#1、项目名称，默认的USER_AGENT由它来构成，也作为日志记录的日志名
BOT_NAME = ‘Amazon‘

#2、爬虫应用路径
SPIDER_MODULES = [‘Amazon.spiders‘]
NEWSPIDER_MODULE = ‘Amazon.spiders‘

#3、客户端User-Agent请求头
#USER_AGENT = ‘Amazon (+http://www.yourdomain.com)‘

#4、是否遵循爬虫协议
# Obey robots.txt rules
ROBOTSTXT_OBEY = False

#5、是否支持cookie，cookiejar进行操作cookie，默认开启
#COOKIES_ENABLED = False

#6、Telnet用于查看当前爬虫的信息，操作爬虫等...使用telnet ip port ，然后通过命令操作
#TELNETCONSOLE_ENABLED = False
#TELNETCONSOLE_HOST = ‘127.0.0.1‘
#TELNETCONSOLE_PORT = [6023,]

#7、Scrapy发送HTTP请求默认使用的请求头
#DEFAULT_REQUEST_HEADERS = {
# ‘Accept‘: ‘text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8‘,
# ‘Accept-Language‘: ‘en‘,
#}

#1、下载器总共最大处理的并发请求数,默认值16
#CONCURRENT_REQUESTS = 32

#2、每个域名能够被执行的最大并发请求数目，默认值8
#CONCURRENT_REQUESTS_PER_DOMAIN = 16

#3、能够被单个IP处理的并发请求数，默认值0，代表无限制，需要注意两点
#I、如果不为零，那CONCURRENT_REQUESTS_PER_DOMAIN将被忽略，即并发数的限制是按照每个IP来计算，而不是每个域名
#II、该设置也影响DOWNLOAD_DELAY，如果该值不为零，那么DOWNLOAD_DELAY下载延迟是限制每个IP而不是每个域
#CONCURRENT_REQUESTS_PER_IP = 16

#4、如果没有开启智能限速，这个值就代表一个规定死的值，代表对同一网址延迟请求的秒数
#DOWNLOAD_DELAY = 3

from scrapy.contrib.throttle import AutoThrottle

#http://scrapy.readthedocs.io/en/latest/topics/autothrottle.html#topics-autothrottle

#1、spiders开始时的下载延迟是基于AUTOTHROTTLE_START_DELAY的值
#2、当收到一个response，对目标站点的下载延迟=收到响应的延迟时间/AUTOTHROTTLE_TARGET_CONCURRENCY
#3、下一次请求的下载延迟就被设置成：对目标站点下载延迟时间和过去的下载延迟时间的平均值
#4、没有达到200个response则不允许降低延迟
#5、下载延迟不能变的比DOWNLOAD_DELAY更低或者比AUTOTHROTTLE_MAX_DELAY更高

#开启智能限速 True，默认False
AUTOTHROTTLE_ENABLED = True

#起始的延迟
AUTOTHROTTLE_START_DELAY = 5

#最小延迟
DOWNLOAD_DELAY = 3

#最大延迟
AUTOTHROTTLE_MAX_DELAY = 10  

#每秒并发请求数的平均值，不能高于 CONCURRENT_REQUESTS_PER_DOMAIN或CONCURRENT_REQUESTS_PER_IP，调高了则吞吐量增大强奸目标站点，调低了则对目标站点更加”礼貌“
#每个特定的时间点，scrapy并发请求的数目都可能高于或低于该值，这是爬虫视图达到的建议值而不是硬限制
AUTOTHROTTLE_TARGET_CONCURRENCY = 16.0


#调试
AUTOTHROTTLE_DEBUG = True
CONCURRENT_REQUESTS_PER_DOMAIN = 16
CONCURRENT_REQUESTS_PER_IP = 16

#1、爬虫允许的最大深度，可以通过meta查看当前深度；0表示无深度
# DEPTH_LIMIT = 3

#2、爬取时，0表示深度优先Lifo(默认)；1表示广度优先FiFo

# 后进先出，深度优先
# DEPTH_PRIORITY = 0
# SCHEDULER_DISK_QUEUE = ‘scrapy.squeue.PickleLifoDiskQueue‘
# SCHEDULER_MEMORY_QUEUE = ‘scrapy.squeue.LifoMemoryQueue‘
# 先进先出，广度优先

# DEPTH_PRIORITY = 1
# SCHEDULER_DISK_QUEUE = ‘scrapy.squeue.PickleFifoDiskQueue‘
# SCHEDULER_MEMORY_QUEUE = ‘scrapy.squeue.FifoMemoryQueue‘


#3、调度器队列
# SCHEDULER = ‘scrapy.core.scheduler.Scheduler‘
# from scrapy.core.scheduler import Scheduler

#4、访问URL去重
# DUPEFILTER_CLASS = ‘step8_king.duplication.RepeatUrl‘

#1、Enable or disable spider middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# ‘Amazon.middlewares.AmazonSpiderMiddleware‘: 543,
#}

#2、Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
# ‘Amazon.middlewares.DownMiddleware1‘: 543,
}

#3、Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
#EXTENSIONS = {
# ‘scrapy.extensions.telnet.TelnetConsole‘: None,
#}

#4、Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
# ‘Amazon.pipelines.CustomPipeline‘: 200,
}

"""
1. 启用缓存
目的用于将已经发送的请求或相应缓存下来，以便以后使用

from scrapy.downloadermiddlewares.httpcache import HttpCacheMiddleware
from scrapy.extensions.httpcache import DummyPolicy
from scrapy.extensions.httpcache import FilesystemCacheStorage
"""
# 是否启用缓存策略
# HTTPCACHE_ENABLED = True

# 缓存策略：所有请求均缓存，下次在请求直接访问原来的缓存即可
# HTTPCACHE_POLICY = "scrapy.extensions.httpcache.DummyPolicy"
# 缓存策略：根据Http响应头：Cache-Control、Last-Modified 等进行缓存的策略
# HTTPCACHE_POLICY = "scrapy.extensions.httpcache.RFC2616Policy"

# 缓存超时时间
# HTTPCACHE_EXPIRATION_SECS = 0

# 缓存保存路径
# HTTPCACHE_DIR = ‘httpcache‘

# 缓存忽略的Http状态码
# HTTPCACHE_IGNORE_HTTP_CODES = []

# 缓存存储的插件
# HTTPCACHE_STORAGE = ‘scrapy.extensions.httpcache.FilesystemCacheStorage‘