python爬取数据存入mysql_python之scrapy爬取数据保存到mysql数据库

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

#Scrapy settings for tencent 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= 'tencent'SPIDER_MODULES= ['tencent.spiders']

NEWSPIDER_MODULE= 'tencent.spiders'LOG_LEVEL="WARNING"LOG_FILE="./qq.log"

#Crawl responsibly by identifying yourself (and your website) on the user-agent

USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36'

#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 = {#'tencent.middlewares.TencentSpiderMiddleware': 543,#}

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

#连接数据MySQL#数据库地址

MYSQL_HOST = 'localhost'

#数据库用户名:

MYSQL_USER = 'root'

#数据库密码

MYSQL_PASSWORD = 'yang156122'

#数据库端口

MYSQL_PORT = 3306

#数据库名称

MYSQL_DBNAME = 'test'

#数据库编码

MYSQL_CHARSET = 'utf8'