[pornotube] Modernize

youtube_dl/extractor/pornotube.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -9,15 +11,16 @@ from ..utils import (
 
 
 class PornotubeIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$'
+    _VALID_URL = r'https?://(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$'
     _TEST = {
-        u'url': u'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing',
+        'url': 'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing',
-        u'file': u'1689755.flv',
+        'md5': '374dd6dcedd24234453b295209aa69b6',
-        u'md5': u'374dd6dcedd24234453b295209aa69b6',
+        'info_dict': {
-        u'info_dict': {
+            'id': '1689755',
-            u"upload_date": u"20090708", 
+            'ext': 'flv',
-            u"title": u"Marilyn-Monroe-Bathing",
+            'upload_date': '20090708',
-            u"age_limit": 18
+            'title': 'Marilyn-Monroe-Bathing',
+            'age_limit': 18
         }
     }
 
@@ -32,22 +35,22 @@ class PornotubeIE(InfoExtractor):
 
         # Get the video URL
         VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",'
-        video_url = self._search_regex(VIDEO_URL_RE, webpage, u'video url')
+        video_url = self._search_regex(VIDEO_URL_RE, webpage, 'video url')
         video_url = compat_urllib_parse.unquote(video_url)
 
         #Get the uploaded date
         VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by'
-        upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, u'upload date', fatal=False)
+        upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, 'upload date', fatal=False)
-        if upload_date: upload_date = unified_strdate(upload_date)
+        if upload_date:
+            upload_date = unified_strdate(upload_date)
         age_limit = self._rta_search(webpage)
 
-        info = {'id': video_id,
+        return {
-                'url': video_url,
+            'id': video_id,
-                'uploader': None,
+            'url': video_url,
-                'upload_date': upload_date,
+            'upload_date': upload_date,
-                'title': video_title,
+            'title': video_title,
-                'ext': 'flv',
+            'ext': 'flv',
-                'format': 'flv',
+            'format': 'flv',
-                'age_limit': age_limit}
+            'age_limit': age_limit,
-
+        }
-        return [info]