nmcSpider/nmc/settings.py

# Scrapy settings for nmc 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 = "nmc"

SPIDER_MODULES = ["nmc.spiders"]
NEWSPIDER_MODULE = "nmc.spiders"

# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36 Edg/125.0.0.0"
REACTOR = 'twisted.internet.selectreactor.SelectReactor'
LOG_LEVEL = 'ERROR'
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
# Configure maximum concurrent requests performed by Scrapy (default: 16)
CONCURRENT_REQUESTS = 32
RETRY_TIMES = 3  # 请求失败时重试次数
DOWNLOAD_TIMEOUT = 15  # 默认下载超时时间，单位秒
# 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 = 1
RANDOMIZE_DOWNLOAD_DELAY = True
# The download delay setting will honor only one of:
# CONCURRENT_REQUESTS_PER_DOMAIN = 16
# CONCURRENT_REQUESTS_PER_IP = 16
# 配置置日志级别，DEBUG, INFO, WARNING, ERROR等，默认为WARNING

# 配置置日志格式
LOG_FORMAT = '%(asctime)s [%(name)s] %(levelname)s: %(message)s'

# 自定义一个文件处理器，将日志写入文件
LOG_FILE = 'logs/scrapy.log'  # 指定日志文件路径，相对或绝对路径

# 配置日志处理器，这里只配置了一个文件处理器
LOG_HANDLERS = {
    'file': {
        'class': 'logging.FileHandler',
        'formatter': 'default',
        'filename': LOG_FILE,
    },
}

# 定义日志处理器格式化器
LOG_FORMATTERS = {
    'default': {
        'format': LOG_FORMAT,
        'datefmt': '%Y-%m-%d %H:%M:%S',
    },
}

# 配置日志处理器字典，定义哪些logger使用哪些处理器
LOGGGER_DELEGATION = {
    'scrapy': {
        'handlers': ['file'],
        'level': LOG_LEVEL,
        'propagate': False,  # 不传播给父logger
    },
    'twisted.core.engine': {  # 可以类似方式配置其他核心组件
        'handlers': ['file'],
        'level': LOG_LEVEL,
        'propagate': False,
    },
}
# 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 = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36',
    '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 = {
#     "nmc.middlewares.NmcSpiderMiddleware": 543,
# }

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
# DOWNLOADER_MIDDLEWARES = {
#     # "nmc.middlewares.NmcDownloaderMiddleware": 543,
#     "nmc.middlewares.SeleniumDownloaderMiddleware": 543,
#     'scrapy.downloadermiddlewares.useragent.UseragentMiddleware': None
# }

# 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 = {
    "nmc.pipelines.NmcPipeline": 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"