Python爬蟲(chóng)入門(mén)案例之爬取二手房源數(shù)據(jù)

更新時(shí)間：2021年10月15日 10:28:31 作者：松鼠愛(ài)吃餅干

讀萬(wàn)卷書(shū)不如行萬(wàn)里路，學(xué)的扎不扎實(shí)要通過(guò)實(shí)戰(zhàn)才能看出來(lái)，今天小編給大家?guī)?lái)一份python爬取二手房源信息的案例，可以用來(lái)直觀的了解房?jī)r(jià)行情,大家可以在過(guò)程中查缺補(bǔ)漏，看看自己掌握程度怎么樣

本文重點(diǎn)

系統(tǒng)分析網(wǎng)頁(yè)性質(zhì)
結(jié)構(gòu)化的數(shù)據(jù)解析
csv數(shù)據(jù)保存

環(huán)境介紹

python 3.8
pycharm 專(zhuān)業(yè)版 >>> 激活碼

#模塊使用

requests >>> pip install requests
parsel >>> pip install parsel
csv

【付費(fèi)VIP完整版】只要看了就能學(xué)會(huì)的教程，80集Python基礎(chǔ)入門(mén)視頻教學(xué)

點(diǎn)這里即可免費(fèi)在線觀看

爬蟲(chóng)代碼實(shí)現(xiàn)步驟: 發(fā)送請(qǐng)求 >>> 獲取數(shù)據(jù) >>> 解析數(shù)據(jù) >>> 保存數(shù)據(jù)

導(dǎo)入模塊

import requests # 數(shù)據(jù)請(qǐng)求模塊 第三方模塊 pip install requests
import parsel # 數(shù)據(jù)解析模塊
import re
import csv

發(fā)送請(qǐng)求, 對(duì)于房源列表頁(yè)發(fā)送請(qǐng)求

url = 'https://bj.lianjia.com/ershoufang/pg1/'
# 需要攜帶上 請(qǐng)求頭: 把python代碼偽裝成瀏覽器 對(duì)于服務(wù)器發(fā)送請(qǐng)求
# User-Agent 瀏覽器的基本信息
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)

獲取數(shù)據(jù)

print(response.text)

解析數(shù)據(jù)

selector_1 = parsel.Selector(response.text)
# 把獲取到response.text 數(shù)據(jù)內(nèi)容轉(zhuǎn)成 selector 對(duì)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選擇器 語(yǔ)法
    # try:
    title = selector.css('.title h1::text').get() # 標(biāo)題
    area = selector.css('.areaName .info a:nth-child(1)::text').get()  # 區(qū)域
    community_name = selector.css('.communityName .info::text').get()  # 小區(qū)
    room = selector.css('.room .mainInfo::text').get()  # 戶型
    room_type = selector.css('.type .mainInfo::text').get()  # 朝向
    height = selector.css('.room .subInfo::text').get().split('/')[-1]  # 樓層
    # 中樓層/共5層 split('/') 進(jìn)行字符串分割  ['中樓層', '共5層'] [-1]
    # ['中樓層', '共5層'][-1] 列表索引位置取值 取列表中最后一個(gè)元素  共5層
    # re.findall('共(\d+)層', 共5層) >>>  [5][0] >>> 5
    height = re.findall('共(\d+)層', height)[0]
    sub_info = selector.css('.type .subInfo::text').get().split('/')[-1]  # 裝修
    Elevator = selector.css('.content li:nth-child(12)::text').get()  # 電梯
    # if Elevator == '暫無(wú)數(shù)據(jù)電梯' or Elevator == None:
    #     Elevator = '無(wú)電梯'
    house_area = selector.css('.content li:nth-child(3)::text').get().replace('㎡', '')  # 面積
    price = selector.css('.price .total::text').get()  # 價(jià)格(萬(wàn)元)
    date = selector.css('.area .subInfo::text').get().replace('年建', '')  # 年份
    dit = {
        '標(biāo)題': title,
        '市區(qū)': area,
        '小區(qū)': community_name,
        '戶型': room,
        '朝向': room_type,
        '樓層': height,
        '裝修情況': sub_info,
        '電梯': Elevator,
        '面積(㎡)': house_area,
        '價(jià)格(萬(wàn)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='|')

保存數(shù)據(jù)

f = open('二手房數(shù)據(jù).csv', mode='a', encoding='utf-8', newline='')
csv_writer = csv.DictWriter(f, fieldnames=[
    '標(biāo)題',
    '市區(qū)',
    '小區(qū)',
    '戶型',
    '朝向',
    '樓層',
    '裝修情況',
    '電梯',
    '面積(㎡)',
    '價(jià)格(萬(wàn)元)',
    '年份',
])
csv_writer.writeheader()

數(shù)據(jù)可視化

導(dǎo)入所需模塊

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

讀取數(shù)據(jù)

df = pd.read_csv('鏈家.csv', encoding = 'utf-8')
df.head()

各城區(qū)二手房數(shù)量北京市地圖

new = [x + '區(qū)' 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='北京市二手房各區(qū)分布'),
            visualmap_opts=opts.VisualMapOpts(max_=3000),
        )
    )
m.render_notebook()

各城區(qū)二手房數(shù)量-平均價(jià)格柱狀圖

df_price.values.tolist()
price = [round(x,2) for x in df_price.values.tolist()]
bar = (
    Bar()
    .add_xaxis(region)
    .add_yaxis('數(shù)量', count,
              label_opts=opts.LabelOpts(is_show=True))
    .extend_axis(
        yaxis=opts.AxisOpts(
            name="價(jià)格（萬(wàn)元）",
            type_="value",
            min_=200,
            max_=900,
            interval=100,
            axislabel_opts=opts.LabelOpts(formatter="{value}"),
        )
    )
    .set_global_opts(
        title_opts=opts.TitleOpts(title='各城區(qū)二手房數(shù)量-平均價(jià)格柱狀圖'),
        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='數(shù)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="價(jià)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['小區(qū)'].values.tolist()
count = top_price['價(jià)格(萬(wàn)元)'].values.tolist()

bar = (
    Bar()
    .add_xaxis(area0)
    .add_yaxis('數(shù)量', count,category_gap = '50%')
    .set_global_opts(
        yaxis_opts=opts.AxisOpts(name='價(jià)格(萬(wàn)元)'),
        xaxis_opts=opts.AxisOpts(name='數(shù)量'),
    )
)
bar.render_notebook()

散點(diǎn)圖

s = (
    Scatter()
    .add_xaxis(df['面積(㎡)'].values.tolist())
    .add_yaxis('',df['價(jià)格(萬(wàn)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=':{c} (wppm3vysvbp%)'),position="outside")
    )
c1.render_notebook()

裝修情況/有無(wú)電梯玫瑰圖（組合圖）

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='數(shù)量'),
        title_opts=opts.TitleOpts(title='裝修情況/有無(wú)電梯玫瑰圖（組合圖）',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/無(wú)電梯',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=':{c} \n (wppm3vysvbp%)'),position="outside")
    )

bar.overlap(c2)
bar.render_notebook()

二手房樓層分布柱狀縮放圖

floor = df_floor.index.tolist()
count = df_floor.values.tolist()
bar = (
    Bar()
    .add_xaxis(floor)
    .add_yaxis('數(shù)量', count)
    .set_global_opts(
        title_opts=opts.TitleOpts(title='二手房樓層分布柱狀縮放圖'),
        yaxis_opts=opts.AxisOpts(name='數(shù)量'),
        xaxis_opts=opts.AxisOpts(name='樓層'),
        datazoom_opts=opts.DataZoomOpts(type_='slider')
    )
)
bar.render_notebook()

房屋面積分布縱向柱狀圖

area = df_area.index.tolist()
count = df_area.values.tolist()

bar = (
    Bar()
    .add_xaxis(area)
    .add_yaxis('數(shù)量', count)
    .reversal_axis()
    .set_series_opts(label_opts=opts.LabelOpts(position="right"))
    .set_global_opts(
        title_opts=opts.TitleOpts(title='房屋面積分布縱向柱狀圖'),
        yaxis_opts=opts.AxisOpts(name='面積(㎡)'),
        xaxis_opts=opts.AxisOpts(name='數(shù)量'),
    )
)
bar.render_notebook()

到此這篇關(guān)于Python爬蟲(chóng)入門(mén)案例之爬取二手房源數(shù)據(jù)的文章就介紹到這了,更多相關(guān)Python 爬取二手房數(shù)據(jù)內(nèi)容請(qǐng)搜索腳本之家以前的文章或繼續(xù)瀏覽下面的相關(guān)文章希望大家以后多多支持腳本之家！

您可能感興趣的文章: