[extractor] Deprecate `_sort_formats`

[yt-dlp.git] / yt_dlp / extractor / xfileshare.py

diff --git a/yt_dlp/extractor/xfileshare.py b/yt_dlp/extractor/xfileshare.py
index cbd5d1cbbb331cbd14777e70950b9c3c2a41175c..08c6d6c7c01f153ba37454a2da0020f8bea49382 100644 (file)
--- a/yt_dlp/extractor/xfileshare.py
+++ b/yt_dlp/extractor/xfileshare.py
@@ -1,14 +1,10 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_chr
 from ..utils import (
+    ExtractorError,
     decode_packed_codes,
     determine_ext,
-    ExtractorError,
     int_or_none,
     js_to_json,
     urlencode_postdata,
@@ -35,11 +31,11 @@ def aa_decode(aa_code):
         aa_char = aa_char.replace('+ ', '')
         m = re.match(r'^\d+', aa_char)
         if m:
-            ret += compat_chr(int(m.group(0), 8))
+            ret += chr(int(m.group(0), 8))
         else:
             m = re.match(r'^u([\da-f]+)', aa_char)
             if m:
-                ret += compat_chr(int(m.group(1), 16))
+                ret += chr(int(m.group(1), 16))
     return ret
 
 
@@ -58,12 +54,14 @@ class XFileShareIE(InfoExtractor):
         (r'vidlocker\.xyz', 'VidLocker'),
         (r'vidshare\.tv', 'VidShare'),
         (r'vup\.to', 'VUp'),
+        (r'wolfstream\.tv', 'WolfStream'),
         (r'xvideosharing\.com', 'XVideoSharing'),
     )
 
     IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1])
     _VALID_URL = (r'https?://(?:www\.)?(?P<host>%s)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
                   % '|'.join(site for site in list(zip(*_SITES))[0]))
+    _EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:%s)/embed-[0-9a-zA-Z]+.*?)\1' % '|'.join(site for site in list(zip(*_SITES))[0])]
 
     _FILE_NOT_FOUND_REGEXES = (
         r'>(?:404 - )?File Not Found<',
@@ -71,6 +69,15 @@ class XFileShareIE(InfoExtractor):
     )
 
     _TESTS = [{
+        'url': 'https://uqload.com/dltx1wztngdz',
+        'md5': '3cfbb65e4c90e93d7b37bcb65a595557',
+        'info_dict': {
+            'id': 'dltx1wztngdz',
+            'ext': 'mp4',
+            'title': 'Rick Astley Never Gonna Give You mp4',
+            'thumbnail': r're:https://.*\.jpg'
+        }
+    }, {
         'url': 'http://xvideosharing.com/fq65f94nd2ve',
         'md5': '4181f63957e8fe90ac836fa58dc3c8a6',
         'info_dict': {
@@ -82,19 +89,13 @@ class XFileShareIE(InfoExtractor):
     }, {
         'url': 'https://aparat.cam/n4d6dh0wvlpr',
         'only_matching': True,
+    }, {
+        'url': 'https://wolfstream.tv/nthme29v9u2x',
+        'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return [
-            mobj.group('url')
-            for mobj in re.finditer(
-                r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:%s)/embed-[0-9a-zA-Z]+.*?)\1'
-                % '|'.join(site for site in list(zip(*XFileShareIE._SITES))[0]),
-                webpage)]
-
     def _real_extract(self, url):
-        host, video_id = re.match(self._VALID_URL, url).groups()
+        host, video_id = self._match_valid_url(url).groups()
 
         url = 'https://%s/' % host + ('embed-%s.html' % video_id if host in ('govid.me', 'vidlo.us') else video_id)
         webpage = self._download_webpage(url, video_id)
@@ -181,7 +182,6 @@ def _real_extract(self, url):
                         'url': video_url,
                         'format_id': 'sd',
                     })
-        self._sort_formats(formats)
 
         thumbnail = self._search_regex(
             [
@@ -194,4 +194,5 @@ def _real_extract(self, url):
             'title': title,
             'thumbnail': thumbnail,
             'formats': formats,
+            'http_headers': {'Referer': url}
         }