python爬虫并制作足球可视化图表（含源码）

import requests from bs4 import BeautifulSoup as soup import json import pandas as pd import matplotlib.pyplot as plt import numpy as np import matplotlib as mpl from matplotlib import pyplot # 请求数据, C罗的ID为2371 url = 'https://understat.com/player/2371' html = requests.get(url) # 解析处理数据 parse_soup = soup(html.content, 'lxml') scripts = parse_soup.find_all('script') strings = scripts[3].string ind_start = strings.index("('")+2 ind_end = strings.index("')") json_data = strings[ind_start:ind_end] json_data = json_data.encode('utf8').decode('unicode_escape') data = json.loads(json_data) # print(data) # 处理数据, 包含射门位置、预期进球、射门结果、赛季 x = [] y = [] xg = [] result = [] season = [] for i, _ in enumerate(data): for key in data[i]: if key == 'X': x.append(data[i][key]) if key == 'Y': y.append(data[i][key]) if key == 'xG': xg.append(data[i][key]) if key == 'result': result.append(data[i][key]) if key == 'season': season.append(data[i][key]) columns = ['X', 'Y', 'xG', 'Result', 'Season'] df_understat = pd.DataFrame([x, y, xg, result, season], index=columns) df_understat = df_understat.T df_understat = df_understat.apply(pd.to_numeric, errors='ignore') # 得到最终的结果 # print(df_understat) df_understat['X'] = df_understat['X'].apply(lambda x: x*100) df_understat['Y'] = df_understat['Y'].apply(lambda x: x*100) # print(df_understat) # 全局取消证书验证 import ssl ssl._create_default_https_context = ssl._create_unverified_context def readfromhtml(filepath): # 选择第二个表格 df = pd.read_html(filepath)[0] column_lst = list(df.columns) for index in range(len(column_lst)): column_lst[index] = column_lst[index][1] df.columns = column_lst df.drop(df[df['Player'] == 'Player'].index, inplace=True) df = df.fillna('0') df.set_index('Rk', drop=True, inplace=True) try: df['Comp'] = df['Comp'].apply(lambda x: ' '.join(x.split()[1:])) df['Nation'] = df['Nation'].astype(str) df['Nation'] = df['Nation'].apply(lambda x: x.split()[-1]) except: print('Error in uploading file:' + filepath) finally: df = df.apply(pd.to_numeric, errors='ignore') return df # 获取2020-2021欧洲五大联赛球员数据 df_fbref = readfromhtml('https://fbref.com/en/comps/Big5/shooting/players/Big-5-European-Leagues-Stats') # print(df_fbref) # from highlight_text import ax_text,fig_text from PIL import Image,ImageDraw,ImageFont import mplsoccer # 背景色 background = '#D6DBD9' # 字体颜色 text_color = 'black' mpl.rcParams['xtick.color'] = text_color mpl.rcParams['ytick.color'] = text_color mpl.rcParams['text.color'] = text_color # 中文字体 # mpl.rcParams['font.family'] = 'Hiragino Sans' plt.rcParams['font.sans-serif'] = 'Songti SC' plt.rcParams['axes.unicode_minus'] = False mpl.rcParams['legend.fontsize'] = 12 # 新建画布 fig, ax = plt.subplots(figsize=(10, 8)) # 关闭坐标轴 ax.axis('off') # 背景色填充 fig.set_facecolor(background) # 垂直方向半个足球场 pitch = mplsoccer.VerticalPitch(half=True, pitch_type='opta', line_zorder=3, pitch_color='grass') # 图表大小 ax_opta1 = fig.add_axes((0.05, 0.06, 0.45, 0.4)) ax_opta1.patch.set_facecolor(background) pitch.draw(ax=ax_opta1) # 2019-2020赛季, C罗射门位置散点图(未得分), 透明度0.6 df_fil = df_understat.loc[df_understat['Season'] == 2019] pitch.scatter(df_fil[df_fil['Result'] != 'Goal']['X'], df_fil[df_fil['Result'] != 'Goal']['Y'], s=np.sqrt(df_fil[df_fil['Result'] != 'Goal']['xG'])*100, marker='o', alpha=0.6, edgecolor='black', facecolor='grey', ax=ax_opta1) # 2019-2020赛季, C罗射门位置散点图(得分), 透明度0.9 pitch.scatter(df_fil[df_fil['Result'] == 'Goal']['X'], df_fil[df_fil['Result'] == 'Goal']['Y'], s=np.sqrt(df_fil[df_fil['Result'] == 'Goal']['xG'])*100, marker='o', alpha=0.9, edgecolor='black', facecolor='#6778d0', ax=ax_opta1, label='Goal') # 添加图例 ax_opta1.legend(loc='lower right').get_texts()[0].set_color("black") # 文字信息 ax_opta1.text(30, 61, '得分次数 : '+str(len(df_fil[df_fil['Result'] == 'Goal'])), weight='bold', size=11) ax_opta1.text(30, 64, f"预期进球 : {round(sum(df_fil['xG']),2)}", weight='bold', size=11) ax_opta1.text(30, 58, '射门次数 : '+str(len(df_fil)), weight='bold', size=11) ax_opta1.text(90, 60, '2019-20赛季', weight='bold', size=14) # 2020-2021赛季, C罗射门位置散点图 ax_opta2 = fig.add_axes((0.50, 0.06, 0.45, 0.4)) ax_opta2.patch.set_facecolor(background) pitch.draw(ax=ax_opta2) # 根据条件, 筛选数据 df_fil = df_understat.loc[df_understat['Season'] == 2020] # 未得分 pitch.scatter(df_fil[df_fil['Result'] != 'Goal']['X'], df_fil[df_fil['Result'] != 'Goal']['Y'], s=np.sqrt(df_fil[df_fil['Result']!='Goal']['xG'])*100, marker='o', alpha=0.6, edgecolor='black', facecolor='grey', ax=ax_opta2) # 得分 pitch.scatter(df_fil[df_fil['Result']=='Goal']['X'], df_fil[df_fil['Result'] == 'Goal']['Y'], s=np.sqrt(df_fil[df_fil['Result'] == 'Goal']['xG'])*100, marker='o', alpha=0.9, edgecolor='black', facecolor='#6778d0', ax=ax_opta2, label='Goal') # 添加图例, 文字信息 ax_opta2.legend(loc='lower right').get_texts()[0].set_color("black") ax_opta2.text(30, 61, '得分次数 : '+str(len(df_fil[df_fil['Result'] == 'Goal'])), weight='bold', size=11) ax_opta2.text(30, 64, f"预期进球 : {round(sum(df_fil['xG']),2)}", weight='bold', size=11) ax_opta2.text(30, 58, '射门次数 : '+str(len(df_fil)), weight='bold', size=11) ax_opta2.text(90, 60, '2020-21赛季', weight='bold', size=14) # 初始化 ax_scatter = fig.add_axes([0.52, 0.57, 0.4, 0.35]) ax_scatter.patch.set_facecolor(background) # 得到散点图的X, Y坐标值 no_90s = 10 df_fil = df_fbref[df_fbref['90s'] >= no_90s] # 前锋位置 df_fil = df_fil[df_fil['Pos'].apply(lambda x: x in ['FW', 'MF,FW', 'FW,MF'])] # 每90s预期进球和得分次数 x, y = (df_fil['xG']/df_fil['90s']).to_list(), (df_fil['Gls']/df_fil['90s']).to_list() # 生成所有前锋位置, 数据散点图 ax_scatter.scatter(x, y, alpha=0.3, c='#EF8804') # C罗的数据 df_player = df_fil[df_fil['Player'] == 'Cristiano Ronaldo'] ax_scatter.scatter(df_player['xG']/df_player['90s'], df_player['Gls']/df_player['90s'], c='blue') # 添加网格线及标签 ax_scatter.grid(visible=True, color='grey', linestyle='-.', linewidth=0.5, alpha=0.4) ax_scatter.set_xlabel('每90秒的预期进球', fontdict={'fontsize': 12, 'weight': 'bold', 'color': text_color}) ax_scatter.set_ylabel('每90秒得分', fontdict=dict(fontsize=12, weight='bold', color=text_color)) # 添加C罗的头像 ax_player = fig.add_axes([0.03, 0.53, 0.25, 0.45]) ax_player.axis('off') im = plt.imread('ronaldo.png') ax_player.imshow(im) ax_team = fig.add_axes([0.27, 0.55, 0.15, 0.15]) ax_team.axis('off') im = plt.imread('FCJ.png') ax_team.imshow(im) plt.savefig('ronaldo_viz.png', dpi=300, facecolor=background) # 添加标题信息 img = Image.open('ronaldo_viz.png') draw = ImageDraw.Draw(img) font = ImageFont.truetype(font='simsun.ttc',size = 19) draw.text(xy=(3,94),text='<克里斯蒂亚诺·罗纳尔多(C罗)> 赛季数据',font=font) font = ImageFont.truetype(font='simsun.ttc',size = 15) draw.text(xy=(25,75),text='位置: <边锋>',font=font) draw.text(xy=(25,56),text='年龄: <36>',font=font) img.save('ronaldo_viz.png') # 添加俱乐部logo # 添加备注 plt.figtext(0.07, 0.03, '制作者：张新宸 数据来源：Fbref.com、Understat.com', size=12, weigh