python - scrapy 爬虫框架 ( redis去重 )

settings 配置
# ############### scrapy redis连接 ####################

REDIS_HOST = ‘140.143.227.206‘                            # 主机名
REDIS_PORT = 8888                                   # 端口
REDIS_PARAMS  = {‘password‘:‘beta‘}                                  # Redis连接参数             默认：REDIS_PARAMS = {‘socket_timeout‘: 30,‘socket_connect_timeout‘: 30,‘retry_on_timeout‘: True,‘encoding‘: REDIS_ENCODING,}）
REDIS_ENCODING = "utf-8"                            # redis编码类型             默认：‘utf-8‘

# REDIS_URL = ‘redis://user:pass@hostname:9001‘       # 连接URL（优先于以上配置）
DUPEFILTER_KEY = ‘dupefilter:%(timestamp)s‘

# DUPEFILTER_CLASS = ‘scrapy_redis.dupefilter.RFPDupeFilter‘
DUPEFILTER_CLASS = ‘dbd.xxx.RedisDupeFilter‘

from scrapy_redis.dupefilter import RFPDupeFilter
from scrapy_redis.connection import get_redis_from_settings
from scrapy_redis import defaults

class RedisDupeFilter(RFPDupeFilter):
    @classmethod
    def from_settings(cls, settings):
        """Returns an instance from given settings.

        This uses by default the key ``dupefilter:<timestamp>``. When using the
        ``scrapy_redis.scheduler.Scheduler`` class, this method is not used as
        it needs to pass the spider name in the key.

        Parameters
        ----------
        settings : scrapy.settings.Settings

        Returns
        -------
        RFPDupeFilter
            A RFPDupeFilter instance.


        """
        server = get_redis_from_settings(settings)
        # XXX: This creates one-time key. needed to support to use this
        # class as standalone dupefilter with scrapy‘s default scheduler
        # if scrapy passes spider on open() method this wouldn‘t be needed
        # TODO: Use SCRAPY_JOB env as default and fallback to timestamp.
        key = defaults.DUPEFILTER_KEY % {‘timestamp‘: ‘这里写 keys‘}
        debug = settings.getbool(‘DUPEFILTER_DEBUG‘)
        return cls(server, key=key, debug=debug)

from scrapy.dupefilter import BaseDupeFilter
import redis
from scrapy.utils.request import request_fingerprint
import scrapy_redis


class DupFilter(BaseDupeFilter):
    def __init__(self):
        self.conn = redis.Redis(host=‘140.143.227.206‘,port=8888,password=‘beta‘)

    def request_seen(self, request):
        """
        检测当前请求是否已经被访问过
        :param request: 
        :return: True表示已经访问过；False表示未访问过
        """
        fid = request_fingerprint(request)
        result = self.conn.sadd(‘visited_urls‘, fid)
        if result == 1:
            return False
        return True