2025-05-28 19:16:17 +08:00

144 lines
5.1 KiB
Python

# -*- coding: utf-8 -*-
BOT_NAME = 'ShipSpiders'
SPIDER_MODULES = ['ShipSpiders.spiders']
NEWSPIDER_MODULE = 'ShipSpiders.spiders'
LOG_ENABLED = True
LOG_ENCODING = 'utf-8'
LOG_FILE = None
LOG_LEVEL = 'INFO'
LOG_STDOUT = False
RETENTION_HOURS = 120
UPDATE_COOKIES_AFTER_REQUEST_COUNT = 3000
# 生产环境配置
DECODE_SERVICE = 'http://172.20.214.61:28085/api/decode'
TRACK_DECODE_SERVICE = 'http://172.20.214.61:28085/api/decode_track'
KAFKA_SERVER = '47.113.231.200:9092'
REDIS_HOST = '107.182.191.3'
REDIS_PORT = 7379
REDIS_PWD = 'jlkj-841-2-redis'
SENSITIVE_SHIP_QUERY_API = 'http://47.115.228.133:28081/api/open/sensitiveTarget/query'
SHIPXY_LOGIN_ACCOUNT = 'jlit_yuxin'
SHIPXY_LOGIN_PASSWD = 'passok'
# SELENIUM_DRIVER_EXECUTABLE_PATH = 'http://172.20.0.15:4444/wd/hub'
# SELENIUM_DRIVER_NAME = 'firefox'
# SELENIUM_DRIVER_ARGUMENTS = ['-headless']
SELENIUM_DRIVER_NAME = 'edge'
SELENIUM_DRIVER_EXECUTABLE_PATH = 'http://172.20.214.61:28088'
# SELENIUM_DRIVER_EXECUTABLE_PATH = "MicrosoftWebDriver.exe"
# '--headless' if using chrome instead of firefox
SELENIUM_DRIVER_ARGUMENTS = [
'--headless',
# '--start-maximized',
'--no-sandbox',
'--disable-dev-shm-usage',
'--disable-gpu'
]
CRAWL_JOB_UPDATE_API = 'http://47.115.228.133:28081/api/open/crawljob'
KAFKA_PROCESS_QUEUE = ['stream-protobuf']
DOWNLOADER_MIDDLEWARES = {
'ShipSpiders.middlewares.UserAgentDownloaderMiddleware': 101,
'ShipSpiders.scrapy_selenium.middlewares.SeleniumMiddleware': 105
}
EXTENSIONS = {
'ShipSpiders.extensions.SetCrawlerStatusExtensions': 501
}
PROXY_SERVICE = 'http://39.101.194.63:6800/'
PER_BATCH_IP_USE_TIMES = 50
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
CUSTOM_USER_AGENT = [
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36',
'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:77.0) Gecko/20100101 Firefox/77.0',
'Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko',
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.18363',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
'Opera/9.80 (Windows NT 6.1; U; zh-cn) Presto/2.9.168 Version/11.50',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; .NET4.0E; SE 2.X MetaSr 1.0',
'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; .NET4.0E',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.41 Safari/535.1 QQBrowser/6.9.11079.201'
]
# 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 = 0.1
# 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 = {
# 'ShipSpiders.middlewares.DumpFiliterSpiderMiddleware': 543,
# }
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
# DOWNLOADER_MIDDLEWARES = {
# }
# 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 = {
# 'ShipSpiders.pipelines.ShipspidersPipeline': 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'