使用Scrapy爬取动态数据

https://s.taobao.com/search?q=%E7%AC%94%E8%AE%B0%E6%9C%AC%E7%94%B5%E8%84%91&imgfile=&commend=all&ssid=s5-e&search_type=item&sourceId=tb.index&spm=a21bo.2017.201856-taobao-item.1&ie=utf8&initiative_id=tbindexz_20170306

from selenium import webdriver
from scrapy.http.response.html import HtmlResponse
from scrapy.http.response import Response
class SeleniumSpiderMiddleware(object):
  def __init__(self):
    self.driver = webdriver.PhantomJS()
  def process_request(self ,request ,spider):
    # 当引擎从调度器中取出request进行请求发送下载器之前
    # 会先执行当前的爬虫中间件 ，在中间件里面使用selenium
    # 请求这个request ，拿到动态网站的数据 然后将请求
    # 返回给spider爬虫对象
    if spider.name == 'taobao':
      # 使用爬虫文件的url地址
      spider.driver.get(request.url)
      for x in range(1 ,12 ,2):
        i = float(x) / 11
        # scrollTop 从上往下的滑动距离
        js = 'document.body.scrollTop=document.body.scrollHeight * %f' % i
        spider.driver.execute_script(js)
      response = HtmlResponse(url=request.url,
                  body=spider.driver.page_source,
                  encoding='utf-8',
                  request=request)
      # 这个地方只能返回response对象，当返回了response对象，那么可以直接跳过下载中间件，将response的值传递给引擎，引擎又传递给 spider进行解析
      return response

DOWNLOADER_MIDDLEWARES = {
  'taobaoSpider.middlewares.SeleniumSpiderMiddleware': 543,
}

from selenium import webdriver

def __init__(self):
  self.driver = webdriver.PhantomJS()

def parse(self, response):
  div_info = response.xpath('//div[@class="info-cont"]')
  print(div_info)
  for div in div_info:
    title = div.xpath('.//div[@class="title-row "]/a/text()').extract_first('')
    # title = self.driver.find_element_by_class_name("title-row").text
    print('名称：', title)
    price = div.xpath('.//div[@class="sale-row row"]/div/span[2]/strong/text()').extract_first('')

name = scrapy.Field()
price = scrapy.Field()

from ..items import TaobaospiderItem

item = TaobaospiderItem()
item['name'] = title
item['price'] = price
yield item

ITEM_PIPELINES = {
  'taobaoSpider.pipelines.TaobaospiderPipeline': 300,
}

import sqlite3
写入数据库的代码如下：
class TaobaospiderPipeline(object):
  def __init__(self):
    self.connect = sqlite3.connect('taobaoDB')
    self.cursor = self.connect.cursor()
    self.cursor.execute('create table if not exists taobaoTable (name text,price text)')
  def process_item(self, item, spider):
    self.cursor.execute('insert into taobaoTable (name,price)VALUES ("{}","{}")'.format(item['name'],item['price']))
    self.connect.commit()
    return item
  def close_spider(self):
    self.cursor.close()
    self.connect.close()

ITEM_PIPELINES = {
  'taobaoSpider.pipelines.TaobaospiderPipeline': 300,
}

# -*- coding: utf-8 -*-
import scrapy
from selenium import webdriver
from ..items import TaobaospiderItem
class TaobaoSpider(scrapy.Spider):
  name = 'taobao'
  allowed_domains = ['taobao.com']
  start_urls = ['https://s.taobao.com/search?q=%E7%AC%94%E8%AE%B0%E6%9C%AC%E7%94%B5%E8%84%91&imgfile=&commend=all&ssid=s5-e&search_type=item&sourceId=tb.index&spm=a21bo.2017.201856-taobao-item.1&ie=utf8&initiative_id=tbindexz_20170306']
  def __init__(self):
    self.driver = webdriver.PhantomJS()
  def parse(self, response):
    div_info = response.xpath('//div[@class="info-cont"]')
    print(div_info)
    for div in div_info:
      title = div.xpath('.//div[@class="title-row "]/a/text()').extract_first('')
      print('名称：', title)
      price = div.xpath('.//div[@class="sale-row row"]/div/span[2]/strong/text()').extract_first('')
      item = TaobaospiderItem()
      item['name'] = title
      item['price'] = price
      yield item
  def close(self,reason):
    print('结束了',reason)
    self.driver.quit()