Merge tag 'upstream/2016.06.25'

[youtubedl] / youtube_dl / extractor / tube8.py

diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py
index d4b7603c7c96a5da148ff50869559b0ff0c11a0f..1d9271d1e70c3f2b5ad30a6c69f6602bd58ac89a 100644 (file)
--- a/youtube_dl/extractor/tube8.py
+++ b/youtube_dl/extractor/tube8.py
@@ -1,65 +1,103 @@
-import os
+from __future__ import unicode_literals
+

 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

+from ..compat import compat_str

 from ..utils import (
 from ..utils import (

-    compat_urllib_parse_urlparse,
-    compat_urllib_request,
-    compat_urllib_parse,
-    unescapeHTML,
-)
-from ..aes import (
-    aes_decrypt_text
+    int_or_none,
+    sanitized_Request,
+    str_to_int,

 )
 )

+from ..aes import aes_decrypt_text
+

 
 class Tube8IE(InfoExtractor):
 
 class Tube8IE(InfoExtractor):

-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>tube8\.com/[^/]+/[^/]+/(?P<videoid>[0-9]+)/?)'
-    _TEST = {
-        u'url': u'http://www.tube8.com/teen/kasia-music-video/229795/',
-        u'file': u'229795.mp4',
-        u'md5': u'e9e0b0c86734e5e3766e653509475db0',
-        u'info_dict': {
-            u"description": u"hot teen Kasia grinding", 
-            u"uploader": u"unknown", 
-            u"title": u"Kasia music video",
-            u"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': '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,

         }
         }

-    }
+    }, {
+        '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)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

-        video_id = mobj.group('videoid')
-        url = 'http://www.' + mobj.group('url')
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')

 
 

-        req = compat_urllib_request.Request(url)
+        req = sanitized_Request(url)

         req.add_header('Cookie', 'age_verified=1')
         req.add_header('Cookie', 'age_verified=1')

-        webpage = self._download_webpage(req, video_id)
+        webpage = self._download_webpage(req, display_id)
+
+        flashvars = self._parse_json(
+            self._search_regex(
+                r'flashvars\s*=\s*({.+?});\r?\n', webpage, 'flashvars'),
+            video_id)
+
+        formats = []
+        for key, video_url in flashvars.items():
+            if not isinstance(video_url, compat_str) or not video_url.startswith('http'):
+                continue
+            height = self._search_regex(
+                r'quality_(\d+)[pP]', key, 'height', default=None)
+            if not height:
+                continue
+            if flashvars.get('encrypted') is True:
+                video_url = aes_decrypt_text(
+                    video_url, flashvars['video_title'], 32).decode('utf-8')
+            formats.append({
+                'url': video_url,
+                'format_id': '%sp' % height,
+                'height': int(height),
+            })
+        self._sort_formats(formats)
+
+        thumbnail = flashvars.get('image_url')

 
 

-        video_title = self._html_search_regex(r'videotitle     ="([^"]+)', webpage, u'title')
-        video_description = self._html_search_regex(r'>Description:</strong>(.+?)<', webpage, u'description', fatal=False)
-        video_uploader = self._html_search_regex(r'>Submitted by:</strong>(?:\s|<[^>]*>)*(.+?)<', webpage, u'uploader', fatal=False)
-        thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, u'thumbnail', fatal=False)
-        if thumbnail:
-            thumbnail = thumbnail.replace('\\/', '/')
+        title = self._html_search_regex(
+            r'videoTitle\s*=\s*"([^"]+)', webpage, 'title')
+        description = self._html_search_regex(
+            r'>Description:</strong>\s*(.+?)\s*<', webpage, 'description', fatal=False)
+        uploader = self._html_search_regex(
+            r'<span class="username">\s*(.+?)\s*<',
+            webpage, 'uploader', fatal=False)
+        duration = int_or_none(flashvars.get('video_duration'))

 
 

-        video_url = self._html_search_regex(r'"video_url":"([^"]+)', webpage, u'video_url')
-        if webpage.find('"encrypted":true')!=-1:
-            password = self._html_search_regex(r'"video_title":"([^"]+)', webpage, u'password')
-            video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8')
-        path = compat_urllib_parse_urlparse(video_url).path
-        extension = os.path.splitext(path)[1][1:]
-        format = path.split('/')[4].split('_')[:2]
-        format = "-".join(format)
+        like_count = int_or_none(self._search_regex(
+            r'rupVar\s*=\s*"(\d+)"', webpage, 'like count', fatal=False))
+        dislike_count = int_or_none(self._search_regex(
+            r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False))
+        view_count = str_to_int(self._search_regex(
+            r'<strong>Views: </strong>([\d,\.]+)\s*</li>',
+            webpage, 'view count', fatal=False))
+        comment_count = str_to_int(self._search_regex(
+            r'<span id="allCommentsCount">(\d+)</span>',
+            webpage, 'comment count', fatal=False))

 
         return {
             'id': video_id,
 
         return {
             'id': video_id,

-            'uploader': video_uploader,
-            'title': video_title,
+            'display_id': display_id,
+            'title': title,
+            'description': description,

             'thumbnail': thumbnail,
             'thumbnail': thumbnail,

-            'description': video_description,
-            'url': video_url,
-            'ext': extension,
-            'format': format,
-            'format_id': format,
+            'uploader': uploader,
+            'duration': duration,
+            'view_count': view_count,
+            'like_count': like_count,
+            'dislike_count': dislike_count,
+            'comment_count': comment_count,

             'age_limit': 18,
             'age_limit': 18,

+            'formats': formats,

         }
         }