pipelines.py

from scrapy.exceptions import DropItem

class DuplicatesPipeline(object):

    def __init__(self):
        self.emails_seen = set()

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