更多博主开源爬虫教程目录索引(宝藏教程,你值得拥有!)
本文爬取的是链家的二手房信息,相信个位小伙伴看完后一定能自己动手爬取链家的其他模块,比如:租房、新房等等模块房屋数据。
话不多说,来到链家首页,点击北京
来到如下页面,这里有全国各个各个省份城市,而且点击某个城市会跳转到以该城市的为定位的页面
点击二手房,来到二手房页面,可以发现链接地址只是在原先的URL上拼接了 /ershoufang/,所以我们之后也可以直接拼接
但注意,以下这种我们不需要的需要排除
建表语句
CREATE TABLE `lianjia` (
`id` int(11) NOT NULL AUTO_INCREMENT,
`city` varchar(100) DEFAULT NULL,
`money` varchar(100) DEFAULT NULL,
`address` varchar(100) DEFAULT NULL,
`house_pattern` varchar(100) DEFAULT NULL,
`house_size` varchar(100) DEFAULT NULL,
`house_degree` varchar(100) DEFAULT NULL,
`house_floor` varchar(100) DEFAULT NULL,
`price` varchar(50) DEFAULT NULL,
PRIMARY KEY (`id`)
) ENGINE=InnoDB AUTO_INCREMENT=212 DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_0900_ai_ci;
from scrapy import cmdline
cmdline.execute("scrapy crawl lianjia".split())
lianjia.py
# -*- coding: utf-8 -*-
import scrapy
import time
from Lianjia.items import LianjiaItem
class LianjiaSpider(scrapy.Spider):
name = 'lianjia'
allowed_domains = ['lianjia.com']
#拥有各个省份城市的URL
start_urls = ['https://www.lianjia.com/city/']
def parse(self, response):
#参考图1,找到class值为city_list_ul的ul标签,在获取其下的所有li标签
ul = response.xpath("//ul[@class='city_list_ul']/li")
#遍历ul,每个省份代表一个li标签
for li in ul:
#参考图2,获取每个省份下的所有城市的li标签
data_ul = li.xpath(".//ul/li")
#遍历得到每个城市
for li_data in data_ul:
#参考图3,获取每个城市的URL和名称
city = li_data.xpath(".//a/text()").get()
#拼接成为二手房链接
page_url = li_data.xpath(".//a/@href").get() + "/ershoufang/"
#多页爬取
for i in range(3):
url = page_url + "pg" + str(i+1)
print(url)
yield scrapy.Request(url=url,callback=self.pageData,meta={
"info":city})
def pageData(self,response):
print("="*50)
#获取传过来的城市名称
city = response.meta.get("info")
#参考图4,找到class值为sellListContent的ul标签,在获取其下的所有li标签
detail_li = response.xpath("//ul[@class='sellListContent']/li")
#遍历
for page_li in detail_li:
#参考图5,获取class值判断排除多余的广告
if page_li.xpath("@class").get() == "list_app_daoliu":
continue
#参考图6,获取房屋总价
money = page_li.xpath(".//div[@class='totalPrice']/span/text()").get()
money = str(money) + "万"
#参考图7
address = page_li.xpath(".//div[@class='positionInfo']/a/text()").get()
#参考图8,获取到房屋的全部数据,进行分割
house_data = page_li.xpath(".//div[@class='houseInfo']/text()").get().split("|")
#房屋格局
house_pattern = house_data[0]
#面积大小
house_size = house_data[1].strip()
#装修程度
house_degree = house_data[3].strip()
#楼层
house_floor = house_data[4].strip()
#单价,参考图9
price = page_li.xpath(".//div[@class='unitPrice']/span/text()").get().replace("单价","")
time.sleep(0.5)
item = LianjiaItem(city=city,money=money,address=address,house_pattern=house_pattern,house_size=house_size,house_degree=house_degree,house_floor=house_floor,price=price)
yield item
lianjia.py
# -*- coding: utf-8 -*-
import scrapy
import time
from Lianjia.items import LianjiaItem
class LianjiaSpider(scrapy.Spider):
name = 'lianjia'
allowed_domains = ['lianjia.com']
start_urls = ['https://www.lianjia.com/city/']
def parse(self, response):
ul = response.xpath("//ul[@class='city_list_ul']/li")
for li in ul:
data_ul = li.xpath(".//ul/li")
for li_data in data_ul:
city = li_data.xpath(".//a/text()").get()
page_url = li_data.xpath(".//a/@href").get() + "/ershoufang/"
for i in range(3):
url = page_url + "pg" + str(i+1)
print(url)
yield scrapy.Request(url=url,callback=self.pageData,meta={
"info":city})
def pageData(self,response):
print("="*50)
city = response.meta.get("info")
detail_li = response.xpath("//ul[@class='sellListContent']/li")
for page_li in detail_li:
if page_li.xpath("@class").get() == "list_app_daoliu":
continue
money = page_li.xpath(".//div[@class='totalPrice']/span/text()").get()
money = str(money) + "万"
address = page_li.xpath(".//div[@class='positionInfo']/a/text()").get()
#获取到房屋的全部数据,进行分割
house_data = page_li.xpath(".//div[@class='houseInfo']/text()").get().split("|")
#房屋格局
house_pattern = house_data[0]
#面积大小
house_size = house_data[1].strip()
#装修程度
house_degree = house_data[3].strip()
#楼层
house_floor = house_data[4].strip()
#单价
price = page_li.xpath(".//div[@class='unitPrice']/span/text()").get().replace("单价","")
time.sleep(0.5)
item = LianjiaItem(city=city,money=money,address=address,house_pattern=house_pattern,house_size=house_size,house_degree=house_degree,house_floor=house_floor,price=price)
yield item
items.py
# -*- coding: utf-8 -*-
import scrapy
class LianjiaItem(scrapy.Item):
#城市
city = scrapy.Field()
#总价
money = scrapy.Field()
#地址
address = scrapy.Field()
# 房屋格局
house_pattern = scrapy.Field()
# 面积大小
house_size = scrapy.Field()
# 装修程度
house_degree = scrapy.Field()
# 楼层
house_floor = scrapy.Field()
# 单价
price = scrapy.Field()
pipelines.py
import pymysql
class LianjiaPipeline:
def __init__(self):
dbparams = {
'host': '127.0.0.1',
'port': 3306,
'user': 'root', #数据库账号
'password': 'root', #数据库密码
'database': 'lianjia', #数据库名称
'charset': 'utf8'
}
#初始化数据库连接
self.conn = pymysql.connect(**dbparams)
self.cursor = self.conn.cursor()
self._sql = None
def process_item(self, item, spider):
#执行sql
self.cursor.execute(self.sql,(item['city'],item['money'],item['address'],item['house_pattern'],item['house_size'],item['house_degree']
,item['house_floor'],item['price']))
self.conn.commit() #提交
return item
@property
def sql(self):
if not self._sql:
#数据库插入语句
self._sql = """
insert into lianjia(id,city,money,address,house_pattern,house_size,house_degree,house_floor,price)
values(null,%s,%s,%s,%s,%s,%s,%s,%s)
"""
return self._sql
return self._sql
settings.py
# -*- coding: utf-8 -*-
BOT_NAME = 'Lianjia'
SPIDER_MODULES = ['Lianjia.spiders']
NEWSPIDER_MODULE = 'Lianjia.spiders'
LOG_LEVEL="ERROR"
# 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://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',
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.135 Safari/537.36 Edg/84.0.522.63"
}
# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'Lianjia.middlewares.LianjiaSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'Lianjia.middlewares.LianjiaDownloaderMiddleware': 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 = {
'Lianjia.pipelines.LianjiaPipeline': 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'
全部数据远远大于518条,博主爬取一会就停下来了,这里只是个演示
博主会持续更新,有兴趣的小伙伴可以点赞、关注和收藏下哦,你们的支持就是我创作最大的动力!
更多博主开源爬虫教程目录索引(宝藏教程,你值得拥有!)
本文爬虫源码已由 GitHub https://github.com/2335119327/PythonSpider 已经收录(内涵更多本博文没有的爬虫,有兴趣的小伙伴可以看看),之后会持续更新,欢迎Star。