mirror of https://github.com/scrapy/scrapy.git
22 lines
594 B
Python
22 lines
594 B
Python
"""
|
|
Common code and definitions used by Link extractors (located in
|
|
scrapy.contrib.linkextractor).
|
|
"""
|
|
|
|
# common file extensions that are not followed if they occur in links
|
|
IGNORED_EXTENSIONS = [
|
|
# images
|
|
'mng', 'pct', 'bmp', 'gif', 'jpg', 'jpeg', 'png', 'pst', 'psp', 'tif',
|
|
'tiff', 'ai', 'drw', 'dxf', 'eps', 'ps', 'svg',
|
|
|
|
# audio
|
|
'mp3', 'wma', 'ogg', 'wav', 'ra', 'aac', 'mid', 'au', 'aiff',
|
|
|
|
# video
|
|
'3gp', 'asf', 'asx', 'avi', 'mov', 'mp4', 'mpg', 'qt', 'rm', 'swf', 'wmv',
|
|
'm4a',
|
|
|
|
# other
|
|
'css', 'pdf', 'doc', 'exe', 'bin', 'rss', 'zip', 'rar',
|
|
]
|