__author__ = 'chunk'

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
    http://stackoverflow.com/questions/12553117/how-to-filter-duplicate-requests-based-on-url-in-scrapy
    """

    def __getid(self, url):
        mm = url.split("/")[-1] #or something like that
        return mm

    def request_seen(self, request):
        fp = self.__getid(request.url)
        if fp in self.fingerprints:
            return True
        self.fingerprints.add(fp)
        if self.file:
            self.file.write(fp + os.linesep)


from scrapy.exceptions import DropItem

class DuplicatesPipeline(object):
    """
    http://doc.scrapy.org/en/latest/topics/item-pipeline.html
    """
    def __init__(self):
        self.ids_seen = set()

    def process_item(self, item, spider):
        if item['id'] in self.ids_seen:
            raise DropItem("Duplicate item found: %s" % item)
        else:
            self.ids_seen.add(item['id'])
            return item