scrapy知网专利爬虫

# -*- coding: utf-8 -*- # Scrapy settings for cnki project # # For simplicity, this file contains only settings considered important or # commonly used. You can find more settings consulting the documentation: # # http://doc.scrapy.org/en/latest/topics/settings.html # http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html # http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html BOT_NAME = 'cnki' SPIDER_MODULES = ['cnki.spiders'] NEWSPIDER_MODULE = 'cnki.spiders' DEFAULT_REQUEST_HEADERS = { 'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:55.0) Gecko/20100101 Firefox/55.0', 'Referer':'http://kns.cnki.net/kns/brief/result.aspx?dbprefix=SCOD', 'Cookie':'e01110a4-d552-48f6-32b5-999450e9ff06;Ecp_ClientcnkiUserKey=Id=2170909081801313483;kc_cnki_net_uid=76e702f3-b239-278d-1fd7-05d3143f2c9c;Ecp_IpLoginFail=170927112.81.2.110;ASP.NET_SessionId=xrzxi2drywctu0njaupkcdql;SID_kns=123121;' } ITEM_PIPELINES = {'cnki.pipelines.CnkiPipeline':300,} #设置管道优先级别，因为只有一个pipeline，所以可以设置0-1000任意 MONGODB_SERVER = "localhost" MONGODB_PORT = 27017 #PORT DBNAME COLLECTION SERVER 必需 MONGODB_DBNAME = 'cnki' #数据库的名字 #MONGODB_DOCNAME = 'book' MONGODB_COLLECTION = 'cnkizl' #数据库table 的名字 # Crawl responsibly by identifying yourself (and your website) on the user-agent #USER_AGENT = 'cnki (+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 http://scrapy.readthedocs.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 http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html #SPIDER_MIDDLEWARES = { # 'cnki.middlewares.CnkiSpiderMiddleware': 543, #} # Enable or disable downloader middlewares # See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html #DOWNLOADER_MIDDLEWARES = { # 'cnki.middlewares.MyCustomDownloaderMiddleware': 543, #} # Enable or disable extensions # See http://scrapy.readthedocs.org/en/latest/topics/extensions.html #EXTENSIONS = { # 'scrapy.extensions.telnet.TelnetConsole': None, #} # Configure item pipelines # See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html #ITEM_PIPELINES = { # 'cnki.pipelines.CnkiPipeline': 300, #} # Enable and configure the AutoThrottle extension (disabled by default) # See http://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 http://scrapy.readthedocs.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'