[4tube] Minor changes and extract more metadata

youtube_dl/extractor/fourtube.py

@@ -1,11 +1,20 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
-from ..utils import compat_urllib_request
+from ..utils import (
+    compat_urllib_request,
+    unified_strdate,
+    str_to_int,
+    parse_duration,
+)
+from youtube_dl.utils import clean_html
+
 
 class FourTubeIE(InfoExtractor):
     IE_NAME = '4tube'
-    _VALID_URL = r'(?:https?://)?www\.4tube\.com/videos/(?P<id>\d+)/.*'
+    _VALID_URL = r'https?://(?:www\.)?4tube\.com/videos/(?P<id>\d+)'
 
     _TEST = {
         'url': 'http://www.4tube.com/videos/209733/hot-babe-holly-michaels-gets-her-ass-stuffed-by-black',
@@ -13,7 +22,11 @@ class FourTubeIE(InfoExtractor):
         'info_dict': {
             'id': '209733',
             'ext': 'mp4',
-                'title': 'Hot Babe Holly Michaels gets her ass stuffed by black'
+            'title': 'Hot Babe Holly Michaels gets her ass stuffed by black',
+            'uploader': 'WCP Club',
+            'uploader_id': 'wcp-club',
+            'upload_date': '20131031',
+            'duration': 583,
         }
     }
 
@@ -26,11 +39,29 @@ class FourTubeIE(InfoExtractor):
 
         self.report_extraction(video_id)
 
-        playlist_json = self._html_search_regex(r'var playerConfigPlaylist\s+=\s+([^;]+)', webpage, u'Playlist')
+        playlist_json = self._html_search_regex(r'var playerConfigPlaylist\s+=\s+([^;]+)', webpage, 'Playlist')
-        media_id = self._search_regex(r'idMedia:\s*(\d+)', playlist_json, u"Media Id")
+        media_id = self._search_regex(r'idMedia:\s*(\d+)', playlist_json, 'Media Id')
-        thumbnail_url = self._search_regex(r'image:\s*"([^"]*)', playlist_json, u'Thumbnail')
+        sources = self._search_regex(r'sources:\s*\[([^\]]*)\]', playlist_json, 'Sources').split(',')
-        sources = self._search_regex(r'sources:\s*\[([^\]]*)\]', playlist_json, u'Sources').split(',')
+        title = self._search_regex(r'title:\s*"([^"]*)', playlist_json, 'Title')
-        title = self._search_regex(r'title:\s*"([^"]*)', playlist_json, u'Title')
+        thumbnail_url = self._search_regex(r'image:\s*"([^"]*)', playlist_json, 'Thumbnail', fatal=False)
+
+        uploader_str = self._search_regex(r'<span>Uploaded by</span>(.*?)<span>', webpage, 'uploader', fatal=False)
+        mobj = re.search(r'<a href="/sites/(?P<id>[^"]+)"><strong>(?P<name>[^<]+)</strong></a>', uploader_str)
+        (uploader, uploader_id) = (mobj.group('name'), mobj.group('id')) if mobj else (clean_html(uploader_str), None)
+
+        upload_date = None
+        view_count = None
+        duration = None
+        description = self._html_search_meta('description', webpage, 'description')
+        if description:
+            upload_date = self._search_regex(r'Published Date: (\d{2} [a-zA-Z]{3} \d{4})', description, 'upload date',
+                fatal=False)
+            if upload_date:
+                upload_date = unified_strdate(upload_date)
+            view_count = self._search_regex(r'Views: ([\d,\.]+)', description, 'view count', fatal=False)
+            if view_count:
+                view_count = str_to_int(view_count)
+            duration = parse_duration(self._search_regex(r'Length: (\d+m\d+s)', description, 'duration', fatal=False))
 
         token_url = "http://tkn.4tube.com/{0}/desktop/{1}".format(media_id, "+".join(sources))
         headers = {
@@ -47,11 +78,18 @@ class FourTubeIE(InfoExtractor):
             'quality': int(format),
             } for format in sources]
 
-        return [{
+        self._sort_formats(formats)
+
+        return {
             'id': video_id,
             'title': title,
             'formats': formats,
             'thumbnail': thumbnail_url,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'upload_date': upload_date,
+            'view_count': view_count,
+            'duration': duration,
             'age_limit': 18,
             'webpage_url': webpage_url,
-            }]
+        }