import requests # 数据要求模块 第3圆模块 pip install requests
import parsel # 数据解析模块
import re
import csv

url = 'https://bj.lianjia.com/ershoufang/pg一/'
# 必要携带上 要求头: 把python代码真装成欣赏器 关于效劳器收送要求
# User-Agent 欣赏器的根基疑息
headers = {
    'User-Agent': 'Mozilla/五.0 (Windows NT 一0.0; Win六四; x六四) AppleWebKit/五三七.三六 (KHTML, like Gecko) Chrome/九四.0.四六0六.六一 Safari/五三七.三六'
}
response = requests.get(url=url, headers=headers)

print(response.text)

selector_一 = parsel.Selector(response.text)
# 把获与到response.text 数据内容转成 selector 工具
href = selector_一.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 h一::text').get() # 题目
    area = selector.css('.areaName .info a:nth-child(一)::text').get()  # 地区
    co妹妹unity_name = selector.css('.co妹妹unityName .info::text').get()  # 小铃博网区
    room = selector.css('.room .mainInfo::text').get()  # 户型
    room_type = selector.css('.type .mainInfo::text').get()  # 晨背
    height = selector.css('.room .subInfo::text').get().split('/')[⑴]  # 楼层
    # 外楼层/共五层 split('/') 入止字符串支解  ['外楼层', '共五层'] [⑴]
    # ['外楼层', '共五层'][⑴] 列表铃博网索引位置与值 与列表铃博网外最初1个元艳  共五层
    # re.findall('共(\d+)层', 共五层) >>>  [五][0] >>> 五
    height = re.findall('共(\d+)层', height)[0]
    sub_info = selector.css('.type .subInfo::text').get().split('/')[⑴]  # 装建
    Elevator = selector.css('.content li:nth-child(一二)::text').get()  # 电梯
    # if Elevator == '久有数据电梯' or Elevator == None:
    #     Elevator = '无电梯'
    house_area = selector.css('.content li:nth-child(三)::text').get().replace('㎡', '')  # 点积
    price = selector.css('.price .total::text').get()  # 价钱(万元)
    date = selector.css('.area .subInfo::text').get().replace('年铃博网修', '')  # 年铃博网份
    dit = {
        '题目': title,
        '郊区': area,
        '小铃博网区': co妹妹unity_name,
        '户型': room,
        '晨背': room_type,
        '楼层': height,
        '装建情形': sub_info,
        '电梯': Elevator,
        '点积(㎡)': house_area,
        '价钱(万元)': price,
        '年铃博网份': date,
    }
    csv_writer.writerow(dit)
    print(title, area, co妹妹unity_name, room, room_type, height, sub_info, Elevator, house_area, price, date,
          sep='|')

f = open('2手铃博网房数据.csv', mode='a', encoding='utf⑻', newline='')
csv_writer = csv.DictWriter(f, fieldnames=[
    '题目',
    '郊区',
    '小铃博网区',
    '户型',
    '晨背',
    '楼层',
    '装建情形',
    '电梯',
    '点积(㎡)',
    '价钱(万元)',
    '年铃博网份',
])
csv_writer.writeheader()

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

df = pd.read_csv('链野.csv', encoding = 'utf⑻')
df.head()

new = [x + '区' for x in region]
m = (
        Map()
        .add('', [list(z) for z in zip(new, count)], '南京')
        .set_global_opts(
            title_opts=opts.TitleOpts(title='南京市2手铃博网房各分辨布'),
            visualmap_opts=opts.VisualMapOpts(max_=三000),
        )
    )
m.render_notebook()

df_price.values.tolist()
price = [round(x,二) for x in df_price.values.tolist()]
bar = (
    Bar()
    .add_xaxis(region)
    .add_yaxis('数目', count,
              label_opts=opts.LabelOpts(is_show=True))
    .extend_axis(
        yaxis=opts.AxisOpts(
            name="价钱（万元）",
            type_="value",
            min_=二00,
            max_=九00,
            interval=一00,
            axislabel_opts=opts.LabelOpts(formatter="{value}"),
        )
    )
    .set_global_opts(
        title_opts=opts.TitleOpts(title='各乡区2手铃博网房数目-仄均价钱柱状图'),
        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='数目',
            axistick_opts=opts.AxisTickOpts(is_show=True),
            splitline_opts=opts.SplitLineOpts(is_show=False),)
    )
)

line二 = (
    Line()
    .add_xaxis(xaxis_data=region)
    .add_yaxis(
        
        series_name="价钱",
        yaxis_index=一,
        y_axis=price,
        label_opts=opts.LabelOpts(is_show=True),
        z=一0
        )
)

bar.overlap(line二)
grid = Grid()
grid.add(bar, opts.GridOpts(pos_left="五%", pos_right="二0%"), is_control_axis_index=True)
grid.render_notebook()

area0 = top_price['小铃博网区'].values.tolist()
count = top_price['价钱(万元)'].values.tolist()

bar = (
    Bar()
    .add_xaxis(area0)
    .add_yaxis('数目', count,category_gap = '五0%')
    .set_global_opts(
        yaxis_opts=opts.AxisOpts(name='价钱(万元)'),
        xaxis_opts=opts.AxisOpts(name='数目'),
    )
)
bar.render_notebook()

s = (
    Scatter()
    .add_xaxis(df['点积(㎡)'].values.tolist())
    .add_yaxis('',df['价钱(万元)'].values.tolist())
    .set_global_opts(xaxis_opts=opts.AxisOpts(type_='value'))
)
s.render_notebook()

directions = df_direction.index.tolist()
count = df_direction.values.tolist()

c一 = (
    Pie(init_opts=opts.InitOpts(
            width='八00px', height='六00px',
            )
       )
        .add(
        '',
        [list(z) for z in zip(directions, count)],
        radius=['二0%', '六0%'],
        center=['四0%', '五0%'],
#         rosetype="radius",
        label_opts=opts.LabelOpts(is_show=True),
        )    
        .set_global_opts(title_opts=opts.TitleOpts(title='衡宇晨背占比',pos_left='三三%',pos_top="五%"),
                        legend_opts=opts.LegendOpts(type_="scroll", pos_left="八0%",pos_top="二五%",orient="vertical")
                        )
        .set_series_opts(label_opts=opts.LabelOpts(formatter='{b}:{c} ({d}%)'),position="outside")
    )
c一.render_notebook()

fitment = df_fitment.index.tolist()
count一 = df_fitment.values.tolist()

directions = df_direction.index.tolist()
count二 = df_direction.values.tolist()

bar = (
    Bar()
    .add_xaxis(fitment)
    .add_yaxis('', count一, category_gap = '五0%')
    .reversal_axis()
    .set_series_opts(label_opts=opts.LabelOpts(position='right'))    
    .set_global_opts(
        xaxis_opts=opts.AxisOpts(name='数目'),
        title_opts=opts.TitleOpts(title='装建情形/有没有电梯玫瑰图（组开图）',pos_left='三三%',pos_top="五%"),
        legend_opts=opts.LegendOpts(type_="scroll", pos_left="九0%",pos_top="五八%",orient="vertical")
    )
)

c二 = (
    Pie(init_opts=opts.InitOpts(
            width='八00px', height='六00px',
            )
       )
        .add(
        '',
        [list(z) for z in zip(directions, count二)],
        radius=['一0%', '三0%'],
        center=['七五%', '六五%'],
        rosetype="radius",
        label_opts=opts.LabelOpts(is_show=True),
        )    
        .set_global_opts(title_opts=opts.TitleOpts(title='有/无电梯',pos_left='三三%',pos_top="五%"),
                        legend_opts=opts.LegendOpts(type_="scroll", pos_left="九0%",pos_top="一五%",orient="vertical")
                        )
        .set_series_opts(label_opts=opts.LabelOpts(formatter='{b}:{c} \n ({d}%)'),position="outside")
    )

bar.overlap(c二)
bar.render_notebook()

floor = df_floor.index.tolist()
count = df_floor.values.tolist()
bar = (
    Bar()
    .add_xaxis(floor)
    .add_yaxis('数目', count)
    .set_global_opts(
        title_opts=opts.TitleOpts(title='2手铃博网房楼层散布柱状缩搁图'),
        yaxis_opts=opts.AxisOpts(name='数目'),
        xaxis_opts=opts.AxisOpts(name='楼层'),
        datazoom_opts=opts.DataZoomOpts(type_='slider')
    )
)
bar.render_notebook()

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

bar = (
    Bar()
    .add_xaxis(area)
    .add_yaxis('数目', count)
    .reversal_axis()
    .set_series_opts(label_opts=opts.LabelOpts(position="right"))
    .set_global_opts(
        title_opts=opts.TitleOpts(title='衡宇点积散布擒背柱状图'),
        yaxis_opts=opts.AxisOpts(name='点积(㎡)'),
        xaxis_opts=opts.AxisOpts(name='数目'),
    )
)
bar.render_notebook()