Python的scrapy之爬取链家网房价信息并保存到本地

因为有在北京租房的打算，于是上网浏览了一下链家网站的房价，想将他们爬取下来，并保存到本地。

先看链家网的源码。。房价信息 都保存在 ul 下的li 里面

​

爬虫结构：

​ 其中封装了一个数据库处理模块，还有一个user-agent池。。

先看mylianjia.py

# -*- coding: utf-8 -*-
import scrapy
from ..items import LianjiaItem
from scrapy.http import Request
from parsel import Selector
import requests
import os


class MylianjiaSpider(scrapy.Spider):
    name = 'mylianjia'
    #allowed_domains = ['lianjia.com']
    start_urls = ['https://bj.lianjia.com/ershoufang/chaoyang/pg']

    def start_requests(self):
        for i in range(1, 101):  #100页的所有信息
            url1 = self.start_urls + list(str(i))
            #print(url1)
            url = ''
            for j in url1:
                url += j + ''
            yield Request(url, self.parse)

    def parse(self, response):
        print(response.url)

        '''
        response1 = requests.get(response.url, params={'search_text': '粉墨', 'cat': 1001})
        if response1.status_code == 200:
            print(response1.text)
        dirPath = os.path.join(os.getcwd(), 'data')
        if not os.path.exists(dirPath):
            os.makedirs(dirPath)
        with open(os.path.join(dirPath, 'lianjia.html'), 'w', encoding='utf-8')as fp:
            fp.write(response1.text)
            print('网页源码写入完毕')
        '''

        infoall=response.xpath("//div[4]/div[1]/ul/li")
        #infos = response.xpath('//div[@class="info clear"]')
        #print(infos)
        #info1 = infoall.xpath('div/div[1]/a/text()').extract_first()
        #print(infoall)
        for info in infoall:
            item =LianjiaItem()
            #print(info)
            info1 = info.xpath('div/div[1]/a/text()').extract_first()
            info1_url = info.xpath('div/div[1]/a/@href').extract_first()
            #info2 = info.xpath('div/div[2]/div/text()').extract_first()
            info2_dizhi = info.xpath('div/div[2]/div/a/text()').extract_first()
            info2_xiangxi= info.xpath('div/div[2]/div/text()').extract()
            #info3 = info.xpath('div/div[3]/div/a/text()').extract_first()
            #info4 = info.xpath('div/div[4]/text()').extract_first()
            price = info.xpath('div/div[4]/div[2]/div/span/text()').extract_first()
            perprice = info.xpath('div/div[4]/div[2]/div[2]/span/text()').extract_first()
            #print(info1,'--',info1_url,'--',info2_dizhi,'--',info2_xiangxi,'--',info4,'--',price,perprice)
            info2_xiangxi1 = ''
            for j1 in info2_xiangxi:
                info2_xiangxi1 += j1 + ''
            #print(info2_xiangxi1)  #化为字符串

            item['houseinfo']=info1
            item['houseurl']=info1_url
            item['housedizhi']=info2_dizhi
            item['housexiangxi']=info2_xiangxi1
            item['houseprice']=price
            item['houseperprice']=perprice

            yield item

 再看items.py

# -*- 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 LianjiaItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    houseinfo=scrapy.Field()
    houseurl=scrapy.Field()
    housedizhi=scrapy.Field()
    housexiangxi=scrapy.Field()
    houseprice=scrapy.Field()
    houseperprice=scrapy.Field()
    pass

　　

接下来看pipelines.py

# -*- 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


class LianjiaPipeline(object):
    def process_item(self, item, spider):
        print('房屋信息:',item['houseinfo'])
        print('房屋链接:', item['houseurl'])
        print('房屋位置:', item['housedizhi'])
        print('房屋详细信息:', item['housexiangxi'])
        print('房屋总价:', item['houseprice'],'万')
        print('平方米价格:', item['houseperprice'])
        print('===='*10)
        return item

　　

接下来看csvpipelines.py

import os
print(os.getcwd())
class LianjiaPipeline(object):
    def process_item(self, item, spider):
        with open('G:pythonAI爬虫大全lianjiadatahouse.txt', 'a+', encoding='utf-8') as fp:
            name=str(item['houseinfo'])
            dizhi=str(item['housedizhi'])
            info=str(item['housexiangxi'])
            price=str(item['houseprice'])
            perprice=str(item['houseperprice'])
            fp.write(name + dizhi + info+ price +perprice+ '
')
            fp.flush()
            fp.close()
        return item

    print('写入文件成功')

　　

 接下来看 settings.py

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

# Scrapy settings for lianjia project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://doc.scrapy.org/en/latest/topics/settings.html
#     https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://doc.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'lianjia'

SPIDER_MODULES = ['lianjia.spiders']
NEWSPIDER_MODULE = 'lianjia.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'lianjia (+http://www.yourdomain.com)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)
# See https://doc.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
DOWNLOAD_DELAY = 0.5
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)
#COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False

# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
#   'Accept-Language': 'en',
#}

# Enable or disable spider middlewares
# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
SPIDER_MIDDLEWARES = {
    'lianjia.middlewares.LianjiaSpiderMiddleware': 543,
    #'scrapy.contrib.downloadermiddleware.useragent.UserAgentMiddleware' : None,
	#'lianjia.rotate_useragent.RotateUserAgentMiddleware' :400
}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
    'lianjia.middlewares.LianjiaDownloaderMiddleware': 543,
}

# Enable or disable extensions
# See https://doc.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
    'lianjia.pipelines.LianjiaPipeline': 300,
    #'lianjia.iopipelines.LianjiaPipeline': 301,
    'lianjia.csvpipelines.LianjiaPipeline':302,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
HTTPCACHE_ENABLED = True
HTTPCACHE_EXPIRATION_SECS = 0
HTTPCACHE_DIR = 'httpcache'
HTTPCACHE_IGNORE_HTTP_CODES = []
HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'


LOG_LEVEL='INFO'
LOG_FILE='lianjia.log'

　　

 最后看starthouse.py

from scrapy.cmdline import execute

execute(['scrapy', 'crawl', 'mylianjia'])

　　

代码运行结果

​

保存到本地效果：

​

完成，事后可以分析一下房价和每平方米的方剂，，因为是海淀区的，，可以看到 都是好几万一平米，总价也得几百万了 而且是二手房，，，可以看出来 ，在北京买房太难。。。。

源码 tyutltf/lianjia: 爬取链家北京房价并保存txt文档  https://github.com/tyutltf/lianjia