# Scrapy settings for demo1 project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
# https://docs.scrapy.org/en/latest/topics/settings.html
# https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
BOT_NAME = 'demo1' # 项目名
SPIDER_MODULES = ['demo1.spiders'] #
NEWSPIDER_MODULE = 'demo1.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'demo1 (+http://www.yourdomain.com)' # 这个可以浏览器抓包查看值 比较重要 一般都要带的
# Obey robots.txt rules
ROBOTSTXT_OBEY = False # 机器人规则 默认是 true 一般都要修改为 false 否则几乎爬不了太多东西
# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32 # 最大并发数 可以开启的爬虫线程数
# 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 = 1 # 下载延迟时间，单位是秒，默认是 3 秒，即爬一个停 3 秒，设置为 1 秒性价比较高，如果要爬取的文件较多，写零点几秒也行
# 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 # 是否保存 COOKIES ，默认关闭，开机可以记录爬取过程中的 COKIE ，非常好用的一个参数
# 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',
#} # 默认请求头，上面写了一个 USER_AGENT ，其实这个东西就是放在请求头里面的，这个东西可以根据你爬取的内容做相应设置。
# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'demo1.middlewares.Demo1SpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'demo1.middlewares.Demo1DownloaderMiddleware': 543,
#}
# 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 = {
#'demo1.pipelines.Demo1Pipeline': 300,
#'demo1.pipelines.Demo1MySqlPipeline' : 200,
#} # 项目管道， 300 为优先级，外汇跟单gendan5.com越低爬取的优先度越高 pipelines.py 里面写了两个管道，一个爬取网页的管道，一个存数据库的管道，我调整了他们的优先级，如果有爬虫数据，优先执行存库操作。
# 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'