From: Sergey M․ <dstftw@gmail.com>
Date: Tue, 1 Jan 2019 11:12:44 +0000 (+0700)
Subject: [bitchute] Fix extraction (closes #18567)
X-Git-Url: http://git.oshgnacknak.de/?a=commitdiff_plain;h=6b688b8942a0bd18b2a3835e69a903f1eeffee2a;p=youtube-dl

[bitchute] Fix extraction (closes #18567)
---

diff --git a/youtube_dl/extractor/bitchute.py b/youtube_dl/extractor/bitchute.py
index 43b4732aa..aa034355a 100644
--- a/youtube_dl/extractor/bitchute.py
+++ b/youtube_dl/extractor/bitchute.py
@@ -5,7 +5,10 @@ import itertools
 import re
 
 from .common import InfoExtractor
-from ..utils import urlencode_postdata
+from ..utils import (
+    orderedSet,
+    urlencode_postdata,
+)
 
 
 class BitChuteIE(InfoExtractor):
@@ -43,10 +46,15 @@ class BitChuteIE(InfoExtractor):
             'description', webpage, 'title',
             default=None) or self._og_search_description(webpage)
 
+        format_urls = []
+        for mobj in re.finditer(
+                r'addWebSeed\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage):
+            format_urls.append(mobj.group('url'))
+        format_urls.extend(re.findall(r'as=(https?://[^&"\']+)', webpage))
+
         formats = [
-            {'url': mobj.group('url')}
-            for mobj in re.finditer(
-                r'addWebSeed\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage)]
+            {'url': format_url}
+            for format_url in orderedSet(format_urls)]
         self._sort_formats(formats)
 
         description = self._html_search_regex(