Python scrapy爬取蘇州二手房交易數(shù)據(jù)

from scrapy import Request
from scrapy.spiders import Spider
from lianjia_home.items import LianjiaHomeItem

class HomeSpider(Spider):
    name = "home"
    current_page=1 #起始頁(yè)

    def start_requests(self): #初始請(qǐng)求
        url="https://su.lianjia.com/ershoufang/"
        yield Request(url=url)

    def parse(self, response): #解析函數(shù)
        list_selctor=response.xpath("http://li/div[@class='info clear']")
        for one_selector in list_selctor:
            try:
                #房屋名稱
                name=one_selector.xpath("http://div[@class='flood']/div[@class='positionInfo']/a/text()").extract_first()
                #其他信息
                other=one_selector.xpath("http://div[@class='address']/div[@class='houseInfo']/text()").extract_first()
                other_list=other.split("|")
                type=other_list[0].strip(" ")#戶型
                area = other_list[1].strip(" ") #面積
                direction=other_list[2].strip(" ") #朝向
                fitment=other_list[3].strip(" ") #裝修
                price_list=one_selector.xpath("div[@class='priceInfo']//span/text()")
                # 總價(jià)
                total_price=price_list[0].extract()
                # 單價(jià)
                unit_price=price_list[1].extract()

                item=LianjiaHomeItem()
                item["name"]=name.strip(" ")
                item["type"]=type
                item["area"] = area
                item["direction"] = direction
                item["fitment"] = fitment
                item["total_price"] = total_price
                item["unit_price"] = unit_price

            #生成詳細(xì)頁(yè)
                url = one_selector.xpath("div[@class='title']/a/@href").extract_first()
                yield Request(url=url,
                              meta={"item":item}, #把item作為數(shù)據(jù)v傳遞
                              callback=self.property_parse) #爬取詳細(xì)頁(yè)
            except:
                print("error")

        #獲取下一頁(yè)
            self.current_page+=1
            if self.current_page=100:
                next_url="https://su.lianjia.com/ershoufang/pg%d"%self.current_page
                yield Request(url=next_url)


    def property_parse(self,response):#詳細(xì)頁(yè)
        #配備電梯
        elevator=response.xpath("http://div[@class='base']/div[@class='content']/ul/li[last()]/text()").extract_first()
        item=response.meta["item"]
        item["elevator"]=elevator
        yield item

import re
from scrapy.exceptions import DropItem
class LianjiaHomePipeline:#數(shù)據(jù)的清洗
    def process_item(self, item, spider):
        #面積
        item["area"]=re.findall("\d+\.?\d*",item["area"])[0] #提取數(shù)字并存儲(chǔ)
        #單價(jià)
        item["unit_price"] = re.findall("\d+\.?\d*", item["unit_price"])[0] #提取數(shù)字并存儲(chǔ)

        #如果有不完全的數(shù)據(jù)，則拋棄
        if item["direction"] =="暫無數(shù)據(jù)":
            raise DropItem("無數(shù)據(jù)，拋棄：%s"%item)

        return item

class CSVPipeline(object):
    file=None
    index=0 #csv文件行數(shù)判斷
    def open_spider(self,spider): #爬蟲開始前，打開csv文件
        self.file=open("home.csv","a",encoding="utf=8")

    def process_item(self, item, spider):#按要求存儲(chǔ)文件。
        if self.index ==0:
            column_name="name,type,area,direction,fitment,elevator,total_price,unit_price\n"
            self.file.write(column_name)#插入第一行的索引信息
            self.index=1

        home_str=item["name"]+","+item["type"]+","+item["area"]+","+item["direction"]+","+item["fitment"]+","+item["elevator"]+","+item["total_price"]+","+item["unit_price"]+"\n"
        self.file.write(home_str) #插入獲取的信息

        return item

    def close_soider(self,spider):#爬蟲結(jié)束后關(guān)閉csv
        self.file.close()

USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.72 Safari/537.36'
#為裝成瀏覽器
ROBOTSTXT_OBEY = False #不遵循robots協(xié)議
ITEM_PIPELINES = {
    'lianjia_home.pipelines.LianjiaHomePipeline': 300,
    #先進(jìn)行數(shù)字提取
    'lianjia_home.pipelines.CSVPipeline': 400
    #在進(jìn)行數(shù)據(jù)的儲(chǔ)存
    #執(zhí)行順序由后邊的數(shù)字決定
}

from scrapy import cmdline

cmdline.execute("scrapy crawl home" .split())