python爬取地理数据_利用Python爬取房产数据！并在地图上显示！Python乃蒂花之秀！...

JiwuspiderSpider.py

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

from scrapy import Spider,Request

import re

from jiwu.items import JiwuItem

class JiwuspiderSpider(Spider):

name = "jiwuspider"

allowed_domains = ["wlmq.jiwu.com"]

start_urls = ['http://wlmq.jiwu.com/loupan']

def parse(self, response):

"""

解析每一页房屋的list

:param response:

:return:

"""

for url in response.xpath('//a[@class="index_scale"]/@href').extract():

yield Request(url,self.parse_html) # 取list集合中的url 调用详情解析方法

# 如果下一页属性还存在，则把下一页的url获取出来

nextpage = response.xpath('//a[@class="tg-rownum-next index-icon"]/@href').extract_first()

#判断是否为空

if nextpage:

yield Request(nextpage,self.parse) #回调自己继续解析

def parse_html(self,response):

"""

解析每一个房产信息的详情页面，生成item

:param response:

:return:

"""

pattern = re.compile('

'address = \'(.*?)\';.*?price = \'(.*?)\';',re.S)

item = JiwuItem()

results = re.findall(pattern,response.text)

for result in results:

item['name'] = result[2]

item['address'] = result[3]

# 对价格判断只取数字，如果为空就设置为0

pricestr =result[4]

pattern2 = re.compile('(\d+)')

s = re.findall(pattern2,pricestr)

if len(s) == 0:

item['price'] = 0

else:item['price'] = s[0]

item['lng'] = result[0]

item['lat'] = result[1]

yield item

item.py

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

# Define here the models for your scraped items

#

# See documentation in:

# http://doc.scrapy.org/en/latest/topics/items.html

import scrapy

class JiwuItem(scrapy.Item):

# define the fields for your item here like:

name = scrapy.Field()

price =scrapy.Field()

address =scrapy.Field()

lng = scrapy.Field()

lat = scrapy.Field()

pass

pipelines.py 注意此处是吧mongodb的保存方法注释了，可以自选选择保存方式

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

# Define your item pipelines here

#

# Don't forget to add your pipeline to the ITEM_PIPELINES setting

# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html

import pymongo

from scrapy.conf import settings

from openpyxl import workbook

class JiwuPipeline(object):

wb = workbook.Workbook()

ws = wb.active

ws.append(['小区名称', '地址', '价格', '经度', '纬度'])

def __init__(self):

# 获取数据库连接信息

host = settings['MONGODB_URL']

port = settings['MONGODB_PORT']

dbname = settings['MONGODB_DBNAME']

client = pymongo.MongoClient(host=host, port=port)

# 定义数据库

db = client[dbname]

self.table = db[settings['MONGODB_TABLE']]

def process_item(self, item, spider):

jiwu = dict(item)

#self.table.insert(jiwu)

line = [item['name'], item['address'], str(item['price']), item['lng'], item['lat']]

self.ws.append(line)

self.wb.save('jiwu.xlsx')

return item

最后报表的数据

mongodb数据库

地图报表效果图：BDP分享仪表盘，分享可视化效果