Created
August 28, 2011 23:12
-
-
Save rmax/1177373 to your computer and use it in GitHub Desktop.
A Redis-based request dupefilter 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
| import redis | |
| from scrapy.dupefilter import BaseDupeFilter | |
| from scrapy.utils.request import request_fingerprint | |
| class RedisDupeFilter(BaseDupeFilter): | |
| def __init__(self, host, port): | |
| self.redis = redis.Redis(host, port) | |
| @classmethod | |
| def from_settings(cls, settings): | |
| host = settings.get('REDIS_HOST', 'localhost') | |
| port = settings.get('REDIS_PORT', 6379) | |
| return cls(host, port) | |
| def request_seen(self, request): | |
| fp = request_fingerprint(request) | |
| added = self.redis.sadd('fingerprints', fp) | |
| return not added |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment