You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
86 lines
3.4 KiB
86 lines
3.4 KiB
import requests
|
|
import re
|
|
import csv
|
|
import pandas as pd
|
|
import matplotlib.pyplot as plt
|
|
import warnings
|
|
|
|
warnings.filterwarnings("ignore")
|
|
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"
|
|
}
|
|
message = []
|
|
message2 = []
|
|
|
|
|
|
def transform(capitals):
|
|
capital1 = []
|
|
for capital in capitals:
|
|
if capital:
|
|
numb = re.findall(r'\d+\.?\d*', capital)
|
|
if capital[0:5] == "(人民币)" or capital[-5:] == "万元人民币" or capital[-5:] == "万人民币元" or capital[
|
|
-4:] == "万人民币" or capital[
|
|
-2:] == "万元" or capital[
|
|
-1:] == "万":
|
|
capital = round(float(numb[0]) / 10000, 2)
|
|
elif capital[0:4] == "(港币)" or capital[-3:] == "万港币":
|
|
capital = round(float(numb[0]) * 0.9392 / 10000, 2)
|
|
elif capital[-3:] == "万美元":
|
|
capital = round(float(numb[0]) * 7.1876 / 10000, 2)
|
|
else:
|
|
capital = round(float(numb[0]), 2)
|
|
capital1.append(capital)
|
|
return capital1
|
|
def getInfo(html):
|
|
company = re.findall('<a.*?target="_blank">(.*?)</a></h3>', html)
|
|
capital = re.findall('注册资本：</span>(.*?)</p>', html)
|
|
capital1 = transform(capital)
|
|
pageTwo = list(zip(company, capital1))
|
|
message2.extend(pageTwo)
|
|
|
|
def save_message(list_message):
|
|
list2 = list_message[1]
|
|
with open("content2.csv", "w", encoding='utf-8') as f:
|
|
w = csv.writer(f)
|
|
w.writerows(list2)
|
|
|
|
def draw_first():
|
|
lc = pd.read_csv('content2.csv', names=["company", "capital"])
|
|
data = lc.sort_values(["capital"], ascending=False).head(20)
|
|
|
|
def autolabel(rects):
|
|
for rect in rects:
|
|
height = rect.get_height()
|
|
plt.text(rect.get_x() + rect.get_width() / 100. - 0.2, 1.1 * height, '%s' % int(height))
|
|
x_data = data['capital']
|
|
y_labels = data['company']
|
|
autolabel(plt.bar(x=range(0, len(x_data)), height=x_data, tick_label=y_labels))
|
|
plt.xlabel('公司排名', labelpad=20, fontsize=12, fontfamily='sans-serif', color='gray')
|
|
plt.ylabel('注册资金（单位：亿元）', labelpad=15, fontsize=12, fontfamily='sans-serif', color='gray')
|
|
plt.title('注册资金top20的公司', pad=20, fontsize=16, fontfamily='sans-serif', color='black')
|
|
plt.xticks(rotation=270)
|
|
plt.gca().spines['top'].set_visible(False)
|
|
plt.gca().spines['right'].set_visible(False)
|
|
plt.gcf().set_facecolor('white')
|
|
plt.tight_layout()
|
|
|
|
|
|
|
|
def main():
|
|
for page in range(16):
|
|
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)
|
|
|
|
response = requests.get(url, headers=headers)
|
|
html = response.text
|
|
getInfo(html)
|
|
list_message = [message, message2]
|
|
save_message(list_message)
|
|
draw_first()
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main()
|