Scrapy_setting
2018-12-06 本文已影响0人
錦魚
# -*- coding: utf-8 -*-
# Scrapy settings for quanshubook 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 = 'quanshubook'
SPIDER_MODULES = ['quanshubook.spiders']
NEWSPIDER_MODULE = 'quanshubook.spiders'
''' 设置模拟浏览器加载'''
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'quanshubook (+http://www.yourdomain.com)'
'''是否遵循robot协议'''
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
'''最大并发数量# 默认１６'''
# 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
'''下载延时 默认为０'''
DOWNLOAD_DELAY = 1
# The download delay setting will honor only one of:
'''在每个域下允许的并发数 默认为８'''
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
'''针对每个ｉｐ，允许发起请求的并发数量 默认为０'''
#CONCURRENT_REQUESTS_PER_IP = 16
'''不为零的情况下ＩＰ优先级比ＤＯＭＡＩＮ优先级要高'''
'''ＤＯＷＮＬＯＡＤ＿ＤＥＡＬＹ的下载延时就针对于ｉｐ而不是网站了'''
# Disable cookies (enabled by default)
"""携带cookie"""
'''是否携带cookies 默认为Ｔｒｕｅ,表示携带cookie'''
COOKIES_ENABLED = False
'''默认为False，表示不追踪cookies'''
COOKIE_DEBUG = True
# Disable Telnet Console (enabled by default)
'''是一个拓展插件，可以监听到当前爬虫的一些状态（默认开启）'''
#TELNETCONSOLE_ENABLED = False
# Override the default request headers:
# 请求头的设置
DEFAULT_REQUEST_HEADERS = {
# 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
# 'Accept-Language': 'en',
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.106 BIDUBrowser/8.7 Safari/537.36',
}
'''中间件'''
# Enable or disable spider middlewares
# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
'''爬虫中间件'''
#SPIDER_MIDDLEWARES = {
# 'quanshubook.middlewares.QuanshubookSpiderMiddleware': 543,
#}
'''下载中间件(数字是优先级，越小优先级越高)'''
# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
'quanshubook.middlewares.QidinaUserAgentDownloadmiddlerware': 543,
'quanshubook.middlewares.QidianProxyDowoloadmiddleware':542,
'quanshubook.middlewares.SeleiniumDoenloadMiddlerWare':544,
}
'''拓展'''
# Enable or disable extensions
# See https://doc.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
# 'scrapy.extensions.telnet.TelnetConsole': None,
#}
'''管道（数字越小优先级越高）'''
# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
'quanshubook.pipelines.QuanshubookPipeline': 300,
}
'''动态设置的下载延时'''
# 默认情况下是关闭的
# 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
'''初始下载延时(为５ｓ)'''
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
'''最大下载延时'''
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
'''发送到服务器的并行的请求数量'''
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
'''是否开启ｄｅｂｕｇ模式（默认为ＴＲＵＥ）'''
#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
'''缓存的拓展，（默认情况下关闭，False）'''
#HTTPCACHE_ENABLED = True
'''设置缓存时间'''
#HTTPCACHE_EXPIRATION_SECS = 0
'''设置缓存保存的路径'''
#HTTPCACHE_DIR = 'httpcache'
'''忽略的响应状态码'''
#HTTPCACHE_IGNORE_HTTP_CODES = []
'''缓存的一个储存插件'''
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
# ＃ 春花秋月何时了，往事知多少
# 将log日志信息，保存到本地文件
LOG_FILE = 'qd_log_file.log'
# 编码
LOG_ENCODING = 'utf-8'
# #开关
# CRITICAL - 严重错误(critical)
# - ERROR - 一般错误(regular errors)
# - WARNING - 警告信息(warning messages)
# - INFO - 一般信息(informational messages)
# - DEBUG - 调试信息(debugging messages)
LOG_LEVEL ='INFO'
'''其他自定义'''
'''
调用时，
属性 = crawler.settings['简直对']
'''
'''mongo'''
MONGO_HOST = '127.0.0.1'
MONGO_POST = 27017
MONGO_DBNAME = 'qd_book'
'''UA池'''
USER_AGENT = [
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
"Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
"Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
"Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
]
'''代理池'''
PROXIES = [
{'ip_port': '111.8.60.9:8123', 'user_pwd': 'user1:pass1'},
{'ip_port': '101.71.27.120:80', 'user_pwd': 'user2:pass2'},
{'ip_port': '122.96.59.104:80', 'user_pwd': None},
{'ip_port': '122.224.249.122:8088', 'user_pwd': None},
]
'''COOKIES池'''
COOKIES = [
]
常用的
'''是否遵循robot协议'''
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
# 请求头的设置
DEFAULT_REQUEST_HEADERS = {
# 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
# 'Accept-Language': 'en',
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.106 BIDUBrowser/8.7 Safari/537.36',
}
'''下载延时 默认为０'''
DOWNLOAD_DELAY = 1
# 管道激活
ITEM_PIPELINES = {
'quanshubook.pipelines.QuanshubookPipeline': 300,
}
# 中间件激活
#
