You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

99 lines
3.4 KiB
Python

# Scrapy settings for douban_book 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 = "douban_book"
SPIDER_MODULES = ["douban_book.spiders"]
NEWSPIDER_MODULE = "douban_book.spiders"
ADDONS = {}
# Crawl responsibly by identifying yourself (and your website) on the user-agent
# USER_AGENT = "douban_book (+http://www.yourdomain.com)"
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
# Concurrency and throttling settings
# CONCURRENT_REQUESTS = 16
CONCURRENT_REQUESTS_PER_DOMAIN = 1
DOWNLOAD_DELAY = 10
# 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; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36"
}
# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
# SPIDER_MIDDLEWARES = {
# "douban_book.middlewares.DoubanBookSpiderMiddleware": 543,
# }
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
RETRY_ENABLED = True
RETRY_TIMES = 2 # 重试3次
RETRY_HTTP_CODES = [500, 502, 503, 504, 408, 400] # 增加了一些常见的错误码
DOWNLOADER_MIDDLEWARES = {
'scrapy.downloadermiddlewares.retry.RetryMiddleware': 550,
# "douban_book.middlewares.DoubanBookDownloaderMiddleware": 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 = {
"douban_book.pipelines.DoubanBookPipeline": 300,
"douban_book.pipelines.DoubanBookInfoStandard": 400,
"douban_book.pipelines.MongoPipeline": 410,
}
MONGO_URI = "mongodb://root:123456@192.168.1.211:27017/"
MONGO_DATABASE = "science2"
REDIS_URL = 'redis://:kcidea1509@192.168.1.211:6379/10'
# 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
FEED_EXPORT_ENCODING = "utf-8"