Merge tag 'upstream/2015.11.27.1'

[youtubedl] / youtube_dl / extractor / fourtube.py

diff --git a/youtube_dl/extractor/fourtube.py b/youtube_dl/extractor/fourtube.py
index b2284ab01cad03fa3152fbc0a2edb70df2ab020f..fc4a5a0fbf01801d598e20a9addd29ebef4a298e 100644 (file)
--- a/youtube_dl/extractor/fourtube.py
+++ b/youtube_dl/extractor/fourtube.py
@@ -3,12 +3,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

-from ..compat import (
-    compat_urllib_request,
-)

 from ..utils import (
     parse_duration,
     parse_iso8601,
 from ..utils import (
     parse_duration,
     parse_iso8601,

+    sanitized_Request,

     str_to_int,
 )
 
     str_to_int,
 )
 


@@ -32,6 +30,7 @@ class FourTubeIE(InfoExtractor):
             'view_count': int,
             'like_count': int,
             'categories': list,
             'view_count': int,
             'like_count': int,
             'categories': list,

+            'age_limit': 18,

         }
     }
 
         }
     }
 


@@ -45,10 +44,10 @@ class FourTubeIE(InfoExtractor):
         thumbnail = self._html_search_meta('thumbnailUrl', webpage)
         uploader_id = self._html_search_regex(
             r'<a class="img-avatar" href="[^"]+/channels/([^/"]+)" title="Go to [^"]+ page">',
         thumbnail = self._html_search_meta('thumbnailUrl', webpage)
         uploader_id = self._html_search_regex(
             r'<a class="img-avatar" href="[^"]+/channels/([^/"]+)" title="Go to [^"]+ page">',

-            webpage, 'uploader id')
+            webpage, 'uploader id', fatal=False)

         uploader = self._html_search_regex(
             r'<a class="img-avatar" href="[^"]+/channels/[^/"]+" title="Go to ([^"]+) page">',
         uploader = self._html_search_regex(
             r'<a class="img-avatar" href="[^"]+/channels/[^/"]+" title="Go to ([^"]+) page">',

-            webpage, 'uploader')
+            webpage, 'uploader', fatal=False)

 
         categories_html = self._search_regex(
             r'(?s)><i class="icon icon-tag"></i>\s*Categories / Tags\s*.*?<ul class="list">(.*?)</ul>',
 
         categories_html = self._search_regex(
             r'(?s)><i class="icon icon-tag"></i>\s*Categories / Tags\s*.*?<ul class="list">(.*?)</ul>',


@@ -67,13 +66,24 @@ class FourTubeIE(InfoExtractor):
             webpage, 'like count', fatal=False))
         duration = parse_duration(self._html_search_meta('duration', webpage))
 
             webpage, 'like count', fatal=False))
         duration = parse_duration(self._html_search_meta('duration', webpage))
 

-        params_js = self._search_regex(
-            r'\$\.ajax\(url,\ opts\);\s*\}\s*\}\)\(([0-9,\[\] ]+)\)',
-            webpage, 'initialization parameters'
-        )
-        params = self._parse_json('[%s]' % params_js, video_id)
-        media_id = params[0]
-        sources = ['%s' % p for p in params[2]]
+        media_id = self._search_regex(
+            r'<button[^>]+data-id=(["\'])(?P<id>\d+)\1[^>]+data-quality=', webpage,
+            'media id', default=None, group='id')
+        sources = [
+            quality
+            for _, quality in re.findall(r'<button[^>]+data-quality=(["\'])(.+?)\1', webpage)]
+        if not (media_id and sources):
+            player_js = self._download_webpage(
+                self._search_regex(
+                    r'<script[^>]id=(["\'])playerembed\1[^>]+src=(["\'])(?P<url>.+?)\2',
+                    webpage, 'player JS', group='url'),
+                video_id, 'Downloading player JS')
+            params_js = self._search_regex(
+                r'\$\.ajax\(url,\ opts\);\s*\}\s*\}\)\(([0-9,\[\] ]+)\)',
+                player_js, 'initialization parameters')
+            params = self._parse_json('[%s]' % params_js, video_id)
+            media_id = params[0]
+            sources = ['%s' % p for p in params[2]]

 
         token_url = 'http://tkn.4tube.com/{0}/desktop/{1}'.format(
             media_id, '+'.join(sources))
 
         token_url = 'http://tkn.4tube.com/{0}/desktop/{1}'.format(
             media_id, '+'.join(sources))


@@ -81,7 +91,7 @@ class FourTubeIE(InfoExtractor):
             b'Content-Type': b'application/x-www-form-urlencoded',
             b'Origin': b'http://www.4tube.com',
         }
             b'Content-Type': b'application/x-www-form-urlencoded',
             b'Origin': b'http://www.4tube.com',
         }

-        token_req = compat_urllib_request.Request(token_url, b'{}', headers)
+        token_req = sanitized_Request(token_url, b'{}', headers)

         tokens = self._download_json(token_req, video_id)
         formats = [{
             'url': tokens[format]['token'],
         tokens = self._download_json(token_req, video_id)
         formats = [{
             'url': tokens[format]['token'],