zoukankan      html  css  js  c++  java
  • 可配置智联爬虫

    settings.py
    # -*- coding: utf-8 -*-
    
    # Scrapy settings for review_spider 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 = 'review_spider'
    
    SPIDER_MODULES = ['review_spider.spiders']
    NEWSPIDER_MODULE = 'review_spider.spiders'
    
    
    # Crawl responsibly by identifying yourself (and your website) on the user-agent
    #USER_AGENT = 'review_spider (+http://www.yourdomain.com)'
    
    # Obey robots.txt rules
    ROBOTSTXT_OBEY = False
    
    # 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
    DOWNLOAD_DELAY = 3
    # 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://doc.scrapy.org/en/latest/topics/spider-middleware.html
    #SPIDER_MIDDLEWARES = {
    #    'review_spider.middlewares.ReviewSpiderSpiderMiddleware': 543,
    #}
    
    # Enable or disable downloader middlewares
    # See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
    DOWNLOADER_MIDDLEWARES = {
       #'review_spider.middlewares.ReviewSpiderDownloaderMiddleware': 543,
        'review_spider.middlewares.SeleniumMiddleware': 520,
    
    }
    
    # Enable or disable extensions
    # See https://doc.scrapy.org/en/latest/topics/extensions.html
    #EXTENSIONS = {
    #    'scrapy.extensions.telnet.TelnetConsole': None,
    #}
    
    # Configure item pipelines
    # See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
    ITEM_PIPELINES = {
       'review_spider.pipelines.ReviewSpiderPipeline': 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'
    LOG_FILE = "ZhilianSpiderSpider.log"
    LOG_LEVEL = "INFO"
    # LOG_STDOUT=True
    LOG_LEVEL_1 = "ERROR"

  • 相关阅读:
    Java基础学习总结(41)——JPA常用注解
    Java基础学习总结(41)——JPA常用注解
    【云速建站】视频播放专题
    一招教你如何修复MySQL slave中继日志损坏问题
    【nodejs原理&源码赏析(3)】欣赏手术级的原型链加工艺术
    【云速建站】后台数据批量导入导出
    【云速建站】会员注册弹窗添加及设置
    【nodejs原理&源码赏析(2)】KOA中间件的基本运作原理
    【nodejs原理&源码赏析(1)】Express中间件系统的基本实现
    补习系列(5)-springboot- restful应用
  • 原文地址:https://www.cnblogs.com/liangliangzz/p/10257707.html
Copyright © 2011-2022 走看看