Last active
December 15, 2015 03:19
-
-
Save pkmishra/5193538 to your computer and use it in GitHub Desktop.
Config settings for Scrapy.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# More comprehensive list can be found at | |
# http://techpatterns.com/forums/about304.html | |
USER_AGENT_LIST = [ | |
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.36 Safari/535.7', | |
'Mozilla/5.0 (Windows NT 6.2; Win64; x64; rv:16.0) Gecko/16.0 Firefox/16.0', | |
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/534.55.3 (KHTML, like Gecko) Version/5.1.3 Safari/534.53.10' | |
] | |
DOWNLOADER_MIDDLEWARES = { | |
'myproject.middlewares.RandomUserAgentMiddleware': 400, | |
'myproject.middlewares.ProxyMiddleware': 410, | |
'scrapy.contrib.downloadermiddleware.useragent.UserAgentMiddleware': None, | |
# Disable compression middleware, so the actual HTML pages are cached | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment