# -*- coding: utf-8 -*-
"""
Created on Thu May 12 14:45:14 2022

@author: pzh
"""

# %% ChinaTop500Company.py
import requests
import re
import csv
import pandas as pd
# 设置请求头信息
headers = {
    "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36"
}
# 存储内容
message = []
# 总共16个页面的数据
for page in range(16):
    # 组装url
    if page == 0:
        url = "https://top.chinaz.com/gongsitop/index_500top.html"
    else:
        url = "https://top.chinaz.com/gongsitop/index_500top_{}.html".format(page + 1)
    # 使用reqeusts模快发起 GET 请求
    response = requests.get(url, headers=headers)
    html = response.text
    # 使用 findall 函数来获取数据
    # 公司名
    company = re.findall('<a.*?target="_blank">(.+?)</a></h3>', html)
    # 注册资本
    money = re.findall('注册资本：</span>(.*?)</p>', html)
    pageOne = list(zip(company, money))
    # 合并列表
    message.extend(pageOne)

with open('content2.csv', 'w') as f:
    w = csv.writer(f)
    w.writerows(message)
    
# %% 读取数据
import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
df = pd.read_csv("content2.csv", names=["company", "money"], encoding = 'gbk')
money = df['money'].values
output = []
i = 0
for elem in money:
    st = str(elem)
    if '万美元' in st:
        num = eval(re.sub(u'([^\u0030-\u0039\u002e\uffe5])', '', st)) / 10000 * 6.79
    elif '万' in st:
        num = eval(re.sub(u'([^\u0030-\u0039\u002e\uffe5])', '', st)) / 10000

    elif st == 'nan':
        num = 0
    else:
        num = eval(re.sub(u'([^\u0030-\u0039\u002e\uffe5])', '', st))
    df['money'].values[i] = round(num, 2)
    i = i + 1
df2 = df.sort_values(by = ['money'], ascending = False)
df3 = df2.head(20)

#绘图
x = list(range(20))
x = x[::-1]
y = df3['money'].values
plt.barh(x, y)
k = 0
plt.yticks(x, df3['company'].values)
for i, j in zip(x, y):
    plt.text(j, i, j, ha = 'right', va = 'center', fontsize = 8)
    k = k + 1
plt.savefig('ChinaTop500Company.png')