
+        (?P<id>[0-9]+)/
+        (?P<seo>.+?)(?:$|[#\?])
+    '''
     _TESTS = [{
-        u'url': u'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
-        u'file': u'1012420.flv',
-        u'md5': u'49f72e2fd2977e6e518be9836dcf861e',
-        u'info_dict': {
-            u"title": u"Fun Jynx Maze solo",
-        }
-    },
-    ]
+        'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
+        'md5': 'b7c9bbd4eb3a226ab91093714dcaa480',
+        'info_dict': {
+            'id': '1012420',
+            'ext': 'flv',
+            'title': 'Fun Jynx Maze solo',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'age_limit': 18,
+        },
+        'skip': 'Video gone',
+    }, {
+        'url': 'http://www.cliphunter.com/w/2019449/ShesNew__My_booty_girlfriend_Victoria_Paradices_pussy_filled_with_jizz',
+        'md5': '55a723c67bfc6da6b0cfa00d55da8a27',
+        'info_dict': {
+            'id': '2019449',
+            'ext': 'mp4',
+            'title': 'ShesNew - My booty girlfriend, Victoria Paradice\'s pussy filled with jizz',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'age_limit': 18,
+        },
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Unable to extract media URL')
-
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        pl_fiji = re.search(r'pl_fiji = \'([^\']+)\'', webpage).group(1)
-        pl_c_qual = re.search(r'pl_c_qual = "(.)"', webpage).group(1)
-        video_title = re.search(r'mediaTitle = "([^"]+)"', webpage).group(1)
+        video_title = self._search_regex(
+            r'mediaTitle = "([^"]+)"', webpage, 'title')
+
+        gexo_files = self._parse_json(
+            self._search_regex(
+                r'var\s+gexoFiles\s*=\s*({.+?});', webpage, 'gexo files'),
+            video_id)
 
-        video_url = string.translate(pl_fiji.encode(), translation_table)
+        formats = []
+        for format_id, f in gexo_files.items():
+            video_url = url_or_none(f.get('url'))
+            if not video_url:
+                continue
+            fmt = f.get('fmt')
+            height = f.get('h')
+            format_id = '%s_%sp' % (fmt, height) if fmt and height else format_id
+            formats.append({
+                'url': video_url,
+                'format_id': format_id,
+                'width': int_or_none(f.get('w')),
+                'height': int_or_none(height),
+                'tbr': int_or_none(f.get('br')),
+            })
+        self._sort_formats(formats)
 
-        formats = [{
-            'url': video_url,
-            'ext': determine_ext(video_url),
-            'format': pl_c_qual,
-            'format_id': pl_c_qual,
-        }]
+        thumbnail = self._search_regex(
+            r"var\s+mov_thumb\s*=\s*'([^']+)';",
+            webpage, 'thumbnail', fatal=False)
 
         return {
             'id': video_id,
             'title': video_title,
             'formats': formats,
-            'description': '',
+            'age_limit': self._rta_search(webpage),
+            'thumbnail': thumbnail,
         }