个人记录帖,方便于后面的代码运行,
首先是scrapy中的setting.py
# -*- coding: utf-8 -*-
# Scrapy settings for mjx_project 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 = 'mjx_project'
SPIDER_MODULES = ['mjx_project.spiders']
NEWSPIDER_MODULE = 'mjx_project.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'mjx_project (+http://www.yourdomain.com)'
# 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://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 = {
# 'mjx_project.middlewares.MjxProjectSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
'mjx_project.middlewares.MjxProjectDownloaderMiddleware': 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 = {
# 'mjx_project.pipelines.XcxPipeline': 1,
# 'mjx_project.pipelines.MysqlProjectPipeline': 300,
'mjx_project.pipelines.TuchongProjectPipeline': 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'
ITEM_PIPELINES中
# 'mjx_project.pipelines.MysqlProjectPipeline': 300,是专门用来各种存储数据
'mjx_project.pipelines.TuchongProjectPipeline': 300,是爬取图虫的管道
存入mysql数据对象化 建于项目下的mysqlhelper.py
import pymysql
class MysqlHelper(object):
def __init__(self):
self.db = pymysql.connect(host='127.0.0.1',port=3306,user='root',password='123456',database='sprider',charset='utf8')
self.cursor = self.db.cursor()
def execute_modify_sql(self,sql,data = None):
self.cursor.execute(sql,data)
self.db.commit()
def __del__(self):
self.cursor.close()
self.db.close()
if __name__ == '__main__':
#用于测试sql语句
sql = 'insert into tc_test(title,room,dizhi,price) values (%s,%s,%s,%s)'
data = ('mjx','mjx','mjx','mjx')
myhelper = MysqlHelper()
myhelper.execute_modify_sql(sql,data)
middleware.py中加入通用请求头
def process_request(self, request, spider):
request.headers['user-agent'] = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'
基本配置成功!下篇文章开始爬取