# REDIS_HOST = 'localhost' # 主机名 # REDIS_PORT = 6379 # 端口 # REDIS_URL = 'redis://user:pass@hostname:9001' # 连接URL（优先于以上配置） # REDIS_PARAMS = {} # Redis连接参数 默认：REDIS_PARAMS = {'socket_timeout': 30,'socket_connect_timeout': 30,'retry_on_timeout': True,'encoding': REDIS_ENCODING,}） # REDIS_PARAMS['redis_cls'] = 'myproject.RedisClient' # 指定连接Redis的Python模块 默认：redis.StrictRedis # REDIS_ENCODING = "utf-8" # redis编码类型 默认：'utf-8' b. 去重规则通过redis的集合完成，集合的Key为： key = defaults.DUPEFILTER_KEY % {'timestamp': int(time.time())} 默认配置： DUPEFILTER_KEY = 'dupefilter:%(timestamp)s' c. 去重规则中将url转换成唯一标示，然后在redis中检查是否已经在集合中存在 from scrapy.utils import request from scrapy.http import Request req = Request(url='http://www.cnblogs.com/wupeiqi.html') result = request.request_fingerprint(req) print(result) # 8ea4fd67887449313ccc12e5b6b92510cc53675c - URL参数位置不同时，计算结果一致； - 默认请求头不在计算范围，include_headers可以设置指定请求头 from scrapy.utils import request from scrapy.http import Request req = Request(url='http://www.baidu.com?name=8&id=1',callback=lambda x:print(x),cookies={'k1':'vvvvv'}) result = request.request_fingerprint(req,include_headers=['cookies',]) print(result) req = Request(url='http://www.baidu.com?id=1&name=8',callback=lambda x:print(x),cookies={'k1':666}) result = request.request_fingerprint(req,include_headers=['cookies',]) print(result) # Ensure all spiders share same duplicates filter through redis. # DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"

2. 调度器

调度器，调度器使用PriorityQueue（有序集合）、FifoQueue（列表）、LifoQueue（列表）进行保存请求，并且使用RFPDupeFilter对URL去重 a. 调度器 SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.PriorityQueue' # 默认使用优先级队列（默认），其他：PriorityQueue（有序集合），FifoQueue（列表）、LifoQueue（列表） SCHEDULER_QUEUE_KEY = '%(spider)s:requests' # 调度器中请求存放在redis中的key SCHEDULER_SERIALIZER = "scrapy_redis.picklecompat" # 对保存到redis中的数据进行序列化，默认使用pickle SCHEDULER_PERSIST = True # 是否在关闭时候保留原来的调度器和去重记录，True=保留，False=清空 SCHEDULER_FLUSH_ON_START = True # 是否在开始之前清空 调度器和去重记录，True=清空，False=不清空 SCHEDULER_IDLE_BEFORE_CLOSE = 10 # 去调度器中获取数据时，如果为空，最多等待时间（最后没数据，未获取到）。 SCHEDULER_DUPEFILTER_KEY = '%(spider)s:dupefilter' # 去重规则，在redis中保存时对应的key SCHEDULER_DUPEFILTER_CLASS = 'scrapy_redis.dupefilter.RFPDupeFilter'# 去重规则对应处理的类 # Enables scheduling storing requests queue in redis. SCHEDULER = "scrapy_redis.scheduler.Scheduler" # 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

3. 数据持久化

2. 定义持久化，爬虫yield Item对象时执行RedisPipeline
    a. 将item持久化到redis时，指定key和序列化函数
        REDIS_ITEMS_KEY = '%(spider)s:items'
        REDIS_ITEMS_SERIALIZER = 'json.dumps'
    b. 使用列表保存item数据
4. 起始URL相关
起始URL相关
    a. 获取起始URL时，去集合中获取还是去列表中获取？True，集合；False，列表
        REDIS_START_URLS_AS_SET = False    # 获取起始URL时，如果为True，则使用self.server.spop；如果为False，则使用self.server.lpop
    b. 编写爬虫时，起始URL从redis的Key中获取
        REDIS_START_URLS_KEY = '%(name)s:start_urls'
# If True, it uses redis' ``spop`` operation. This could be useful if you
# want to avoid duplicates in your start urls list. In this cases, urls must
# be added via ``sadd`` command or you will get a type error from redis.
# REDIS_START_URLS_AS_SET = False
# Default start urls key for RedisSpider and RedisCrawlSpider.
# REDIS_START_URLS_KEY = '%(name)s:start_urls'

scrapy-redis示例

# DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"
# from scrapy_redis.scheduler import Scheduler
# from scrapy_redis.queue import PriorityQueue
# SCHEDULER = "scrapy_redis.scheduler.Scheduler"
# SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.PriorityQueue'          # 默认使用优先级队列（默认），其他：PriorityQueue（有序集合），FifoQueue（列表）、LifoQueue（列表）
# SCHEDULER_QUEUE_KEY = '%(spider)s:requests'                         # 调度器中请求存放在redis中的key
# SCHEDULER_SERIALIZER = "scrapy_redis.picklecompat"                  # 对保存到redis中的数据进行序列化，默认使用pickle
# SCHEDULER_PERSIST = True                                            # 是否在关闭时候保留原来的调度器和去重记录，True=保留，False=清空
# SCHEDULER_FLUSH_ON_START = False                                    # 是否在开始之前清空 调度器和去重记录，True=清空，False=不清空
# SCHEDULER_IDLE_BEFORE_CLOSE = 10                                    # 去调度器中获取数据时，如果为空，最多等待时间（最后没数据，未获取到）。
# SCHEDULER_DUPEFILTER_KEY = '%(spider)s:dupefilter'                  # 去重规则，在redis中保存时对应的key
# SCHEDULER_DUPEFILTER_CLASS = 'scrapy_redis.dupefilter.RFPDupeFilter'# 去重规则对应处理的类
# REDIS_HOST = '10.211.55.13'                           # 主机名
# REDIS_PORT = 6379                                     # 端口
# # REDIS_URL = 'redis://user:pass@hostname:9001'       # 连接URL（优先于以上配置）
# # REDIS_PARAMS  = {}                                  # Redis连接参数             默认：REDIS_PARAMS = {'socket_timeout': 30,'socket_connect_timeout': 30,'retry_on_timeout': True,'encoding': REDIS_ENCODING,}）
# # REDIS_PARAMS['redis_cls'] = 'myproject.RedisClient' # 指定连接Redis的Python模块  默认：redis.StrictRedis
# REDIS_ENCODING = "utf-8"                              # redis编码类型             默认：'utf-8'

import scrapy
class ChoutiSpider(scrapy.Spider):
    name = "chouti"
    allowed_domains = ["chouti.com"]
    start_urls = (
        'http://www.chouti.com/',
    def parse(self, response):
        for i in range(0,10):
            yield