108 lines
3.9 KiB
Python
108 lines
3.9 KiB
Python
# Scrapy settings for zcspider 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 = "zcspider"
|
|
|
|
SPIDER_MODULES = ["zcspider.spiders"]
|
|
NEWSPIDER_MODULE = "zcspider.spiders"
|
|
|
|
|
|
# Crawl responsibly by identifying yourself (and your website) on the user-agent
|
|
#USER_AGENT = "zcspider (+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,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',
|
|
'Cache-Control': 'max-age=0',
|
|
'Proxy-Connection': 'keep-alive',
|
|
'Referer': 'https://www.baidu.com/',
|
|
'Upgrade-Insecure-Requests': '1',
|
|
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36 Edg/112.0.1722.48',
|
|
}
|
|
|
|
# Enable or disable spider middlewares
|
|
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
|
|
#SPIDER_MIDDLEWARES = {
|
|
# "zcspider.middlewares.ZcspiderSpiderMiddleware": 543,
|
|
#}
|
|
|
|
# Enable or disable downloader middlewares
|
|
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
|
|
#DOWNLOADER_MIDDLEWARES = {
|
|
# "zcspider.middlewares.ZcspiderDownloaderMiddleware": 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 = {
|
|
# "zcspider.pipelines.ZcspiderPipeline": 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 = 'gb18030'
|
|
LOG_LEVEL = 'ERROR'
|
|
DOWNLOAD_TIMEOUT = 10
|
|
|
|
ITEM_PIPELINES = {
|
|
# 'zcspider.pipelines.ZcspiderPipeline': 300,
|
|
}
|
|
|
|
FEED_EXPORTERS = {
|
|
'xlsx': 'scrapy_xlsx.XlsxItemExporter',
|
|
} |