Scrapy——settings配置文件

# -*- coding: utf-8 -*-

# Scrapy settings for tencent project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://doc.scrapy.org/en/latest/topics/settings.html
#     https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://doc.scrapy.org/en/latest/topics/spider-middleware.html

# 项目名
BOT_NAME = 'tencent'

# 爬虫位置
SPIDER_MODULES = ['tencent.spiders']
NEWSPIDER_MODULE = 'tencent.spiders'

# 日志输出
LOG_LEVEL = "INFO"

# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36'

# Robot协议
# Obey robots.txt rules
ROBOTSTXT_OBEY = True

# 设置最大并发请求
# 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://doc.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs

# 每次请求之前的下载延迟
#DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16   #每个域名的最大并发请求数
#CONCURRENT_REQUESTS_PER_IP = 16       #每个ip的最大并发请求数

# 下次请求之前携带之前请求的cookie
# Disable cookies (enabled by default)
#COOKIES_ENABLED = False

# 禁用Telnet控制台（默认启用）
# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False

# 覆盖默认请求头，USER_AGENT在之前，放此处将不起作用
# 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',
#}

# 启用或禁用spider中间件
# Enable or disable spider middlewares
# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'tencent.middlewares.TencentSpiderMiddleware': 543,
#}

# 启用或禁用下载器中间件
# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'tencent.middlewares.TencentDownloaderMiddleware': 543,
#}

#启用或禁用扩展程序
# Enable or disable extensions
# See https://doc.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# 配置项目管道
# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'tencent.pipelines.TencentPipeline': 300,
}

# 启用和配置AutoThrottle扩展（默认情况下禁用）
# Enable and configure the AutoThrottle extension (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True

#初始下载延迟
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5

#在高延迟的情况下设置的最大下载延迟
# 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

#启用显示所收到的每个响应的调节统计信息：
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False

#启用和配置HTTP缓存（默认情况下禁用）
# Enable and configure HTTP caching (disabled by default)
# See https://doc.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'