Scrapy, a fast high-level web crawling & scraping framework for Python.
Include extensions from #2067
Adrián Chavesbe6da5201999
diff --git a/scrapy/linkextractors/__init__.py b/scrapy/linkextractors/__init__.pyindex 3c75e683d..a2ac963fe 100644--- a/scrapy/linkextractors/__init__.py+++ b/scrapy/linkextractors/__init__.py@@ -19,9 +19,12 @@ from scrapy.utils.url import (# common file extensions that are not followed if they occur in linksIGNORED_EXTENSIONS = [+ # archives+ '7z', '7zip', 'bz2', 'rar', 'tar', 'tar.gz', 'xz', 'zip',+# images'mng', 'pct', 'bmp', 'gif', 'jpg', 'jpeg', 'png', 'pst', 'psp', 'tif',- 'tiff', 'ai', 'drw', 'dxf', 'eps', 'ps', 'svg',+ 'tiff', 'ai', 'drw', 'dxf', 'eps', 'ps', 'svg', 'cdr', 'ico',# audio'mp3', 'wma', 'ogg', 'wav', 'ra', 'aac', 'mid', 'au', 'aiff',@@ -35,7 +38,7 @@ IGNORED_EXTENSIONS = ['odp',# other- 'css', 'pdf', 'exe', 'bin', 'rss', 'zip', 'rar', 'dmg', 'iso', 'apk', 'xz'+ 'css', 'pdf', 'exe', 'bin', 'rss', 'dmg', 'iso', 'apk']