103 lines
4.0 KiB
Python
103 lines
4.0 KiB
Python
# Scrapy settings for linyidzwww 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 = "linyidzwww"
|
||
|
||
SPIDER_MODULES = ["linyidzwww.spiders"]
|
||
NEWSPIDER_MODULE = "linyidzwww.spiders"
|
||
|
||
# 使用scrapy-redis里的去重组件，不使用scrapy默认的去重方式
|
||
#一个去重的类，用来将url去重
|
||
DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"
|
||
#一个队列
|
||
SCHEDULER = "scrapy_redis.scheduler.Scheduler"
|
||
#是否持久化（爬完后不会再爬了，像一些固定的数据）
|
||
SCHEDULER_PERSIST = True
|
||
#你的redis地址
|
||
REDIS_URL = "redis://default:jhkdjhkjdhsIUTYURTU_hFBi3n@192.168.192.217:6379"
|
||
# Crawl responsibly by identifying yourself (and your website) on the user-agent
|
||
USER_AGENT = "Mozilla/5.0 (iPhone; CPU iPhone OS 16_6 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.6 Mobile/15E148 Safari/604.1 Edg/120.0.0.0"
|
||
|
||
# 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,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
|
||
"Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6",
|
||
"User-Agent": "Mozilla/5.0 (iPhone; CPU iPhone OS 16_6 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.6 Mobile/15E148 Safari/604.1 Edg/120.0.0.0"
|
||
}
|
||
|
||
# Enable or disable spider middlewares
|
||
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
|
||
#SPIDER_MIDDLEWARES = {
|
||
# "linyidzwww.middlewares.LinyidzwwwSpiderMiddleware": 543,
|
||
#}
|
||
|
||
# Enable or disable downloader middlewares
|
||
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
|
||
#DOWNLOADER_MIDDLEWARES = {
|
||
# "linyidzwww.middlewares.LinyidzwwwDownloaderMiddleware": 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 = {
|
||
"linyidzwww.pipelines.LinyidzwwwPipeline": 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"
|
||
|
||
# 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"
|