前言:
下面给大家介绍将下载的数据存入到Mysql数据库的用法,数据来源是Mooc的课程。
代码实现:
items.py
from scrapy import Item,Field
class MoocspiderItem(Item):
# define the fields for your item here like:
# name = scrapy.Field()
Url = Field()
Title = Field()
Image_Url = Field()
Student = Field()
Introduction = Field()
settings.py
BOT_NAME = 'MoocSpider'
SPIDER_MODULES = ['MoocSpider.spiders']
NEWSPIDER_MODULE = 'MoocSpider.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'MoocSpider (+http://www.yourdomain.com)'
# Obey robots.txt rules
ROBOTSTXT_OBEY = True
#相信这些代码大家都懂的吧
MYSQL_DB_NAME = 'python_data'
MYSQL_HOST='localhost'
MYSQL_USER='root'
MYSQL_PASSWORD='root'
ITEM_PIPELINES = {
'MoocSpider.pipelines.MysqlPipeline':10,
}
pipelines.py
# -*- coding: utf-8 -*-
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
import json
from twisted.enterprise import adbapi
#这里要说一下,要先安装一下MySQLdb,PYTHON用来对数据库进行操作的库
import MySQLdb
#使用了连接池的插入数据库函数
class MysqlPipeline(object):
#def __init__(self):
#self.file = open('MoocSpider1.json','w',encoding='utf-8')
def open_spider(self,spider):
db = spider.settings.get('MYSQL_DB_NAME','python_data')
host = spider.settings.get('MYSQL_HOST','localhost')
port = 3306
user = spider.settings.get('MYSQL_DB_USER','root')
passwd = spider.settings.get('MYSQL_DB_PASSWORD','root')
self.dbpool = adbapi.ConnectionPool('MySQLdb',host=host,db=db,user=user,passwd=passwd,charset='utf8')
def close_spider(self,spider):
self.dbpool.close()
def process_item(self, item, spider):
#读取item中的数据
#line = json.dumps(dict(item), ensure_ascii=False) + "\n"
#写入文件
#self.file.write(line)
#返回item
#return item
self.dbpool.runInteraction(self.insert_db,item)
def insert_db(self,tx,item):
values = (
item['Url'],
item['Title'],
item['Image_Url'],
item['Student'],
item['Introduction'],
)
sql = 'INSERT INTO books VALUES (%s,%s,%s,%s,%s)'
tx.execute(sql,values)
#普通的连接函数
class MysqlPipeline1(object):
def open_spider(self,spider):
db = spider.settings.get('MYSQL_DB_NAME','python_data')
host = spider.settings.get('MYSQL_HOST','localhost')
port = 3306
user = spider.settings.get('MYSQL_DB_USER','root')
passwd = spider.settings.get('MYSQL_DB_PASSWORD','root')
self.db_conn = MySQLdb.connect(host=host,port=port,db=db,user=user,passwd=passwd,charset='utf8')
self.db_cur = self.db_conn.cursor()
def process_item(self, item, spider):
#读取item中的数据
#line = json.dumps(dict(item), ensure_ascii=False) + "\n"
#写入文件
#self.file.write(line)
#返回item
#return item
try:
self.insert_db(item)
self.db_conn.commit()
except Exception as error:
print(error)
return item
def insert_db(self,item):
values = (
item['Url'],
item['Title'],
item['Image_Url'],
item['Student'],
item['Introduction']
)
sql = 'INSERT INTO books VALUES (%s,%s,%s,%s,%s)'
self.db_cur.execute(sql,values)
MoocSpider.py
import scrapy
from MoocSpider.items import MoocspiderItem
from scrapy.selector import Selector
class MoocSpider(scrapy.Spider):
name = 'MoocSpider'
allowed_domains = ['imooc.com']
start_urls = ['http://www.imooc.com/course/list']
def parse(self, response):
html = Selector(response)
item = MoocspiderItem()
base_url = 'http://www.imooc.com'
content = html.xpath('//div[@class="course-card-container"]')
for each in content:
item = MoocspiderItem()
item['Url'] = base_url + each.xpath('.//a/@href').extract_first()
item['Title'] = each.xpath('.//a/div/h3/text()').extract_first()
item['Image_Url'] = each.xpath('.//a/div/img/@src').extract_first()
item['Student'] = each.xpath('.//a/div/div/div/span/text()').extract()[1]
item['Introduction'] = each.xpath('.//a/div/div/p/text()').extract_first()
yield item
#获取下一页的URL
#url = response.xpath('//a[contains(text(),"下一页")]/@href').extract()
#if url:
#page = 'http://www.imooc.com' + url[0]
#yield scrapy.Request(page,callback = self.parse)
参考资料:《精通Scrapy网络爬虫》
转载请注明来自:www.bywalks.com