You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
102 lines
3.3 KiB
102 lines
3.3 KiB
|
|
BOT_NAME = 'spider'
|
|
|
|
SPIDER_MODULES = ['spider.spiders']
|
|
NEWSPIDER_MODULE = 'spider.spiders'
|
|
|
|
# Crawl responsibly by identifying yourself (and your website) on the user-agent
|
|
# USER_AGENT = 'spider (+http://www.yourdomain.com)'
|
|
|
|
# scrapy-redis
|
|
# 去重
|
|
DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"
|
|
# 使用scrapy_redis的调度器
|
|
SCHEDULER = "scrapy_redis.scheduler.Scheduler"
|
|
# 是否允许暂停
|
|
SCHEDULER_PERSIST = True
|
|
|
|
# Obey robots.txt rules
|
|
ROBOTSTXT_OBEY = True
|
|
|
|
# Configure maximum concurrent requests performed by Scrapy (default: 16)
|
|
# CONCURRENT_REQUESTS = 32
|
|
|
|
# Configure a delay for requests for the same website (default: 0)
|
|
# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
|
|
# See also autothrottle settings and docs
|
|
|
|
DOWNLOAD_DELAY = 3 #延迟时间
|
|
RANDOMIZE_DOWNLOAD_DELAY = True # 随机延迟开关
|
|
|
|
# The download delay setting will honor only one of:
|
|
# CONCURRENT_REQUESTS_PER_DOMAIN = 16
|
|
# CONCURRENT_REQUESTS_PER_IP = 16
|
|
|
|
# Disable cookies (enabled by default)
|
|
# COOKIES_ENABLED = False
|
|
|
|
# Disable Telnet Console (enabled by default)
|
|
# TELNETCONSOLE_ENABLED = False
|
|
|
|
# Override the default request headers:
|
|
# DEFAULT_REQUEST_HEADERS = {
|
|
# 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
|
|
# 'Accept-Language': 'en',
|
|
# }
|
|
|
|
# Enable or disable spider middlewares
|
|
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
|
|
# SPIDER_MIDDLEWARES = {
|
|
# 'spider.middlewares.SpiderSpiderMiddleware': 543,
|
|
# }
|
|
|
|
# Enable or disable downloader middlewares
|
|
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
|
|
DOWNLOADER_MIDDLEWARES = {
|
|
'spider.middlewares.SpiderDownloaderMiddleware': 543,
|
|
# 'spider.middlewares.ProxyMiddleware': 600,
|
|
|
|
|
|
}
|
|
|
|
# Enable or disable extensions
|
|
# See https://docs.scrapy.org/en/latest/topics/extensions.html
|
|
# EXTENSIONS = {
|
|
# 'scrapy.extensions.telnet.TelnetConsole': None,
|
|
# }
|
|
|
|
# Configure item pipelines
|
|
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
|
|
ITEM_PIPELINES = {
|
|
# 'spider.pipelines.ExcelPipeline': 300,
|
|
'spider.pipelines.MysqlPipeline': 300,
|
|
|
|
# 使用scrapy_redis的管道
|
|
'scrapy_redis.pipelines.RedisPipeline': 400,
|
|
}
|
|
|
|
# Enable and configure the AutoThrottle extension (disabled by default)
|
|
# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
|
|
# AUTOTHROTTLE_ENABLED = True
|
|
# The initial download delay
|
|
# AUTOTHROTTLE_START_DELAY = 5
|
|
# The maximum download delay to be set in case of high latencies
|
|
# AUTOTHROTTLE_MAX_DELAY = 60
|
|
# The average number of requests Scrapy should be sending in parallel to
|
|
# each remote server
|
|
# AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
|
|
# Enable showing throttling stats for every response received:
|
|
# AUTOTHROTTLE_DEBUG = False
|
|
|
|
# Enable and configure HTTP caching (disabled by default)
|
|
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
|
|
# HTTPCACHE_ENABLED = True
|
|
# HTTPCACHE_EXPIRATION_SECS = 0
|
|
# HTTPCACHE_DIR = 'httpcache'
|
|
# HTTPCACHE_IGNORE_HTTP_CODES = []
|
|
# HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
|
|
|
|
# Set settings whose default value is deprecated to a future-proof value
|
|
REQUEST_FINGERPRINTER_IMPLEMENTATION = '2.7'
|
|
TWISTED_REACTOR = 'twisted.internet.asyncioreactor.AsyncioSelectorReactor'
|