From 3b4077a50c0d6cf73fdd5cf4b955846e61dd850f Mon Sep 17 00:00:00 2001 From: pmh9c3ri2 <1306209041@qq.com> Date: Fri, 22 Apr 2022 10:48:47 +0800 Subject: [PATCH] ADD file via upload --- settings.py | 134 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 134 insertions(+) create mode 100644 settings.py diff --git a/settings.py b/settings.py new file mode 100644 index 0000000..b8a7dd4 --- /dev/null +++ b/settings.py @@ -0,0 +1,134 @@ +# Scrapy settings for VulCrawl 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 +import random + +CUSTOM_USER_AGENT = [ + "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)", + "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)", + "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)", + "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)", + "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 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6", + "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11", + "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20", + "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52", +] + +BOT_NAME = 'VulCrawl' + +SPIDER_MODULES = ['VulCrawl.spiders'] +NEWSPIDER_MODULE = 'VulCrawl.spiders' + +USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1' +#USER_AGENT = random.choice(CUSTOM_USER_AGENT) +# Crawl responsibly by identifying yourself (and your website) on the user-agent +#USER_AGENT = 'VulCrawl (+http://www.yourdomain.com)' + +# Obey robots.txt rules +ROBOTSTXT_OBEY = False +#LOG_LEVEL = 'ERROR' + +# 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://docs.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://docs.scrapy.org/en/latest/topics/spider-middleware.html +#SPIDER_MIDDLEWARES = { +# 'VulCrawl.middlewares.VulcrawlSpiderMiddleware': 543, +#} + +# Enable or disable downloader middlewares +# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html +#DOWNLOADER_MIDDLEWARES = { +# 'VulCrawl.middlewares.VulcrawlDownloaderMiddleware': 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 = { +# 'VulCrawl.pipelines.VulcrawlPipeline': 300, +# } + +ITEM_PIPELINES = { + 'scrapy_redis.pipelines.RedisPipeline': 400, + #'VulCrawl.pipelines.VulcrawlPipeline': 300, +} +# 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' + +# 把scrapy中默认的去重组件替换为scrapy-redis中的去重组件 + +DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter" +# 把scrapy中默认的调度器替换成scrapy-redis中的调度器 +SCHEDULER = "scrapy_redis.scheduler.Scheduler" + +# 任务持久化 +SCHEDULER_PERSIST = True +SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.PriorityQueue' +# REDIS_HOST = '106.55.35.173' +# REDIS_PORT = 6379 +# REDIS_PARAMS = { +# 'password': 'lsylth', +# } + +# DOWNLOADER_MIDDLEWARES = { +# 'VulCrawl.middlewares.UserAgentMiddleware': 300, +# 'VulCrawl.middlewares.VulcrawlSpiderMiddleware': 543, +# }