Update upstream source from tag 'upstream/2018.11.07'

[youtubedl] / youtube_dl / extractor / tube8.py

diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py
index 46ef61ff5cafbac172b975e64be9e86ae5e3de91..db93b018252d23bfa66c34b4161c56e1d14c568e 100644 (file)
--- a/youtube_dl/extractor/tube8.py
+++ b/youtube_dl/extractor/tube8.py
@@ -1,93 +1,86 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-import json

 import re
 
 import re
 

-from .common import InfoExtractor
-from ..compat import compat_urllib_parse_urlparse

 from ..utils import (
     int_or_none,
 from ..utils import (
     int_or_none,

-    sanitized_Request,

     str_to_int,
 )
     str_to_int,
 )

-from ..aes import aes_decrypt_text
+from .keezmovies import KeezMoviesIE

 
 
 
 

-class Tube8IE(InfoExtractor):
+class Tube8IE(KeezMoviesIE):

     _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/(?P<id>\d+)'
     _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,
+    _TESTS = [{
+        'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
+        'md5': '65e20c48e6abff62ed0c3965fff13a39',
+        '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,
+            'duration': 230,
+            'categories': ['Teen'],
+            'tags': ['dancing'],

         },
         },

-    ]
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        display_id = mobj.group('display_id')
-
-        req = sanitized_Request(url)
-        req.add_header('Cookie', 'age_verified=1')
-        webpage = self._download_webpage(req, display_id)
+    }, {
+        '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,
+    }]

 
 

-        flashvars = json.loads(self._html_search_regex(
-            r'flashvars\s*=\s*({.+?});\r?\n', webpage, 'flashvars'))
+    @staticmethod
+    def _extract_urls(webpage):
+        return re.findall(
+            r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?tube8\.com/embed/(?:[^/]+/)+\d+)',
+            webpage)

 
 

-        video_url = flashvars['video_url']
-        if flashvars.get('encrypted') is True:
-            video_url = aes_decrypt_text(video_url, flashvars['video_title'], 32).decode('utf-8')
-        path = compat_urllib_parse_urlparse(video_url).path
-        format_id = '-'.join(path.split('/')[4].split('_')[:2])
+    def _real_extract(self, url):
+        webpage, info = self._extract_info(url)

 
 

-        thumbnail = flashvars.get('image_url')
+        if not info['title']:
+            info['title'] = self._html_search_regex(
+                r'videoTitle\s*=\s*"([^"]+)', webpage, 'title')

 
 

-        title = self._html_search_regex(
-            r'videoTitle\s*=\s*"([^"]+)', webpage, 'title')

         description = self._html_search_regex(
         description = self._html_search_regex(

-            r'>Description:</strong>\s*(.+?)\s*<', webpage, 'description', fatal=False)
+            r'(?s)Description:</dt>\s*<dd>(.+?)</dd>', webpage, 'description', fatal=False)

         uploader = self._html_search_regex(
             r'<span class="username">\s*(.+?)\s*<',
             webpage, 'uploader', fatal=False)
 
         uploader = self._html_search_regex(
             r'<span class="username">\s*(.+?)\s*<',
             webpage, 'uploader', fatal=False)
 

-        like_count = int_or_none(self._html_search_regex(
+        like_count = int_or_none(self._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(
+        dislike_count = int_or_none(self._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,\.]+)\s*</li>', webpage, 'view count', fatal=False)
-        if view_count:
-            view_count = str_to_int(view_count)
-        comment_count = self._html_search_regex(
-            r'<span id="allCommentsCount">(\d+)</span>', webpage, 'comment count', fatal=False)
-        if comment_count:
-            comment_count = str_to_int(comment_count)
+        view_count = str_to_int(self._search_regex(
+            r'Views:\s*</dt>\s*<dd>([\d,\.]+)',
+            webpage, 'view count', fatal=False))
+        comment_count = str_to_int(self._search_regex(
+            r'<span id="allCommentsCount">(\d+)</span>',
+            webpage, 'comment count', fatal=False))
+
+        category = self._search_regex(
+            r'Category:\s*</dt>\s*<dd>\s*<a[^>]+href=[^>]+>([^<]+)',
+            webpage, 'category', fatal=False)
+        categories = [category] if category else None
+
+        tags_str = self._search_regex(
+            r'(?s)Tags:\s*</dt>\s*<dd>(.+?)</(?!a)',
+            webpage, 'tags', fatal=False)
+        tags = [t for t in re.findall(
+            r'<a[^>]+href=[^>]+>([^<]+)', tags_str)] if tags_str else None

 
 

-        return {
-            'id': video_id,
-            'display_id': display_id,
-            'url': video_url,
-            'title': title,
+        info.update({

             'description': description,
             'description': description,

-            'thumbnail': thumbnail,

             'uploader': uploader,
             'uploader': uploader,

-            'format_id': format_id,

             'view_count': view_count,
             'like_count': like_count,
             'dislike_count': dislike_count,
             'comment_count': comment_count,
             'view_count': view_count,
             'like_count': like_count,
             'dislike_count': dislike_count,
             'comment_count': comment_count,

-            'age_limit': 18,
-        }
+            'categories': categories,
+            'tags': tags,
+        })
+
+        return info