- # -*- coding: utf-8 -*-
- # Scrapy settings for maitian 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
- BOT_NAME = 'maitian'
- SPIDER_MODULES = ['maitian.spiders']
- NEWSPIDER_MODULE = 'maitian.spiders'
- # 不能批量设置
- # Crawl responsibly by identifying yourself (and your website) on the user-agent
- USER_AGENT = 'maitian (+http://www.yourdomain.com)'
- # 默认遵守 robots 协议
- # Obey robots.txt rules
- ROBOTSTXT_OBEY = False
- # 设置日志文件
- LOG_FILE="maitian.log"
- # 日志等级分为 5 种: 1.DEBUG 2.INFO 3.Warning 4.ERROR 5.CRITICAL
- # 等级越高 输出的日志越少
- # LOG_LEVEL="INFO"
- #scrapy 设置最大并发数 默认 16
- # Configure maximum concurrent requests performed by Scrapy (default: 16)
- #CONCURRENT_REQUESTS = 32
- # 设置批量延迟请求 16 等待 3 秒再发 16 秒
- # 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
- #DOWNLOAD_DELAY = 3
- # The download delay setting will honor only one of:
- #CONCURRENT_REQUESTS_PER_DOMAIN = 16
- #CONCURRENT_REQUESTS_PER_IP = 16
- #cookie 不生效 默认是 True
- # Disable cookies (enabled by default)
- #COOKIES_ENABLED = False
- # 远程
- # Disable Telnet Console (enabled by default)
- #TELNETCONSOLE_ENABLED = False
- # 加载默认的请求头
- # 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',
- #
- }
- # 爬虫中间件
- # Enable or disable spider middlewares
- # See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
- #SPIDER_MIDDLEWARES = {
- # 'maitian.middlewares.MaitianSpiderMiddleware': 543,
- #
- }
- # 下载中间件
- # Enable or disable downloader middlewares
- # See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
- #DOWNLOADER_MIDDLEWARES = {
- # 'maitian.middlewares.MaitianDownloaderMiddleware': 543,
- #
- }
- # Enable or disable extensions
- # See https://doc.scrapy.org/en/latest/topics/extensions.html
- #EXTENSIONS = {
- # 'scrapy.extensions.telnet.TelnetConsole': None,
- #
- }
- # 在配置文件 开启管道
- # 优先级的范围 0--1000; 值越小 优先级越高
- # Configure item pipelines
- # See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
- #ITEM_PIPELINES = {
- # 'maitian.pipelines.MaitianPipeline': 300,
- #
- }
- # Enable and configure the AutoThrottle extension (disabled by default)
- # See https://doc.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://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'
来源: http://www.bubuko.com/infodetail-3280922.html