init

README.md

@@ -0,0 +1,7 @@
+# 链家爬虫
+### 简介 
+    链家房源爬虫，通过小区信息爬取所有房源,基于scrapy
+### 用法
+    setting.py中配置MongoDB
+    run run.py
+

house_spider/items.py

@@ -0,0 +1,60 @@
+# -*- 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 HouseSpiderItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass
+
+
+class LianjiaVillageItem(scrapy.Item):
+    # 链家小区
+    collection = 'lianjia_village'
+    id = scrapy.Field()
+    name = scrapy.Field()
+    zone = scrapy.Field()
+    address = scrapy.Field()
+    latitude = scrapy.Field()
+    longitude = scrapy.Field()
+    year = scrapy.Field()
+    build_type = scrapy.Field()
+    property_costs = scrapy.Field()
+    property_company = scrapy.Field()
+    developers = scrapy.Field()
+    buildings = scrapy.Field()
+    total_house = scrapy.Field()
+
+class LianjiaHouseItem(scrapy.Item):
+    collection = 'lianjia_House'
+    房屋Id = scrapy.Field()
+    标题 = scrapy.Field()
+    售价 = scrapy.Field()
+    小区 = scrapy.Field()
+    小区ID = scrapy.Field()
+    房屋户型 = scrapy.Field()
+    所在楼层 = scrapy.Field()
+    建筑面积 = scrapy.Field()
+    户型结构 = scrapy.Field()
+    套内面积 = scrapy.Field()
+    建筑类型 = scrapy.Field()
+    房屋朝向 = scrapy.Field()
+    建筑结构 = scrapy.Field()
+    装修情况 = scrapy.Field()
+    梯户比例 = scrapy.Field()
+    配备电梯 = scrapy.Field()
+    产权年限 = scrapy.Field()
+    挂牌时间 = scrapy.Field()
+    交易权属 = scrapy.Field()
+    上次交易 = scrapy.Field()
+    房屋用途 = scrapy.Field()
+    房屋年限 = scrapy.Field()
+    产权所属 = scrapy.Field()
+    抵押信息 = scrapy.Field()
+    房本备件 = scrapy.Field()

house_spider/middlewares.py

@@ -0,0 +1,103 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class HouseSpiderSpiderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(self, response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(self, response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(self, response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(self, start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)
+
+
+class HouseSpiderDownloaderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the downloader middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_request(self, request, spider):
+        # Called for each request that goes through the downloader
+        # middleware.
+
+        # Must either:
+        # - return None: continue processing this request
+        # - or return a Response object
+        # - or return a Request object
+        # - or raise IgnoreRequest: process_exception() methods of
+        #   installed downloader middleware will be called
+        return None
+
+    def process_response(self, request, response, spider):
+        # Called with the response returned from the downloader.
+
+        # Must either;
+        # - return a Response object
+        # - return a Request object
+        # - or raise IgnoreRequest
+        return response
+
+    def process_exception(self, request, exception, spider):
+        # Called when a download handler or a process_request()
+        # (from other downloader middleware) raises an exception.
+
+        # Must either:
+        # - return None: continue processing this exception
+        # - return a Response object: stops process_exception() chain
+        # - return a Request object: stops process_exception() chain
+        pass
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

house_spider/pipelines.py

@@ -0,0 +1,25 @@
+# -*- 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
+import pymongo
+from scrapy.conf import settings
+
+
+class HouseSpiderPipeline(object):
+    def process_item(self, item, spider):
+        return item
+
+
+class LianjiaVillageSavePipeline(object):
+    def __init__(self):
+        pass
+
+    def process_item(self, item, spider):
+        if spider.name == 'lianjia':
+            client = pymongo.MongoClient(host=settings['MONGO_HOST'], port=settings['MONGO_PORT'])
+            db = client['house']
+            coll = db[item.collection]
+            coll.insert(dict(item))

house_spider/run.py

@@ -0,0 +1,3 @@
+from scrapy import cmdline
+
+cmdline.execute("scrapy crawl lianjia".split())

house_spider/settings.py

@@ -0,0 +1,94 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for house_spider 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 = 'house_spider'
+
+SPIDER_MODULES = ['house_spider.spiders']
+NEWSPIDER_MODULE = 'house_spider.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'house_spider (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = True
+
+# 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 = 3
+# 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 = {
+#    'house_spider.middlewares.HouseSpiderSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'house_spider.middlewares.HouseSpiderDownloaderMiddleware': 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 = {
+    'house_spider.pipelines.HouseSpiderPipeline': 300,
+    'house_spider.pipelines.LianjiaVillageSavePipeline': 301,
+}
+
+# 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'
+
+MONGO_HOST = "127.0.0.1"  # 主机IP
+MONGO_PORT = 27017  # 端口号

house_spider/spiders/__init__.py

@@ -0,0 +1,4 @@
+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

house_spider/spiders/lianjia.py

@@ -0,0 +1,142 @@
+# -*- coding: utf-8 -*-
+import scrapy
+from scrapy import Selector
+import json
+import re
+
+from house_spider.items import LianjiaVillageItem, LianjiaHouseItem
+
+
+class LianjiaSpider(scrapy.Spider):
+    name = 'lianjia'
+    allowed_domains = ['cq.lianjia.com']
+    start_urls = ['cq.lianjia.com']
+
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+        self.base_url = 'https://cq.lianjia.com'
+
+    def start_requests(self):
+        request_url = 'https://cq.lianjia.com/xiaoqu/'
+        yield scrapy.Request(url=request_url, callback=self.parse_district_links)
+
+    def parse_district_links(self, response):
+        """提取地区链接"""
+        sel = Selector(response)
+        links = sel.css("div[data-role='ershoufang'] div:first-child a::attr(href)").extract()
+        for link in links:
+            url = self.base_url + link
+            yield scrapy.Request(url=url, callback=self.parse_bizcircle_links)
+
+    def parse_bizcircle_links(self, response):
+        """提取商圈链接"""
+        sel = Selector(response)
+        links = sel.css("div[data-role='ershoufang'] div:nth-child(2) a::attr(href)").extract()
+        for link in links:
+            url = self.base_url + link
+            yield scrapy.Request(url=url, callback=self.parse_village_list, meta={"ref": url})
+
+    def parse_village_list(self, response):
+        """提取小区链接"""
+        sel = Selector(response)
+        links = sel.css(".listContent .xiaoquListItem .img::attr(href)").extract()
+        for link in links:
+            yield scrapy.Request(url=link, callback=self.parse_village_detail)
+
+        # page
+        page_data = sel.css(".house-lst-page-box::attr(page-data)").extract_first()
+        page_data = json.loads(page_data)
+        if page_data['curPage'] < page_data['totalPage']:
+            url = response.meta["ref"] + 'pg' + str(page_data['curPage'] + 1)
+            yield scrapy.Request(url=url, callback=self.parse_village_list, meta=response.meta)
+
+    def parse_village_detail(self, response):
+        """提取小区详情"""
+        village_url = response.url
+        sel = Selector(response)
+        zone = sel.css('.xiaoquDetailbreadCrumbs .l-txt a::text').extract()
+        latitude = 0
+        longitude = 0
+        try:
+            html = response.body.decode().replace('\r', '')
+            local = html[html.find('resblockPosition:'):html.find('resblockName') - 1]
+            m = re.search('(\d.*\d),(\d.*\d)', local)
+            longitude = m.group(1)
+            latitude = m.group(2)
+        except Exception:
+            pass
+
+        item = LianjiaVillageItem()
+        item['id'] = village_url.replace(self.base_url + '/xiaoqu/', '').replace('/', '')
+        item['name'] = sel.css('.detailHeader .detailTitle::text').extract_first()
+        item['address'] = sel.css('.detailHeader .detailDesc::text').extract_first()
+        item['latitude'] = latitude
+        item['longitude'] = longitude
+        item['zone'] = ','.join(zone)
+        item['year'] = sel.css('.xiaoquInfo .xiaoquInfoItem:nth-child(1) .xiaoquInfoContent::text').extract_first()
+        item['build_type'] = sel.css('.xiaoquInfo .xiaoquInfoItem:nth-child(2) .xiaoquInfoContent::text').extract_first()
+        item['property_costs'] = sel.css('.xiaoquInfo .xiaoquInfoItem:nth-child(3) .xiaoquInfoContent::text').extract_first()
+        item['property_company'] = sel.css('.xiaoquInfo .xiaoquInfoItem:nth-child(4) .xiaoquInfoContent::text').extract_first()
+        item['developers'] = sel.css('.xiaoquInfo .xiaoquInfoItem:nth-child(5) .xiaoquInfoContent::text').extract_first()
+        item['buildings'] = sel.css('.xiaoquInfo .xiaoquInfoItem:nth-child(6) .xiaoquInfoContent::text').extract_first()
+        item['total_house'] = sel.css('.xiaoquInfo .xiaoquInfoItem:nth-child(7) .xiaoquInfoContent::text').extract_first()
+
+        print(item['name'])
+        yield item
+
+        # 小区房源 https://cq.lianjia.com/ershoufang/c3620038190566370/
+        url = self.base_url + "/ershoufang/c" + item['id'] + "/"
+        yield scrapy.Request(url=url, callback=self.parse_house_list, meta={"ref": url})
+
+    def parse_house_list(self, response):
+        """提取房源链接"""
+        sel = Selector(response)
+        # 链家有时小区查询不到数据
+        total = sel.css('.resultDes .total span::text').extract_first()
+        total = int(total)
+        if total > 0:
+            # 提取房源链接
+            links = sel.css(".sellListContent li .info .title a::attr(href)").extract()
+            for link in links:
+                yield scrapy.Request(url=link, callback=self.parse_house_detail)
+            # 链接分页
+            page_data = sel.css(".house-lst-page-box::attr(page-data)").extract_first()
+            page_data = json.loads(page_data)
+            if page_data['curPage'] == 1 and page_data['totalPage'] > 1:
+                price = response.url.replace(self.base_url + '/ershoufang/', '')
+                for x in range(2, page_data['totalPage'] + 1, 1):
+                    url = self.base_url + '/ershoufang/' + 'pg' + str(x) + price
+                    yield scrapy.Request(url=url, callback=self.parse_house_list)
+
+    def parse_house_detail(self, response):
+        """提取房源信息"""
+        sel = Selector(response)
+
+        item = LianjiaHouseItem()
+        item['房屋Id'] = response.url.replace(self.base_url + '/ershoufang/', '').replace('.html', '')
+        item['标题'] = sel.css('.title-wrapper .title .main::text').extract_first()
+        item['售价'] = sel.css('.overview .content .price .total::text').extract_first()
+        item['小区'] = sel.css('.overview .content .aroundInfo .communityName a.info::text').extract_first()
+        item['小区ID'] = sel.css('.overview .content .aroundInfo .communityName a.info::attr(href)').extract_first().replace('/xiaoqu/', '').replace('/', '')
+        item['房屋户型'] = sel.css('#introduction .base .content ul li:nth-child(1)::text').extract_first()
+        item['所在楼层'] = sel.css('#introduction .base .content ul li:nth-child(2)::text').extract_first()
+        item['建筑面积'] = sel.css('#introduction .base .content ul li:nth-child(3)::text').extract_first()
+        item['户型结构'] = sel.css('#introduction .base .content ul li:nth-child(4)::text').extract_first()
+        item['套内面积'] = sel.css('#introduction .base .content ul li:nth-child(5)::text').extract_first()
+        item['建筑类型'] = sel.css('#introduction .base .content ul li:nth-child(6)::text').extract_first()
+        item['房屋朝向'] = sel.css('#introduction .base .content ul li:nth-child(7)::text').extract_first()
+        item['建筑结构'] = sel.css('#introduction .base .content ul li:nth-child(8)::text').extract_first()
+        item['装修情况'] = sel.css('#introduction .base .content ul li:nth-child(9)::text').extract_first()
+        item['梯户比例'] = sel.css('#introduction .base .content ul li:nth-child(10)::text').extract_first()
+        item['配备电梯'] = sel.css('#introduction .base .content ul li:nth-child(11)::text').extract_first()
+        item['产权年限'] = sel.css('#introduction .base .content ul li:nth-child(12)::text').extract_first()
+        item['挂牌时间'] = sel.css('#introduction .transaction .content ul li:nth-child(1) span:nth-child(2)::text').extract_first()
+        item['交易权属'] = sel.css('#introduction .transaction .content ul li:nth-child(2) span:nth-child(2)::text').extract_first()
+        item['上次交易'] = sel.css('#introduction .transaction .content ul li:nth-child(3) span:nth-child(2)::text').extract_first()
+        item['房屋用途'] = sel.css('#introduction .transaction .content ul li:nth-child(4) span:nth-child(2)::text').extract_first()
+        item['房屋年限'] = sel.css('#introduction .transaction .content ul li:nth-child(5) span:nth-child(2)::text').extract_first()
+        item['产权所属'] = sel.css('#introduction .transaction .content ul li:nth-child(6) span:nth-child(2)::text').extract_first()
+        item['抵押信息'] = sel.css('#introduction .transaction .content ul li:nth-child(7) span:nth-child(2)::attr(title)').extract_first()
+        item['房本备件'] = sel.css('#introduction .transaction .content ul li:nth-child(8) span:nth-child(2)::text').extract_first()
+
+        yield item

scrapy.cfg

@@ -0,0 +1,11 @@
+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.io/en/latest/deploy.html
+
+[settings]
+default = house_spider.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = house_spider