scrapy–基于Redis的Bloomfilter去重
本文代码去重对象是item

class RedisPipeline(object):
    def __init__(self, redis_uri, redis_db):
        self.redis_uri = redis_uri
        self.redis_db = redis_db


    @classmethod
    def from_crawler(cls, crawler):
        return cls(redis_uri=crawler.settings.get('REDIS_URI'), redis_db=crawler.settings.get('REDIS_DB'))

    def open_spider(self, spider):
        self.bf = BloomFilter(host=self.redis_uri,key=self.redis_db)


    def process_item(self, item, spider):

       if item["app_name"]:
            if self.bf.isContains(item["app_name"]):  # 判断字符串是否存在
                raise DropItem("{name}已经存在".format(name=item["app_name"]))
            else:
                self.bf.insert(item["app_name"])
                return item
       else :
           raise DropItem("{name}空值".format(name=item["app_name"]))

    def close_spider(self, spider):
        self.bf.close()

settings中

1、
#redis config
REDIS_URI="localhost"
REDIS_DB="wandoujia"
2、
ITEM_PIPELINES = {
   'wandoujiaScrapy.pipelines.RedisPipeline': 200,
}

redis储存

# coding=utf-8
import redis
from hashlib import md5
from wandoujiaScrapy.settings import *

class SimpleHash(object):
    def __init__(self, cap, seed):
        self.cap = cap
        self.seed = seed

    def hash(self, value):
        ret = 0
        for i in range(len(value)):
            ret += self.seed * ret + ord(value[i])
        return (self.cap - 1) & ret


class BloomFilter(object):
    def __init__(self, host='localhost', port=6379, db=0, blockNum=1, key='bloomfilter'):
        """
        :param host: the host of Redis
        :param port: the port of Redis
        :param db: witch db in Redis
        :param blockNum: one blockNum for about 90,000,000; if you have more strings for filtering, increase it.
        :param key: the key's name in Redis
        """
        self.server = redis.Redis(host=host, port=port, db=db)
        self.bit_size = 1 << 31  # Redis的String类型最大容量为512M，现使用256M
        self.seeds = [5, 7, 11, 13, 31, 37, 61]
        self.key = key
        self.blockNum = blockNum
        self.hashfunc = []
        for seed in self.seeds:
            self.hashfunc.append(SimpleHash(self.bit_size, seed))

    def isContains(self, str_input):
        if not str_input:
            return False
        m5 = md5()
        #s1.update(upwd.encode("utf8"))  # 指定编码格式，否则会报错
        m5.update(str_input.encode("utf8"))
        str_input = m5.hexdigest()
        ret = True
        name = self.key + str(int(str_input[0:2], 16) % self.blockNum)
        for f in self.hashfunc:
            loc = f.hash(str_input)
            ret = ret & self.server.getbit(name, loc)
        return ret

    def insert(self, str_input):
        m5 = md5()
        m5.update(str_input.encode("utf8"))
        str_input = m5.hexdigest()
        name = self.key + str(int(str_input[0:2], 16) % self.blockNum)
        for f in self.hashfunc:
            loc = f.hash(str_input)
            self.server.setbit(name, loc, 1)

    def close(self):
        self.server.flushdb()
#关闭时清除此数据库
    def __del__(self):
        self.close()


if __name__ == '__main__':
    """ 第一次运行时会显示 not exists!，之后再运行会显示 exists! """
    bf = BloomFilter()
    if bf.isContains('http://www.baidu.com'):   # 判断字符串是否存在
        print('exists!')
    else:
        print('not exists!')
        bf.insert('http://www.baidu.com')