基于scrapy+mysql爬取博客信息并保存到数据库中

# Scrapy settings for myblog project # # For simplicity, this file contains only settings considered important or # commonly used. You can find more settings consulting the documentation: # # https://docs.scrapy.org/en/latest/topics/settings.html # https://docs.scrapy.org/en/latest/topics/downloader-middleware.html # https://docs.scrapy.org/en/latest/topics/spider-middleware.html BOT_NAME = "myblog" SPIDER_MODULES = ["myblog.spiders"] NEWSPIDER_MODULE = "myblog.spiders" # Crawl responsibly by identifying yourself (and your website) on the user-agent USER_AGENT = "User-Agent':'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.94 Safari/537.36" # Obey robots.txt rules ROBOTSTXT_OBEY = False # 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://docs.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", "User-Agent": "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.94 Safari/537.36", } # Enable or disable spider middlewares # See https://docs.scrapy.org/en/latest/topics/spider-middleware.html #SPIDER_MIDDLEWARES = { # "myblog.middlewares.MyblogSpiderMiddleware": 543, #} # Enable or disable downloader middlewares # See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html #DOWNLOADER_MIDDLEWARES = { # "myblog.middlewares.MyblogDownloaderMiddleware": 543, #} # Enable or disable extensions # See https://docs.scrapy.org/en/latest/topics/extensions.html #EXTENSIONS = { # "scrapy.extensions.telnet.TelnetConsole": None, #} # Configure item pipelines # See https://docs.scrapy.org/en/latest/topics/item-pipeline.html ITEM_PIPELINES = { "myblog.pipelines.MyblogPipeline": 300, } # Enable and configure the AutoThrottle extension (disabled by default) # See https://docs.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://docs.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" # Set settings whose default value is deprecated to a future-proof value REQUEST_FINGERPRINTER_IMPLEMENTATION = "2.7" TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor" FEED_EXPORT_ENCODING = "utf-8" # Mysql数据库的配置信息 MYSQL_HOST = 'localhost' MYSQL_DBNAME = 'test' # 数据库名字，请修改 MYSQL_USER = 'root' # 数据库账号，请修改 MYSQL_PASSWD = '123456' # 数据库密码，请修改 MYSQL_PORT = 3306 # 数据库端口，在db中使用