Python_manhua/manhua/settings.py

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

# Scrapy settings for manhua 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 = 'manhua'

SPIDER_MODULES = ['manhua.spiders']
NEWSPIDER_MODULE = 'manhua.spiders'

# USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'
#
# DOWNLOADER_MIDDLEWARES = {
#    'manhua.middlewares.AreaSpiderMiddleware': 543,
# }
#
# ITEM_PIPELINES = {
#    'manhua.pipelines.AirHistoryPipeline': 300,
# }
# 渲染服务的url
SPLASH_URL = 'http://192.168.99.100:8050'


# 去重过滤器
DUPEFILTER_CLASS = 'scrapy_splash.SplashAwareDupeFilter'

# 使用Splash的Http缓存
HTTPCACHE_STORAGE = 'scrapy_splash.SplashAwareFSCacheStorage'


SPIDER_MIDDLEWARES = {
    'scrapy_splash.SplashDeduplicateArgsMiddleware': 100,
}


#下载器中间件
DOWNLOADER_MIDDLEWARES = {
    'scrapy_splash.SplashCookiesMiddleware': 723,
    'scrapy_splash.SplashMiddleware': 725,
    'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810,
}
SPIDER_MIDDLEWARES = {
   'scrapy_splash.SplashDeduplicateArgsMiddleware': 100,
}

# 请求头
DEFAULT_REQUEST_HEADERS = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.89 Safari/537.36',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
}

# 管道
# ITEM_PIPELINES = {
#    'news.pipelines.NewsPipeline': 300,
# }

FEED_EXPORT_ENCODING = 'utf-8'

ROBOTSTXT_OBEY = False
# 默认是16，一次可以请求的最大次数
CONCURRENT_REQUESTS = 1
# 下载延迟
# DOWNLOAD_DELAY = 0.1
COOKIES_ENABLED = False
DEFAULT_REQUEST_HEADERS = {
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
    'Accept-Encoding': 'utf-8',
    'Accept-Language': 'zh-CN,zh;q=0.8',
    'Cache-Control': 'max-age=0',
    'Connection': 'keep-alive',
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36'}

ITEM_PIPELINES = {'manhua.pipelines.mmonlyPipeline': 100}
# 日志级别
LOG_LEVEL = 'INFO'
LOG_FILE = '/tmp/log.txt'




# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'manhua (+http://www.yourdomain.com)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = True

# 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
#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,*/*;q=0.8',
#   'Accept-Language': 'en',
#}

# Enable or disable spider middlewares
# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'manhua.middlewares.ManhuaSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'manhua.middlewares.ManhuaDownloaderMiddleware': 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 = {
#    'manhua.pipelines.ManhuaPipeline': 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'


# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html

# DEPTH_LIMIT = 100