快速简单爬取携程酒店信息简介

先查看网站发送信息格式，发现可以通过ajax来拿取信息，还没有ip访问限制。然后顺便爬了杭州5000家酒店信息

import scrapy
import time
import json
from xiechen.items import XiechenItem




class XiecSpider(scrapy.Spider):
    name = 'xiec'
    allowed_domains = ['xiecheng.com']


    # http://hotels.ctrip.com/Domestic/Tool/AjaxHotelList.aspx
    def start_requests(self):
        num = 0
        for i in range(300):
            time.sleep(0.5)
            num += 1
            yield scrapy.FormRequest(
                method='POST',
                url="http://hotels.ctrip.com/Domestic/Tool/AjaxHotelList.aspx",
                formdata={