Skip to content

Instantly share code, notes, and snippets.

import os
from scrapy.dupefilter import RFPDupeFilter
from scrapy.utils.request import request_fingerprint
class CustomFilter(RFPDupeFilter):
"""A dupe filter that considers specific ids in the url"""
def __getid(self, url):
mm = url.split("&refer")[0] #or something like that
@yourmoonlight
yourmoonlight / pool.py
Last active August 29, 2015 14:08 — forked from binux/pool.py
# !/usr/bin/env python
# -*- coding:utf-8 -*-
import sys
import time
import Queue
import threading
import traceback
class ExitException(Exception):
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
  • first thing i need to do
  • second thing i need to do
  • third thing i need to do