93 lines
3.2 KiB
Python
93 lines
3.2 KiB
Python
# -*- coding: utf-8 -*-
|
|
|
|
# Scrapy settings for baike 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
|
|
|
|
BOT_NAME = 'baike'
|
|
|
|
SPIDER_MODULES = ['baike.spiders']
|
|
NEWSPIDER_MODULE = 'baike.spiders'
|
|
|
|
|
|
# Crawl responsibly by identifying yourself (and your website) on the user-agent
|
|
#USER_AGENT = 'baike (+http://www.yourdomain.com)'
|
|
|
|
# Obey robots.txt rules
|
|
ROBOTSTXT_OBEY = False
|
|
|
|
# Configure maximum concurrent requests performed by Scrapy (default: 16)
|
|
CONCURRENT_REQUESTS = 100
|
|
LOG_LEVEL = 'WARNING'
|
|
|
|
DOWNLOAD_TIMEOUT = 15
|
|
REACTOR_THREADPOOL_MAXSIZE = 20
|
|
|
|
# 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
|
|
#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 = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36',
|
|
'Accept': 'text / html, application / xhtml + xml, application / xml;q = 0.9,image/webp, * / *;q = 0.8'}
|
|
|
|
# Enable or disable spider middlewares
|
|
# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
|
|
#SPIDER_MIDDLEWARES = {
|
|
# 'WEB_KG.middlewares.WebKgSpiderMiddleware': 543,
|
|
#}
|
|
|
|
# Enable or disable downloader middlewares
|
|
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
|
|
#DOWNLOADER_MIDDLEWARES = {
|
|
# 'WEB_KG.middlewares.WebKgDownloaderMiddleware': 543,
|
|
#}
|
|
|
|
# Enable or disable extensions
|
|
# See https://doc.scrapy.org/en/latest/topics/extensions.html
|
|
#EXTENSIONS = {
|
|
# 'scrapy.extensions.telnet.TelnetConsole': None,
|
|
#}
|
|
|
|
# Configure item pipelines
|
|
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
|
|
#ITEM_PIPELINES = {
|
|
# 'WEB_KG.pipelines.WebKgPipeline': 300,
|
|
#}
|
|
|
|
# Enable and configure the AutoThrottle extension (disabled by default)
|
|
# See https://doc.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://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'
|