# Enables scheduling storing requests queue in redis.
SCHEDULER = "scrapy_redis.scheduler.Scheduler"

# Ensure all spiders share same duplicates filter through redis.
DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"

# Enables stats shared based on Redis
STATS_CLASS = "scrapy_redis.stats.RedisStatsCollector"

# Default requests serializer is pickle, but it can be changed to any module
# with loads and dumps functions. Note that pickle is not compatible between
# python versions.
# Caveat: In python 3.x, the serializer must return strings keys and support
# bytes as values. Because of this reason the json or msgpack module will not
# work by default. In python 2.x there is no such issue and you can use
# 'json' or 'msgpack' as serializers.
#SCHEDULER_SERIALIZER = "scrapy_redis.picklecompat"

# Don't cleanup redis queues, allows to pause/resume crawls.
#SCHEDULER_PERSIST = True

# Schedule requests using a priority queue. (default)
#SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.PriorityQueue'

# Alternative queues.
#SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.FifoQueue'
#SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.LifoQueue'

# Max idle time to prevent the spider from being closed when distributed crawling.
# This only works if queue class is SpiderQueue or SpiderStack,
# and may also block the same time when your spider start at the first time (because the queue is empty).
#SCHEDULER_IDLE_BEFORE_CLOSE = 10

# Maximum idle time before close spider.
# When the number of idle seconds is greater than MAX_IDLE_TIME_BEFORE_CLOSE, the crawler will close.
# If 0, the crawler will DontClose forever to wait for the next request.
# If negative number, the crawler will immediately close when the queue is empty, just like Scrapy.
#MAX_IDLE_TIME_BEFORE_CLOSE = 0

# Store scraped item in redis for post-processing.
ITEM_PIPELINES = {
    'scrapy_redis.pipelines.RedisPipeline': 300
}

# The item pipeline serializes and stores the items in this redis key.
#REDIS_ITEMS_KEY = '%(spider)s:items'

# The items serializer is by default ScrapyJSONEncoder. You can use any
# importable path to a callable object.
#REDIS_ITEMS_SERIALIZER = 'json.dumps'

# Specify the host and port to use when connecting to Redis (optional).
#REDIS_HOST = 'localhost'
#REDIS_PORT = 6379

# Specify the full Redis URL for connecting (optional).
# If set, this takes precedence over the REDIS_HOST and REDIS_PORT settings.
#REDIS_URL = 'redis://user:pass@hostname:9001'

# Custom redis client parameters (i.e.: socket timeout, etc.)
#REDIS_PARAMS  = {}
# Use custom redis client class.
#REDIS_PARAMS['redis_cls'] = 'myproject.RedisClient'

# If True, it uses redis' ``SPOP`` operation. You have to use the ``SADD``
# command to add URLs to the redis queue. This could be useful if you
# want to avoid duplicates in your start urls list and the order of
# processing does not matter.
#REDIS_START_URLS_AS_SET = False

# If True, it uses redis ``zrevrange`` and ``zremrangebyrank`` operation. You have to use the ``zadd``
# command to add URLS and Scores to redis queue. This could be useful if you
# want to use priority and avoid duplicates in your start urls list.
#REDIS_START_URLS_AS_ZSET = False

# Default start urls key for RedisSpider and RedisCrawlSpider.
#REDIS_START_URLS_KEY = '%(name)s:start_urls'

# Use other encoding than utf-8 for redis.
#REDIS_ENCODING = 'latin1'

from scrapy_redis.spiders import RedisSpider

class MySpider(RedisSpider):
    name = 'myspider'

    def parse(self, response):
        # do stuff
        pass