scrapy 利用urljoin实现自动翻页 蛋壳租房房源信息

一。项目结构

二。模块划分

1.dankespider

import scrapy
from ..items import ZufangItem

headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36'
}

class Danke_Spider(scrapy.Spider):
    name = 'danke'

    def start_requests(self):
        url = 'https://www.danke.com/room/sh'

        yield scrapy.Request(url=url,headers=headers)

    def parse(self, response):
        house = response.xpath('//div[@class="r_lbx_cena"]/a/text()').getall()
        money = response.xpath('//div[@class="r_lbx_moneya"]/span/text()').getall()
        status = response.xpath('//div[@class="r_lbx_cenb"]').xpath('string(.)').getall()
        print(house,money,status)
        print(len(house),len(money),len(status))
        print(type(house),type(money),type(status))

        for i in range(len(house)):
            info = ZufangItem()
            #清洗数据
            house[i] = house[i].replace(' ','')
            status[i] = status[i].replace(' ','')


            info['house'] = house[i]
            info['money'] = money[i]
            info['status'] = status[i]
            yield info

        #下一页
        next_page = response.xpath('/html/body/div[3]/div/div[6]/div[3]/a/@href').getall()[-1]
        print(next_page)

        if next_page is not None:
            print('进入下一页了啊')
            next_page = response.urljoin(next_page)
            yield scrapy.Request(next_page,callback=self.parse)

分析：先获取div下的所有a标签的href组成的列表，然后取最后一个href
即：response.xpath(’/html/body/div[3]/div/div[6]/div[3]/a/@href’).getall()[-1]

2.items

# -*- 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 ZufangItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    house = scrapy.Field()
    money = scrapy.Field()
    status = scrapy.Field()

3.pipelines
使用mongoDB数据库

# -*- 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 pymongo

conn = pymongo.MongoClient(host='localhost',port=27017)

mydb = conn.test

myset = mydb.zufang

class ZufangPipeline(object):
    def process_item(self, item, spider):
        print('插入信息')
        informations = {
            'house':item['house'],
            'money':item['money'],
            'status':item['status'],
        }

        myset.insert(informations)
        return item

4.settings

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

# Scrapy settings for zufang 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 = 'zufang'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'zufang (+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://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 = {
#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
#   'Accept-Language': 'en',
#}

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

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'zufang.middlewares.ZufangDownloaderMiddleware': 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 = {
   'zufang.pipelines.ZufangPipeline': 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
#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://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'

5.main

from scrapy import cmdline

cmdline.execute(['scrapy','crawl','danke'])