Scrapy——settings配置文件

# -*- coding: utf-8 -*-

# Scrapy settings for tencent project # # For simplicity, this file contains only settings considered important or # commonly used. You can find more settings consulting the documentation: # # https://doc.scrapy.org/en/latest/topics/settings.html # https://doc.scrapy.org/en/latest/topics/downloader-middleware.html # https://doc.scrapy.org/en/latest/topics/spider-middleware.html

# 項目名
BOT_NAME = 'tencent'

# 爬蟲位置
SPIDER_MODULES = ['tencent.spiders'] NEWSPIDER_MODULE = 'tencent.spiders'

# 日誌輸出
LOG_LEVEL = "INFO"

# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36'

# Robot協議 # Obey robots.txt rules
ROBOTSTXT_OBEY = True # 設置最大併發請求 # 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://doc.scrapy.org/en/latest/topics/settings.html#download-delay # See also autothrottle settings and docs

# 每次請求以前的下載延遲 #DOWNLOAD_DELAY = 3 # The download delay setting will honor only one of: #CONCURRENT_REQUESTS_PER_DOMAIN = 16 #每一個域名的最大併發請求數 #CONCURRENT_REQUESTS_PER_IP = 16 #每一個ip的最大併發請求數

# 下次請求以前攜帶以前請求的cookie # Disable cookies (enabled by default) #COOKIES_ENABLED = False

# 禁用Telnet控制檯（默認啓用） # Disable Telnet Console (enabled by default) #TELNETCONSOLE_ENABLED = False

# 覆蓋默認請求頭，USER_AGENT在以前，放此處將不起做用 # 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', #}

# 啓用或禁用spider中間件 # Enable or disable spider middlewares # See https://doc.scrapy.org/en/latest/topics/spider-middleware.html #SPIDER_MIDDLEWARES = { # 'tencent.middlewares.TencentSpiderMiddleware': 543, #}

# 啓用或禁用下載器中間件 # Enable or disable downloader middlewares # See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html #DOWNLOADER_MIDDLEWARES = { # 'tencent.middlewares.TencentDownloaderMiddleware': 543, #}

#啓用或禁用擴展程序 # Enable or disable extensions # See https://doc.scrapy.org/en/latest/topics/extensions.html #EXTENSIONS = { # 'scrapy.extensions.telnet.TelnetConsole': None, #}


# 配置項目管道 # Configure item pipelines # See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = { 'tencent.pipelines.TencentPipeline': 300, } # 啓用和配置AutoThrottle擴展（默認狀況下禁用） # Enable and configure the AutoThrottle extension (disabled by default) # See https://doc.scrapy.org/en/latest/topics/autothrottle.html #AUTOTHROTTLE_ENABLED = True

#初始下載延遲 # The initial download delay #AUTOTHROTTLE_START_DELAY = 5

#在高延遲的狀況下設置的最大下載延遲 # 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

#啓用顯示所收到的每一個響應的調節統計信息： # Enable showing throttling stats for every response received: #AUTOTHROTTLE_DEBUG = False

#啓用和配置HTTP緩存（默認狀況下禁用） # Enable and configure HTTP caching (disabled by default) # See https://doc.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'