利用Python对中国500强排行榜数据进行可视化分析_python_

url="http://www.fortunechina.com/fortune500/c/2020-07/27/content_369925.htm" res = requests.get(url,headers=headers) res.encoding = 'utf-8' text = res.text

for i in range(0,len(table_tr)): try: #name = i.xpath('.//td/a/text()')[0] href = table_tr[i].xpath('.//td/a/@href')[0].replace("../../../../","http://www.fortunechina.com/") column_list = get_detail(href) for k in range(0,len(column_list)): outws.cell(row=count, column=k+1, value=column_list[k]) print(count) count = count+1 except: pass

name = selector.xpath('//*[@class="comp-name"]/text()')[0] r1 = selector.xpath('//*[@class="con"]/em[@class="r1"]/text()')[0] r2 = selector.xpath('//*[@class="con"]/span/em/font[@class="ft-red"]/text()')[0] address = selector.xpath('//*[@class="info"]/p')[0].xpath('.//text()')[0].replace(" ", "") table_tbody_tr = selector.xpath('//*[@class="table"]/table/tr')

outwb = openpyxl.Workbook() outws = outwb.create_sheet(index=0) outws.cell(row=1, column=1, value="企业名称") outws.cell(row=1, column=2, value="2020年排名") outws.cell(row=1, column=3, value="2019年排名") outws.cell(row=1, column=4, value="总部地址") outws.cell(row=1, column=5, value="营业收入") outws.cell(row=1, column=6, value="营业收入年增减") outws.cell(row=1, column=7, value="利润") outws.cell(row=1, column=8, value="利润年增减") outws.cell(row=1, column=9, value="资产") outws.cell(row=1, column=10, value="市值") outws.cell(row=1, column=11, value="股东权益") outwb.save("中国500强排行榜数据.xlsx") # 保存

from pyecharts import options as opts from pyecharts.charts import Line from pyecharts.charts import Map import pandas as pd from pyecharts import options as opts from pyecharts.globals import ThemeType from pyecharts.charts import Bar

address = pd_data['总部地址'] address = address.tolist() address_03 = [] for i in address: ###取省份（前两位） address_03.append(i[0:2]) data =[] address_03_set = set(address_03) #address_03_set是另外一个列表，里面的内容是address_03里面的无重复 项 for item in address_03_set: data.append((item,address_03.count(item)))

def map_china() -> Map: c = ( Map() .add(series_name="企业数量", data_pair=data, maptype="china",zoom = 1,center=[105,38]) .set_global_opts( title_opts=opts.TitleOpts(title="中国500强企业省份分布"), visualmap_opts=opts.VisualMapOpts(max_=9999,is_piecewise=True, pieces=[{"max": 9, "min": 0, "label": "0-9","color":"#FFE4E1"}, {"max": 99, "min": 10, "label": "10-99","color":"#FF7F50"}, {"max": 499, "min": 100, "label": "100-499","color":"#F08080"}, {"max": 999, "min": 500, "label": "500-999","color":"#CD5C5C"}, {"max": 9999, "min": 1000, "label": ">=1000", "color":"#8B0000"}] ) ) ) return c

income_rate = pd_data['营业收入年增减'] compare_name = pd_data['企业名称'] income_rate = income_rate.tolist() compare_name = compare_name.tolist() m = income_rate # 求一个list中最大的50个数，并排序 max_number = heapq.nlargest(50, m) # 最大的2个数对应的，如果用nsmallest则是求最小的数及其索引 max_index = map(m.index, heapq.nlargest(50, m)) # max_index 直接输出来不是数，使用list()或者set()均可输出 #print(set(max_index)) ###{235, 140, 273, 148, 86} max_index = list(set(max_index)) #ss = [m.index(j) for j in max_number] name =[compare_name[k] for k in set(max_index)] outwb = openpyxl.Workbook() outws = outwb.create_sheet(index=0)

income_rate = income_rate.tolist() compare_name = compare_name.tolist() m = income_rate # 求一个list中最小的50个数，并排序 min_number = heapq.nsmallest(60, m) min_index = [m.index(j) for j in min_number] name =[compare_name[k] for k in set(min_index)]

###折线图 def LinePic(x_data,y_data,name): ( Line() # 进行全局设置 .set_global_opts( tooltip_opts=opts.TooltipOpts(is_show=True), # 显示提示信息,默认为显示,可以不写 xaxis_opts=opts.AxisOpts(type_="category"), yaxis_opts=opts.AxisOpts( type_="value", axistick_opts=opts.AxisTickOpts(is_show=True), splitline_opts=opts.SplitLineOpts(is_show=True), ), ) # 添加x轴的点 .add_xaxis(xaxis_data=x_data) # 添加y轴的点 .add_yaxis( series_name=name, y_axis=y_data, symbol="emptyCircle", is_symbol_show=True, label_opts=opts.LabelOpts(is_show=True), ) # 保存为一个html文件 .render(name+".html") )

for k, g in groupby(sorte
                
提示：
                    本文由神整理自网络，如有侵权请联系本站删除！
                    

                    本站声明： 

                    1、本站所有资源均来源于互联网，不保证100%完整、不提供任何技术支持； 

                    2、本站所发布的文章以及附件仅限用于学习和研究目的;不得将用于商业或者非法用途；否则由此产生的法律后果，本站概不负责！
                
                

                

                                            
上一篇：python使用Matplotlib绘制多种常见图形_python_
                                                                
下一篇：python爬取全国火锅店数量并可视化展示_python_