newsspider/decspider/settings.py
2024-05-17 13:49:44 +08:00

115 lines
3.7 KiB
Python

# Scrapy settings for decspider 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
BOT_NAME = "decspider"
SPIDER_MODULES = ["decspider.spiders"]
NEWSPIDER_MODULE = "decspider.spiders"
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = "decspider (+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://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 = {
# "decspider.middlewares.DecspiderSpiderMiddleware": 543,
#}
DOWNLOADER_MIDDLEWARES = {
"decspider.middlewares.ProxyMiddleware": 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 = {
'decspider.pipelines.DecspiderPipeline': 300,
'crawlab.CrawlabPipeline': 888,
}
# 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"
# Set settings whose default value is deprecated to a future-proof value
REQUEST_FINGERPRINTER_IMPLEMENTATION = "2.7"
TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor"
FEED_EXPORT_ENCODING = "utf-8"
# Proxy setting
SECRETID = "oadugxyl9fhoqsamqopc"
SECRETKEY = "j2gugufp2batb8y2olw9la1cptxfapko"
USERNAME = "d2667352953"
PASSWORD = "m93ih6hh"
PROXYPOOL_UPDATENUM = 1
PROXYPOOL_MIN_NUM = 3
PROXYPOOL_MIN_DURATION = 1
# MySQL Configuration
MYSQL_USERNAME = "root"
MYSQL_PASSWORD = "yGWptA_tX4bZ2q"
MYSQL_HOST = "10.18.30.148"
MYSQL_PORT = 3307
MYSQL_DATABASE = "crawler_data"
# Test
CLOSESPIDER_PAGECOUNT = 5