Merge tag 'upstream/2015.06.04.1'

[youtubedl] / youtube_dl / extractor / tube8.py

diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py
index 36bc36ad8aa7bf3680db6e30d081fec644d61bcd..6ca8840b0869f1490c06c7df0905c28e38ba1fee 100644 (file)
--- a/youtube_dl/extractor/tube8.py
+++ b/youtube_dl/extractor/tube8.py
@@ -4,9 +4,11 @@ import json
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse_urlparse,
     compat_urllib_request,
+)
+from ..utils import (
     int_or_none,
     str_to_int,
 )
@@ -14,29 +16,38 @@ from ..aes import aes_decrypt_text
 
 
 class Tube8IE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/){2}(?P<id>\d+)'
-    _TEST = {
-        'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
-        'file': '229795.mp4',
-        'md5': 'e9e0b0c86734e5e3766e653509475db0',
-        'info_dict': {
-            'description': 'hot teen Kasia grinding',
-            'uploader': 'unknown',
-            'title': 'Kasia music video',
-            'age_limit': 18,
-        }
-    }
+    _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/(?P<id>\d+)'
+    _TESTS = [
+        {
+            'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
+            'md5': '44bf12b98313827dd52d35b8706a4ea0',
+            'info_dict': {
+                'id': '229795',
+                'display_id': 'kasia-music-video',
+                'ext': 'mp4',
+                'description': 'hot teen Kasia grinding',
+                'uploader': 'unknown',
+                'title': 'Kasia music video',
+                'age_limit': 18,
+            }
+        },
+        {
+            'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/',
+            'only_matching': True,
+        },
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
 
         req = compat_urllib_request.Request(url)
         req.add_header('Cookie', 'age_verified=1')
-        webpage = self._download_webpage(req, video_id)
+        webpage = self._download_webpage(req, display_id)
 
         flashvars = json.loads(self._html_search_regex(
-            r'var flashvars\s*=\s*({.+?})', webpage, 'flashvars'))
+            r'flashvars\s*=\s*({.+?})', webpage, 'flashvars'))
 
         video_url = flashvars['video_url']
         if flashvars.get('encrypted') is True:
@@ -47,19 +58,19 @@ class Tube8IE(InfoExtractor):
         thumbnail = flashvars.get('image_url')
 
         title = self._html_search_regex(
-            r'videotitle\s*=\s*"([^"]+)', webpage, 'title')
+            r'videoTitle\s*=\s*"([^"]+)', webpage, 'title')
         description = self._html_search_regex(
-            r'>Description:</strong>(.+?)<', webpage, 'description', fatal=False)
+            r'>Description:</strong>\s*(.+?)\s*<', webpage, 'description', fatal=False)
         uploader = self._html_search_regex(
-            r'<strong class="video-username">(?:<a href="[^"]+">)?([^<]+)(?:</a>)?</strong>',
+            r'<span class="username">\s*(.+?)\s*<',
             webpage, 'uploader', fatal=False)
 
         like_count = int_or_none(self._html_search_regex(
-            r"rupVar\s*=\s*'(\d+)'", webpage, 'like count', fatal=False))
+            r'rupVar\s*=\s*"(\d+)"', webpage, 'like count', fatal=False))
         dislike_count = int_or_none(self._html_search_regex(
-            r"rdownVar\s*=\s*'(\d+)'", webpage, 'dislike count', fatal=False))
+            r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False))
         view_count = self._html_search_regex(
-            r'<strong>Views: </strong>([\d,\.]+)</li>', webpage, 'view count', fatal=False)
+            r'<strong>Views: </strong>([\d,\.]+)\s*</li>', webpage, 'view count', fatal=False)
         if view_count:
             view_count = str_to_int(view_count)
         comment_count = self._html_search_regex(
@@ -69,6 +80,7 @@ class Tube8IE(InfoExtractor):
 
         return {
             'id': video_id,
+            'display_id': display_id,
             'url': video_url,
             'title': title,
             'description': description,