import requests
import re
import csv
import pandas
import matplotlib.pyplot as plt
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36 Edg/120.0.0.0'}
rank = []
company_list = []
zczb_list = []
for i in range(1,18):
    if i==1:
        url = "https://top.chinaz.com/gongsi/index_zhuce.html"
    else:
        url = "https://top.chinaz.com/gongsi/index_zhuce_{}.html".format(i)
    responce = requests.get(url=url, headers=headers)
    company = re.findall('<a.*?target="_blank">(.+?)</a></h3>', responce.text)
    zczb = re.findall('<p class="RtCData"><span>注册资本：</span>(.+?)</p>', responce.text)
    for i in zczb:
        if '美' in i:
            f = round(float(re.findall(r'\d+\.?\d*', i)[0])*7.18/10000,2)
        else:
            if '万' in i:
                f = round(float(re.findall(r'\d+\.?\d*', i)[0])/10000, 2)
            else:
                f = round(float(re.findall(r'\d+\.?\d*', i)[0]), 2)
        zczb[zczb.index(i)] = f
    company_list.extend(company)
    zczb_list.extend(zczb)
rank = zip(company_list,zczb_list)
with open('content.csv','w') as f:
    w = csv.writer(f)
    w.writerows(rank)
df = pandas.read_csv('content.csv',names=['company','registered captital'],encoding='ANSI')
plt.rcParams['font.sans-serif']=['SimHei']
x = df.loc[:19,'company']
height = df.loc[:19,'registered captital']
plt.grid(axis='y',which='major')
plt.xlabel('公司')
plt.ylabel('注册资金')
plt.title('注册资金20强公司')
plt.bar(x,height,width=0.5,align='center',color='b',alpha=0.5)
plt.legend(['单位：亿人民币'])
plt.tick_params(axis='x',labelsize=9)
plt.xticks(rotation=30)
plt.show()