python爬虫六

import pymysql
class QiubaiproPipelineByMysql(object):

    conn = None  #mysql的连接对象声明
    cursor = None#mysql游标对象声明
    def open_spider(self,spider):
        print(‘开始爬虫‘)
        #链接数据库
        self.conn = pymysql.Connect(host=‘127.0.0.1‘,port=3306,user=‘root‘,password=‘123456‘,db=‘qiubai‘)
    #编写向数据库中存储数据的相关代码
    def process_item(self, item, spider):
        #1.链接数据库
        #2.执行sql语句
        sql = ‘insert into qiubai values("%s","%s")‘%(item[‘author‘],item[‘content‘])
        self.cursor = self.conn.cursor()
        #执行事务
        try:
            self.cursor.execute(sql)
            self.conn.commit()
        except Exception as e:
            print(e)
            self.conn.rollback()

        return item
    def close_spider(self,spider):
        print(‘爬虫结束‘)
        self.cursor.close()
        self.conn.close()

- settings.py

ITEM_PIPELINES = {
    ‘qiubaiPro.pipelines.QiubaiproPipelineByMysql‘: 300,
}

import redis

class QiubaiproPipelineByRedis(object):
    conn = None
    def open_spider(self,spider):
        print(‘开始爬虫‘)
        #创建链接对象
        self.conn = redis.Redis(host=‘127.0.0.1‘,port=6379)
    def process_item(self, item, spider):
        dict = {
            ‘author‘:item[‘author‘],
            ‘content‘:item[‘content‘]
        }
        #写入redis中
        self.conn.lpush(‘data‘, dict)
        return item

ITEM_PIPELINES = {
   ‘doublekill.pipelines.DoublekillPipeline‘: 300,
    ‘doublekill.pipelines.DoublekillPipeline_db‘: 200,
}

def start_requests(self):
        #请求的url
        post_url = ‘http://fanyi.baidu.com/sug‘
        # post请求参数
        formdata = {
            ‘kw‘: ‘wolf‘,
        }
        # 发送post请求
        yield scrapy.FormRequest(url=post_url, formdata=formdata, callback=self.parse)

import scrapy
from moviePro.items import MovieproItem

class MovieSpider(scrapy.Spider):
    name = ‘movie‘
    allowed_domains = [‘www.id97.com‘]
    start_urls = [‘http://www.id97.com/‘]

    def parse(self, response):
        div_list = response.xpath(‘//div[@class="col-xs-1-5 movie-item"]‘)

        for div in div_list:
            item = MovieproItem()
            item[‘name‘] = div.xpath(‘.//h1/a/text()‘).extract_first()
            item[‘score‘] = div.xpath(‘.//h1/em/text()‘).extract_first()
            #xpath(string(.))表示提取当前节点下所有子节点中的数据值（.）表示当前节点
            item[‘kind‘] = div.xpath(‘.//div[@class="otherinfo"]‘).xpath(‘string(.)‘).extract_first()
            item[‘detail_url‘] = div.xpath(‘./div/a/@href‘).extract_first()
            #请求二级详情页面，解析二级页面中的相应内容,通过meta参数进行Request的数据传递
            yield scrapy.Request(url=item[‘detail_url‘],callback=self.parse_detail,meta={‘item‘:item})

    def parse_detail(self,response):
        #通过response获取item
        item = response.meta[‘item‘]
        item[‘actor‘] = response.xpath(‘//div[@class="row"]//table/tr[1]/a/text()‘).extract_first()
        item[‘time‘] = response.xpath(‘//div[@class="row"]//table/tr[7]/td[2]/text()‘).extract_first()
        item[‘long‘] = response.xpath(‘//div[@class="row"]//table/tr[8]/td[2]/text()‘).extract_first()
        #提交item到管道
        yield item

　　items文件：

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

# Define here the models for your scraped items
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/items.html

import scrapy


class MovieproItem(scrapy.Item):
    # define the fields for your item here like:
    name = scrapy.Field()
    score = scrapy.Field()
    time = scrapy.Field()
    long = scrapy.Field()
    actor = scrapy.Field()
    kind = scrapy.Field()
    detail_url = scrapy.Field()

    管道文件：

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

# Define your item pipelines here
#
# Don‘t forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html

import json
class MovieproPipeline(object):
    def __init__(self):
        self.fp = open(‘data.txt‘,‘w‘)
    def process_item(self, item, spider):
        dic = dict(item)
        print(dic)
        json.dump(dic,self.fp,ensure_ascii=False)
        return item
    def close_spider(self,spider):
        self.fp.close()