使用python爬虫爬取链家潍坊市二手房项目
使用python爬虫爬取链家潍坊市二手房项目需求分析
需要将潍坊市各县市区页面所展示的二手房信息按要求爬取下来，同时保存到本地。
流程设计
[*]明确目标网站URL（ https://wf.lianjia.com/ ）
[*]确定爬取二手房哪些具体信息（字段名）
[*]python爬虫关键实现：requests库和lxml库
[*]将爬取的数据存储到CSV或数据库中
实现过程
项目目录
https://img2023.cnblogs.com/blog/2424738/202303/2424738-20230318134527446-1061174760.png
1、在数据库中创建数据表
我电脑上使用的是MySQL8.0，图形化工具用的是Navicat.
数据库字段对应
id-编号、title-标题、total_price-房屋总价、unit_price-房屋单价、
square-面积、size-户型、floor-楼层、direction-朝向、type-楼型、
district-地区、nearby-附近区域、community-小区、elevator-电梯有无、
elevatorNum-梯户比例、ownership-房屋性质
该图显示的是字段名、数据类型、长度等信息。
https://img2023.cnblogs.com/blog/2424738/202303/2424738-20230318123839689-496702009.png
2、自定义数据存储函数
这部分代码放到Spider_wf.py文件中
通过write_csv函数将数据存入CSV文件，通过write_db函数将数据存入数据库
点击查看代码import csvimport pymysql#写入CSVdef write_csv(example_1): csvfile = open('二手房数据.csv', mode='a', encoding='utf-8', newline='') fieldnames = ['title', 'total_price', 'unit_price', 'square', 'size', 'floor','direction','type', 'BuildTime','district','nearby', 'community', 'decoration', 'elevator','elevatorNum','ownership'] writer = csv.DictWriter(csvfile, fieldnames=fieldnames) writer.writerow(example_1)#写入数据库def write_db(example_2): conn = pymysql.connect(host='127.0.0.1',port= 3306,user='changziru', password='ru123321',database='secondhouse_wf',charset='utf8mb4' ) cursor =conn.cursor() title = example_2.get('title', '') total_price = example_2.get('total_price', '0') unit_price = example_2.get('unit_price', '') square = example_2.get('square', '') size = example_2.get('size', '') floor = example_2.get('floor', '') direction = example_2.get('direction', '') type = example_2.get('type', '') BuildTime = example_2.get('BuildTime','') district = example_2.get('district', '') nearby = example_2.get('nearby', '') community = example_2.get('community', '') decoration = example_2.get('decoration', '') elevator = example_2.get('elevator', '') elevatorNum = example_2.get('elevatorNum', '') ownership = example_2.get('ownership', '') cursor.execute('insert into wf (title, total_price, unit_price, square, size, floor,direction,type,BuildTime,district,nearby, community, decoration, elevator,elevatorNum,ownership)' 'values (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)', ) conn.commit()#传入数据库 conn.close()#关闭数据库3、爬虫程序实现
这部分代码放到lianjia_house.py文件，调用项目Spider_wf.py文件中的write_csv和write_db函数
点击查看代码#爬取链家二手房详情页信息import timefrom random import randintimport requestsfrom lxml import etreefrom secondhouse_spider.Spider_wf import write_csv,write_db#模拟浏览器操作USER_AGENTS = [ "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)", "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)", "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)", "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)", "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)", "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)", "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)", "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)", "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6", "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1", "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0", "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5", "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20", "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",]#随机USER_AGENTSrandom_agent = USER_AGENTSheaders = {'User-Agent': random_agent,}class SpiderFunc: def __init__(self): self.count = 0 def spider(self ,list): for sh in list: response = requests.get(url=sh, params={'param':'1'},headers={'Connection':'close'}).text tree = etree.HTML(response) li_list = tree.xpath('//ul[@]/li[@]') for li in li_list: # 获取每套房子详情页的URL detail_url = li.xpath('.//div[@]/a/@href') try: # 向每个详情页发送请求 detail_response = requests.get(url=detail_url, headers={'Connection': 'close'}).text except Exception as e: sleeptime = randint(15,30) time.sleep(sleeptime)#随机时间延迟 print(repr(e))#打印异常信息 continue else: detail_tree = etree.HTML(detail_response) item = {} title_list = detail_tree.xpath('//div[@]/h1/text()') item['title'] = title_list if title_list else None# 1简介 total_price_list = detail_tree.xpath('//span[@]/text()') item['total_price'] = total_price_list if total_price_list else None# 2总价 unit_price_list = detail_tree.xpath('//span[@]/text()') item['unit_price'] = unit_price_list if unit_price_list else None# 3单价 square_list = detail_tree.xpath('//div[@]/div[@]/text()') item['square'] = square_list if square_list else None# 4面积 size_list = detail_tree.xpath('//div[@]/div[@]/ul/li/text()') item['size'] = size_list if size_list else None# 5户型 floor_list = detail_tree.xpath('//div[@]/div[@]/ul/li/text()') item['floor'] = floor_list if floor_list else None#6楼层 direction_list = detail_tree.xpath('//div[@]/div[@]/text()') item['direction'] = direction_list if direction_list else None# 7朝向 type_list = detail_tree.xpath('//div[@]/div[@]/text()') item['type'] = type_list if type_list else None# 8楼型 BuildTime_list = detail_tree.xpath('//div[@]/div[@]/ul/li/span/text()') item['BuildTime'] = BuildTime_list if BuildTime_list else None# 9房屋年限 district_list = detail_tree.xpath('//div[@]/span[@]/a/text()') item['district'] = district_list if district_list else None# 10地区 nearby_list = detail_tree.xpath('//div[@]/span[@]/a/text()') item['nearby'] = nearby_list if nearby_list else None# 11区域 community_list = detail_tree.xpath('//div[@]/a/text()') item['community'] = community_list if community_list else None# 12小区 decoration_list = detail_tree.xpath('//div[@]/div[@]/ul/li/text()') item['decoration'] = decoration_list if decoration_list else None# 13装修 elevator_list = detail_tree.xpath('//div[@]/div[@]/ul/li/text()') item['elevator'] = elevator_list if elevator_list else None# 14电梯 elevatorNum_list = detail_tree.xpath('//div[@]/div[@]/ul/li/text()') item['elevatorNum'] = elevatorNum_list if elevatorNum_list else None# 15梯户比例 ownership_list = detail_tree.xpath('//div[@]/div[@]/ul/li/span/text()') item['ownership'] = ownership_list if ownership_list else None# 16交易权属 self.count += 1 print(self.count,title_list) # 将爬取到的数据存入CSV文件 write_csv(item) # 将爬取到的数据存取到MySQL数据库中 write_db(item)#循环目标网站count =0for page in range(1,101): if page
页:
[1]