scrapy存储mysql

scrapy 数据存储mysql

 

#spider.py
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from Cwpjt.items import CwpjtItem

class FulongSpider(CrawlSpider):
    name = 'fulong'
    allowed_domains = ['sina.com.cn']
    start_urls = ['http://sina.com.cn/']
    'http://news.sina.com.cn/c/2017-05-09/doc-ifyeycte9324112.shtml'
    rules = (
        Rule(LinkExtractor(allow=('.*?/[0-9]{4}.[0-9]{2}.[0-9]{2}.doc-.*?shtml'),allow_domains=('sina.com.cn')),
             callback='parse_item', follow=True),
    )

    def parse_item(self, response):
        i = CwpjtItem()
        i['name']=response.xpath('/html/head/title/text()').extract()
        i['kws'] = response.xpath('/html/head/meta[@name="keywords"]/@content').extract()
        #i['domain_id'] = response.xpath('//input[@id="sid"]/@value').extract()
        #i['name'] = response.xpath('//div[@id="name"]').extract()
        #i['description'] = response.xpath('//div[@id="description"]').extract()
        return i

pipeline

import pymysql
from pymysql import connections
class CwpjtPipeline(object):
    def __init__(self):
        self.conn = pymysql.connect(host='127.0.0.1',user='root',passwd='123456',db ='mydb')
        self.cursor = self.conn.cursor()
    def process_item(self, item, spider):
        name = item['name'][0]
        kws = item['kws'][0]
        sql ="insert into hehe(title,kws) VALUES(%s,%s)"
        self.cursor.execute(sql,(name,kws,))
        self.conn.commit()
        return item
    def close_spider(self,spider):
        self.conn.close()

item

import scrapy


class CwpjtItem(scrapy.Item):
    # define the fields for your item here like:
    name = scrapy.Field()
    kws = scrapy.Field()