python 获取拉勾网招聘信息（全图汇总）

将多张图片汇总到一个页面，大屏可视化数据展示

python 获取拉勾网招聘信息

需要导入的库

import json
import pandas as pd
import numpy as np
import jieba
import jieba.analyse
from pyecharts import options as opts 
from pyecharts.charts import Geo,Map,Bar, Line, Page,Pie, Boxplot, WordCloud
from pyecharts.globals import ChartType, SymbolType,ThemeType

之前的生成各个统计图的代码都写到函数里

#数据分析
#画各个省市招聘人数块地图
def setmap(df):  
        #转化省份信息
    dfp = pd.read_excel('province.xlsx')
    df_new = pd.merge(df,dfp.loc[:,['city','province']],how='left',on = 'city')
    result=pd.value_counts(df_new['province'])
    resultp=dict(result)
    province = list(resultp.keys())
    values = list(resultp.values())
    valuesint=[]
    for i in values:
        valuesint.append(int(i))
        
    c = (
        Map(init_opts=opts.InitOpts( theme=ThemeType.LIGHT))#设置主题
        .add("各个省市招聘人数", [list(z) for z in zip(province, valuesint)], "china",is_map_symbol_show=False, tooltip_opts=opts.TooltipOpts())
        .set_series_opts(label_opts=opts.LabelOpts(is_show=False))
        .set_global_opts(title_opts=opts.TitleOpts(title="各个省市招聘人数"),
        visualmap_opts=opts.VisualMapOpts(max_=200,is_piecewise = True,#图例分段显示
                                          

                                         ))
    )
    
    
    return c


#画各个省市招聘人数条形图
def setbar(df):
        #转化省份信息
    dfp = pd.read_excel('province.xlsx')
    df_new = pd.merge(df,dfp.loc[:,['city','province']],how='left',on = 'city')
    result=pd.value_counts(df_new['province'])
    resultp=dict(result)
    province = list(resultp.keys())
    values = list(resultp.values())
    valuesint=[]
    for i in values:
        valuesint.append(int(i))
        
    c = (
    Bar(init_opts=opts.InitOpts(theme=ThemeType.LIGHT))#设置主题
    .add_xaxis(province)#x轴为省份
    .add_yaxis("人数",valuesint)#y轴为人数
    .set_global_opts(title_opts=opts.TitleOpts(title="各个省市招聘人数"))
    .set_series_opts(
            label_opts=opts.LabelOpts(is_show=False),
            #插入平均值线
            markline_opts=opts.MarkLineOpts(data=[opts.MarkLineItem(type_="average", name="平均值"),]),
            #插入最大值最小值点
            markpoint_opts=opts.MarkPointOpts(data=[
                    opts.MarkPointItem(type_="max", name="最大值"),
                    opts.MarkPointItem(type_="min", name="最小值"),
                ])
    )
)
    
    return c


#画学历饼图
def setpai(df):
    result=pd.value_counts(df['education'])
    resulted=dict(result)
    ed = list(resulted.keys())
    edvalues = list(resulted.values())
    edvaluesint=[]
    for i in edvalues:
        edvaluesint.append(int(i))
    
    c = (
        Pie(init_opts=opts.InitOpts(theme=ThemeType.LIGHT))
        .add(
            "",
            [list(z) for z in zip(ed, edvaluesint)],
            radius=["30%", "75%"],
            center=["25%", "50%"],
            rosetype="radius",
            label_opts=opts.LabelOpts(is_show=False),
        )
        .add(
            "",
            [list(z) for z in zip(ed, edvaluesint)],
            radius=["30%", "75%"],
            center=["75%", "50%"],
            rosetype="area",
        )
        .set_global_opts(title_opts=opts.TitleOpts(title="学历要求"))
    )
    
    return c


#画不同工作经验的薪酬分布箱线图
def setbox(df):
    #处理薪酬数据

    pattern = '\d+'
    # 将字符串转化为列表,薪资取最低值加上区间值得25%，比较贴近现实
    df['salarys'] = df['salary'].str.findall(pattern)
    #
    avg_salary_list = []
    for k in df['salarys']:
        int_list = [int(n) for n in k]
        avg_salary = int_list[0] + (int_list[1] - int_list[0]) / 4
        avg_salary_list.append(avg_salary)
    df['月薪'] = avg_salary_list



    #处理工作年限数据

    df['workYears']=df['workYear'].replace({'应届毕业生':'1年以下','不限':'1年以下'})
    groupby_workyear=df.groupby(['workYears'])['月薪']
    count_groupby_workyear=groupby_workyear.count()
    count_groupby_workyear=count_groupby_workyear.reindex(['1年以下','1-3年','3-5年','5-10年'])
    a = count_groupby_workyear.index
    dff=[]
    for b in a:
        c=groupby_workyear.get_group(b).values
        dff.append(c)
    c = Boxplot(init_opts=opts.InitOpts(theme=ThemeType.LIGHT))
    c.add_xaxis(['1年以下','1-3年','3-5年','5-10年']).add_yaxis("薪酬k/月", c.prepare_data(dff)
        ).set_global_opts(title_opts=opts.TitleOpts(title="不同工作经验的薪酬分布"))
    
    return c


#画设计类型饼图
def setrose(df):
    result=pd.value_counts(df['secondType'])
    resultst=dict(result)
    st= list(resultst.keys())
    stvalues = list(resultst.values())
    stvaluesint=[]
    for i in stvalues:
        stvaluesint.append(int(i))
    

    c = (
        Pie(init_opts=opts.InitOpts(theme=ThemeType.LIGHT))
        .add(
            "",
            [
                list(z)
                for z in zip(
                    st ,
                    stvaluesint ,
                )
            ],
            #设置圆心坐标
            center=["40%", "57%"],
        )
        .set_global_opts(
            title_opts=opts.TitleOpts(title="设计类型"),
            legend_opts=opts.LegendOpts(
                type_="scroll", pos_left="80%", orient="vertical",pos_top="15%"
            ),
        )
        .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}"))
    )
    
    return c


#画岗位需求词云图
def setword(df):
    needs=[]
    for i in df['need']:
        needs.append(i)

    set_need=str(needs).replace('n1',"").replace('n2',"").replace('n3',"").replace('n4',"").replace('n5',"").replace('n6',"").replace('n7',"").replace('n',"")

    cut = jieba.lcut(set_need)
    need_cut=' '.join(cut)
    #设置停止词，删除跟岗位需求无关的词
    stopwords = ['nan','具备','岗位职责','任职','相关','公司','进行','工作','根据','提供','作品','以上学历','优先','计算','经验','学历','上学','熟练','使用','以上',
                 '熟悉','能力','负责','完成','能够','要求','项目','制作','具有','良好','行业','专业','设计','团队','岗位','优秀','我们','关注'
                 ,'xa0','产品','软件','n6','视频','创意','游戏','需求','视觉','大专','本科','各种','以及','n7','了解','职位','结果'
    ]
    jieba_need = jieba.analyse.extract_tags(set_need, topK=80, withWeight=True)
    jieba_result=[]
    for  i in jieba_need:
        if i[0] not in stopwords:
            jieba_result.append(i)


    c = (
            WordCloud(init_opts=opts.InitOpts(theme=ThemeType.LIGHT))
            .add("", jieba_result, word_size_range=[20, 100],shape=SymbolType.RECT)
            .set_global_opts(title_opts=opts.TitleOpts(title="岗位需求"))
        )

   
    return c

首先需要保证你的pyecharts版本在1.4以上，我这里安装了最新版本的pip install pyecharts==1.7.1，还有page = Page(layout=Page.DraggablePageLayout)记住这句话是关键信息！
先执行这段代码生成test.html文件

df = pd.read_excel('lagou_sj.xlsx')
page = Page(layout=Page.DraggablePageLayout)
page.add(setword(df),setrose(df),setbox(df),setpai(df),setbar(df),setmap(df))
page.render("test.html")

点击save_config.生成json文件放入相应项目组

然后注释page.render("test.html")代码添加以下代码执行即可

Page.save_resize_html("test.html", 
	cfg_file="chart_config.json",
 	dest="my_test.html")