scrapy抓取贝壳找房租房数据

链接:https://jn.zu.ke.com/zufang

首先我们使用scrapy startproject Beike 这个命令创建一个scrapy爬虫项目，接着我们用pycharm打开项目，完善item

接着我们找到setting文件，把ROBOTSTXT_OBEY = True，注释掉，或删除，表示我们不遵守协议

设置请求头，伪装成浏览器，不设置直接识别scrapy爬虫框架，直接把你机器拉入黑名单

我们抓取的是页面上的信息字段

我们明确了item以后，我们开始一个scrapy爬虫项目，使用命令： scrapy genspider beike jn.zu.ke.com

beike ------ 是爬虫名字

beike jn.zu.ke.com – domain

接下来我们先编写爬虫文件先写解析列表页面，还有详情页面，我们先不进行翻页，一步一步实现：

代码如下：

# -*- coding: utf-8 -*-
import scrapy
from Beike.items import BeikeItem
import copy


class BeikeSpider(scrapy.Spider):
    name = 'beike'
    allowed_domains = ['jn.zu.ke.com']
    start_urls = ['https://jn.zu.ke.com/zufang']
    page = 2


    def parse(self, response):
        print(response.url)
        node_list = response.xpath('//div[@class="content__list--item--main"]')
        print(len(node_list))
        item = BeikeItem()
        for node in node_list:
            item["title"] = node.xpath("./p[1]/a/text()").extract_first().strip()
            item["link"] = response.urljoin(node.xpath("./p[1]/a/@href").extract_first().strip())
            item["address"] = node.xpath("./p[2]/a[3]/text()").extract_first().strip()
            item["big"] = node.xpath("./p[2]/text()[5]").extract_first().strip()
            item["where"] = node.xpath("./p[2]/text()[6]").extract_first().strip()
            item["how"] = node.xpath("./p[2]/text()[7]").extract_first().strip()
            item["price"] = node.xpath(
                './span[@class="content__list--item-price"]/em/text()').extract_first().strip() + '元/月'
            yield scrapy.Request(
                url=item["link"],
                callback=self.detail_parse,
                meta={"item": copy.deepcopy(item)},
                dont_filter=True
            )

    def detail_parse(self, response):
        item = response.meta['item']
        item["name"] = response.xpath('//*[@id="aside"]/div[2]/div[2]/div[1]/span/text()').extract_first()
        print(item["title"])
        yield item

因为翻页是动态加载的，我们就直接拼接下一页链接

第二页：https://jn.zu.ke.com/zufang/pg2/#contentList

第三页：https://jn.zu.ke.com/zufang/pg3/#contentList

发现变化的是pg后面的数字，构建代码：

        if self.page < 100:
            next_url = 'https://jn.zu.ke.com/zufang/pg{}/#contentList'.format(self.page)
            self.page += 1
            yield scrapy.Request(next_url, callback=self.parse)

交给scrapy框架进行请求解析，昨晚有一个bug一直困扰，就是解析列表页数据正常，但是解析详情页就出现了问题，最后打印数据是一样的，找了好久，然后通过百度找到了解决方法那就是导入copy模块，将列表的item传递使用深拷贝一下就好了meta={“item”: copy.deepcopy(item)},切记爬虫编写时，一定要注意对应好item字段，否则报错，注意一定要打开dont_fillter,不过滤，不打开了就会出现一个bug，当前页面会referer到上一页，数据一样就像这样

我们写完spider爬虫后，运行爬虫 scrapy crawl beike 查看效果：

下一步我们我们将数据保存csv，使用pipline管道，将数据写入

注意：一定要在setting文件中注册管道后面数值越小，越优先

保存csv效果

全部代码：

爬虫item文件代码

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

# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html

import scrapy


class BeikeItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    title = scrapy.Field()
    link = scrapy.Field()
    address = scrapy.Field()
    big = scrapy.Field()
    where = scrapy.Field()
    how = scrapy.Field()
    price = scrapy.Field()
    name = scrapy.Field()

spider爬虫文件：

# -*- coding: utf-8 -*-
import scrapy
from Beike.items import BeikeItem
import copy


class BeikeSpider(scrapy.Spider):
    name = 'beike'
    allowed_domains = ['jn.zu.ke.com']
    start_urls = ['https://jn.zu.ke.com/zufang']
    page = 2


    def parse(self, response):
        print(response.url)
        node_list = response.xpath('//div[@class="content__list--item--main"]')
        print(len(node_list))
        item = BeikeItem()
        for node in node_list:
            item["title"] = node.xpath("./p[1]/a/text()").extract_first().strip()
            item["link"] = response.urljoin(node.xpath("./p[1]/a/@href").extract_first().strip())
            item["address"] = node.xpath("./p[2]/a[3]/text()").extract_first().strip()
            item["big"] = node.xpath("./p[2]/text()[5]").extract_first().strip()
            item["where"] = node.xpath("./p[2]/text()[6]").extract_first().strip()
            item["how"] = node.xpath("./p[2]/text()[7]").extract_first().strip()
            item["price"] = node.xpath(
                './span[@class="content__list--item-price"]/em/text()').extract_first().strip() + '元/月'
            yield scrapy.Request(
                url=item["link"],
                callback=self.detail_parse,
                meta={"item": copy.deepcopy(item)},
                dont_filter=True
            )
        if self.page < 100:
            next_url = 'https://jn.zu.ke.com/zufang/pg{}/#contentList'.format(self.page)
            self.page += 1
            yield scrapy.Request(next_url, callback=self.parse)

    def detail_parse(self, response):
        item = response.meta['item']
        item["name"] = response.xpath('//*[@id="aside"]/div[2]/div[2]/div[1]/span/text()').extract_first()
        print(item["title"])
        yield item

pipline代码

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

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html
import csv



class SavePipeline(object):
    def open_spider(self, spider):
        self.file = open("贝壳.csv", 'a', newline="",encoding="gb18030")
        self.csv_writer = csv.writer(self.file)
        self.csv_writer.writerow(["标题", "链接", '地址', "大小", "方向", "居室",
                                  "价格", "名字"])

    def process_item(self, item, spider):
        self.csv_writer.writerow(
            [item["title"], item["link"], item["address"],
             item["big"], item["where"], item["how"], item["price"], item["name"]]
        )
        return item

    def close_spider(self, spider):
        self.file.close()

setting文件

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

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

BOT_NAME = 'Beike'

SPIDER_MODULES = ['Beike.spiders']
NEWSPIDER_MODULE = 'Beike.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/87.0.4280.88 ' \
             'Safari/537.36 '

# 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://docs.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 = {
#     "Referer": "https://jn.zu.ke.com/zufang"
# }

# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
# SPIDER_MIDDLEWARES = {
#    'Beike.middlewares.BeikeSpiderMiddleware': 543,
# }

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

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

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'Beike.pipelines.SavePipeline': 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
# AUTOTHROTTLE_ENABLED = True
# The initial download delay
# AUTOTHROTTLCONCURRENT_REQUESTSE_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://docs.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'

整个代码实现比较简单，就是有坑，每个人主要就是从项目中积累经验吧，这个网站，没有反爬，也没cookie模拟登录，后续遇到反爬可以用一个请求头池，还有ip代理池，进行持续化抓取数据，以上都是个人学习经验，如有不正请指教，谢谢！