Python爬虫入门案例之爬取二手房源数据
程序员文章站
2022-03-19 09:28:50
本文重点 系统分析网页性质 结构化的数据解析 csv数据保存环境介绍 python 3.8 pycharm 专业版 >>> 激活码#模块使用 re...
本文重点
- 系统分析网页性质
- 结构化的数据解析
- csv数据保存
环境介绍
- python 3.8
- pycharm 专业版 >>> 激活码
#模块使用
- requests >>> pip install requests
- parsel >>> pip install parsel
- csv
【付费vip完整版】只要看了就能学会的教程,80集python基础入门视频教学
爬虫代码实现步骤: 发送请求 >>> 获取数据 >>> 解析数据 >>> 保存数据
导入模块
import requests # 数据请求模块 第三方模块 pip install requests import parsel # 数据解析模块 import re import csv
发送请求, 对于房源列表页发送请求
url = 'https://bj.lianjia.com/ershoufang/pg1/' # 需要携带上 请求头: 把python代码伪装成浏览器 对于服务器发送请求 # user-agent 浏览器的基本信息 headers = { 'user-agent': 'mozilla/5.0 (windows nt 10.0; win64; x64) applewebkit/537.36 (khtml, like gecko) chrome/94.0.4606.61 safari/537.36' } response = requests.get(url=url, headers=headers)
获取数据
print(response.text)
解析数据
selector_1 = parsel.selector(response.text) # 把获取到response.text 数据内容转成 selector 对象 href = selector_1.css('div.leftcontent li div.title a::attr(href)').getall() for link in href: html_data = requests.get(url=link, headers=headers).text selector = parsel.selector(html_data) # css选择器 语法 # try: title = selector.css('.title h1::text').get() # 标题 area = selector.css('.areaname .info a:nth-child(1)::text').get() # 区域 community_name = selector.css('.communityname .info::text').get() # 小区 room = selector.css('.room .maininfo::text').get() # 户型 room_type = selector.css('.type .maininfo::text').get() # 朝向 height = selector.css('.room .subinfo::text').get().split('/')[-1] # 楼层 # 中楼层/共5层 split('/') 进行字符串分割 ['中楼层', '共5层'] [-1] # ['中楼层', '共5层'][-1] 列表索引位置取值 取列表中最后一个元素 共5层 # re.findall('共(\d+)层', 共5层) >>> [5][0] >>> 5 height = re.findall('共(\d+)层', height)[0] sub_info = selector.css('.type .subinfo::text').get().split('/')[-1] # 装修 elevator = selector.css('.content li:nth-child(12)::text').get() # 电梯 # if elevator == '暂无数据电梯' or elevator == none: # elevator = '无电梯' house_area = selector.css('.content li:nth-child(3)::text').get().replace('㎡', '') # 面积 price = selector.css('.price .total::text').get() # 价格(万元) date = selector.css('.area .subinfo::text').get().replace('年建', '') # 年份 dit = { '标题': title, '市区': area, '小区': community_name, '户型': room, '朝向': room_type, '楼层': height, '装修情况': sub_info, '电梯': elevator, '面积(㎡)': house_area, '价格(万元)': price, '年份': date, } csv_writer.writerow(dit) print(title, area, community_name, room, room_type, height, sub_info, elevator, house_area, price, date, sep='|')
保存数据
f = open('二手房数据.csv', mode='a', encoding='utf-8', newline='') csv_writer = csv.dictwriter(f, fieldnames=[ '标题', '市区', '小区', '户型', '朝向', '楼层', '装修情况', '电梯', '面积(㎡)', '价格(万元)', '年份', ]) csv_writer.writeheader()
数据可视化
导入所需模块
import pandas as pd from pyecharts.charts import map from pyecharts.charts import bar from pyecharts.charts import line from pyecharts.charts import grid from pyecharts.charts import pie from pyecharts.charts import scatter from pyecharts import options as opts
读取数据
df = pd.read_csv('链家.csv', encoding = 'utf-8') df.head()
各城区二手房数量北京市地图
new = [x + '区' for x in region] m = ( map() .add('', [list(z) for z in zip(new, count)], '北京') .set_global_opts( title_opts=opts.titleopts(title='北京市二手房各区分布'), visualmap_opts=opts.visualmapopts(max_=3000), ) ) m.render_notebook()
各城区二手房数量-平均价格柱状图
df_price.values.tolist() price = [round(x,2) for x in df_price.values.tolist()] bar = ( bar() .add_xaxis(region) .add_yaxis('数量', count, label_opts=opts.labelopts(is_show=true)) .extend_axis( yaxis=opts.axisopts( name="价格(万元)", type_="value", min_=200, max_=900, interval=100, axislabel_opts=opts.labelopts(formatter="{value}"), ) ) .set_global_opts( title_opts=opts.titleopts(title='各城区二手房数量-平均价格柱状图'), tooltip_opts=opts.tooltipopts( is_show=true, trigger="axis", axis_pointer_type="cross" ), xaxis_opts=opts.axisopts( type_="category", axispointer_opts=opts.axispointeropts(is_show=true, type_="shadow"), ), yaxis_opts=opts.axisopts(name='数量', axistick_opts=opts.axistickopts(is_show=true), splitline_opts=opts.splitlineopts(is_show=false),) ) ) line2 = ( line() .add_xaxis(xaxis_data=region) .add_yaxis( series_name="价格", yaxis_index=1, y_axis=price, label_opts=opts.labelopts(is_show=true), z=10 ) ) bar.overlap(line2) grid = grid() grid.add(bar, opts.gridopts(pos_left="5%", pos_right="20%"), is_control_axis_index=true) grid.render_notebook()
area0 = top_price['小区'].values.tolist() count = top_price['价格(万元)'].values.tolist() bar = ( bar() .add_xaxis(area0) .add_yaxis('数量', count,category_gap = '50%') .set_global_opts( yaxis_opts=opts.axisopts(name='价格(万元)'), xaxis_opts=opts.axisopts(name='数量'), ) ) bar.render_notebook()
散点图
s = ( scatter() .add_xaxis(df['面积(㎡)'].values.tolist()) .add_yaxis('',df['价格(万元)'].values.tolist()) .set_global_opts(xaxis_opts=opts.axisopts(type_='value')) ) s.render_notebook()
房屋朝向占比
directions = df_direction.index.tolist() count = df_direction.values.tolist() c1 = ( pie(init_opts=opts.initopts( width='800px', height='600px', ) ) .add( '', [list(z) for z in zip(directions, count)], radius=['20%', '60%'], center=['40%', '50%'], # rosetype="radius", label_opts=opts.labelopts(is_show=true), ) .set_global_opts(title_opts=opts.titleopts(title='房屋朝向占比',pos_left='33%',pos_top="5%"), legend_opts=opts.legendopts(type_="scroll", pos_left="80%",pos_top="25%",orient="vertical") ) .set_series_opts(label_opts=opts.labelopts(formatter='{b}:{c} ({d}%)'),position="outside") ) c1.render_notebook()
装修情况/有无电梯玫瑰图(组合图)
fitment = df_fitment.index.tolist() count1 = df_fitment.values.tolist() directions = df_direction.index.tolist() count2 = df_direction.values.tolist() bar = ( bar() .add_xaxis(fitment) .add_yaxis('', count1, category_gap = '50%') .reversal_axis() .set_series_opts(label_opts=opts.labelopts(position='right')) .set_global_opts( xaxis_opts=opts.axisopts(name='数量'), title_opts=opts.titleopts(title='装修情况/有无电梯玫瑰图(组合图)',pos_left='33%',pos_top="5%"), legend_opts=opts.legendopts(type_="scroll", pos_left="90%",pos_top="58%",orient="vertical") ) ) c2 = ( pie(init_opts=opts.initopts( width='800px', height='600px', ) ) .add( '', [list(z) for z in zip(directions, count2)], radius=['10%', '30%'], center=['75%', '65%'], rosetype="radius", label_opts=opts.labelopts(is_show=true), ) .set_global_opts(title_opts=opts.titleopts(title='有/无电梯',pos_left='33%',pos_top="5%"), legend_opts=opts.legendopts(type_="scroll", pos_left="90%",pos_top="15%",orient="vertical") ) .set_series_opts(label_opts=opts.labelopts(formatter='{b}:{c} \n ({d}%)'),position="outside") ) bar.overlap(c2) bar.render_notebook()
二手房楼层分布柱状缩放图
floor = df_floor.index.tolist() count = df_floor.values.tolist() bar = ( bar() .add_xaxis(floor) .add_yaxis('数量', count) .set_global_opts( title_opts=opts.titleopts(title='二手房楼层分布柱状缩放图'), yaxis_opts=opts.axisopts(name='数量'), xaxis_opts=opts.axisopts(name='楼层'), datazoom_opts=opts.datazoomopts(type_='slider') ) ) bar.render_notebook()
房屋面积分布纵向柱状图
area = df_area.index.tolist() count = df_area.values.tolist() bar = ( bar() .add_xaxis(area) .add_yaxis('数量', count) .reversal_axis() .set_series_opts(label_opts=opts.labelopts(position="right")) .set_global_opts( title_opts=opts.titleopts(title='房屋面积分布纵向柱状图'), yaxis_opts=opts.axisopts(name='面积(㎡)'), xaxis_opts=opts.axisopts(name='数量'), ) ) bar.render_notebook()
到此这篇关于python爬虫入门案例之爬取二手房源数据的文章就介绍到这了,更多相关python 爬取二手房数据内容请搜索以前的文章或继续浏览下面的相关文章希望大家以后多多支持!