爬取房天下 省份 城市 小区的名字 价格 几居，这是列表 面积 行政区 是否在售 房天下的详情页面url
fang.py
import scrapy import re from fangtianxia.items import FangtianxiaItem class FangSpider(scrapy.Spider): name = 'fang' start_urls = ['https://www.fang.com/SoufunFamily.htm#'] # 省份 城市 小区的名字 价格 几居，这是列表 面积 行政区 是否在售 房天下的详情页面url def parse(self, response): item=FangtianxiaItem() trs=response.xpath('//div[@id="c02"]//tr') for tr in trs: province=tr.xpath('./td[2]/text()').extract_first() item['province']=province if province=='其他': continue a_list=tr.xpath('./td[3]/a') for a in a_list: city_name=a.xpath('./text()').extract_first() url=a.xpath('./@href').extract_first() url = url.split('.')[0].split(':')[1] #新房url city_url='https:'+url+'.newhouse.fang.com/house/s/' item['city_name']=city_name item['city_url']=city_url yield scrapy.Request(url=city_url,callback=self.parsem,meta={'item':item}) def parsem(self,response): item=response.mete['item'] li_list=response.xpath('//div[@class="nlcd_name"]') for a_list in li_list: url=a_list.xpath('./a/@href').extract_first() yield scrapy.Request(url=url,callback=self.get_content,meta={'item':item}) # new_url=response.url+url.split('/')[3] def get_content(self,response): item=response.meta['item'] district_detail=response.xpath('//mate[@name="Description"]/@content').extract_first() yield item
# -*- 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 FangtianxiaItem(scrapy.Item): # define the fields for your item here like: # name = scrapy.Field() province=scrapy.Field() city_name=scrapy.Field() district_detail=scrapy.Field()
# -*- 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 FangtianxiaSpiderMiddleware(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 FangtianxiaDownloaderMiddleware(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)
import pymysql class FangtianxiaPipeline(object): def open_spider(self,spider): self.conn=pymysql.Connection(host='127.0.0.1',port=3306,password='123456',user='root',db='jianxiang') def process_item(self, item, spider): province=item['province'] city_name=item['city_name'] district_detail=item['district_detail'] self.cursor=self.conn.cursor() sql='insert into fang values(%s,%s,%s)' try: self.cursor.executemany(sql,(province,city_name,district_detail)) self.conn.commit() except Exception as e: print(e) self.conn.rollback() return item def close_spider(self,spider): self.conn.close()
# -*- coding: utf-8 -*- # Scrapy settings for fangtianxia 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 = 'fangtianxia' SPIDER_MODULES = ['fangtianxia.spiders'] NEWSPIDER_MODULE = 'fangtianxia.spiders' # Crawl responsibly by identifying yourself (and your website) on the user-agent USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36' # 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 = 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 = { # 'fangtianxia.middlewares.FangtianxiaSpiderMiddleware': 543, #} # Enable or disable downloader middlewares # See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html #DOWNLOADER_MIDDLEWARES = { # 'fangtianxia.middlewares.FangtianxiaDownloaderMiddleware': 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 = { # 'fangtianxia.pipelines.FangtianxiaPipeline': 300, #} # 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'