- # -*- coding: utf-8 -*-
- # Scrapy settings for kdlSpider project
- #
- # For simplicity, this file contains only settings considered important or
- # commonly used. You can find more settings consulting the documentation:
- #
- # http://doc.scrapy.org/en/latest/topics/settings.html
- # http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
- # http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
- BOT_NAME = 'kdlSpider'
- SPIDER_MODULES = ['kdlSpider.spiders']
- NEWSPIDER_MODULE = 'kdlSpider.spiders'
- USER_AGENTS = [
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
"Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
"Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) ApplewebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
"Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
"Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.104 Safari/537.36",
"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36 QIHU 360SE",
"Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko"
- ]
- # Crawl responsibly by identifying yourself (and your website) on the user-agent
- #USER_AGENT = 'kdlSpider (+http://www.yourdomain.com)'
- # 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 http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
- # See also autothrottle settings and docs
- # DOWNLOAD_DELAY = 5
- # 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',
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.104 Safari/537.36',
- 'Host':'www.kuaidaili.com',
- }
- # Enable or disable spider middlewares
- # See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
- #SPIDER_MIDDLEWARES = {
- # 'kdlSpider.middlewares.MyCustomSpiderMiddleware': 543,
- #}
- # Enable or disable downloader middlewares
- # See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
- DOWNLOADER_MIDDLEWARES = {
- 'kdlSpider.middlewares.RandomUserAgentMiddleware': 543,
- 'kdlSpider.middlewares.ProxyMiddleware':250,
- }
- # Enable or disable extensions
- # See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
- #EXTENSIONS = {
- # 'scrapy.extensions.telnet.TelnetConsole': None,
- #}
- # Configure item pipelines
- # See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
- ITEM_PIPELINES = {
- 'kdlSpider.pipelines.KdlspiderPipeline': 300,
- }
- # Enable and configure the AutoThrottle extension (disabled by default)
- # See http://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 http://scrapy.readthedocs.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: https://www.cnblogs.com/huangguifeng/p/7635512.html