python爬虫获取2023世界大学排名

#爬取数据 import re import requests #发送请求 import csv # with open('rank.csv', encoding='utf-8', newline='', mode='a') as f: # csv_writer = csv.writer(f) # csv_writer.writerow(['university','region','country','score','rank','year']) # url='https://www.qschina.cn/sites/default/files/qs-rankings-data/cn/2174878_indicators.txt' # response = requests.get(url) #<Response [200]>: 请求成功 # json_date=response.json() #python字典 # def replace(str_): # str_=re.findall('<div class="td-wrap"><div class="td-wrap-in">(.*?)</div></div>',str_)[0] # return str_ # for i in json_date['data']: # year="2023" # country= i['location'] # rank= i['overall_rank'] # region= i['region'] # score=replace(i['overall']) # university=i['uni'] # university=re.findall('<div class="td-wrap"><div class="td-wrap-in"><a href=".*?" class="uni-link">(.*?)</a></div></div>',university)[0] # print(university,region,country,score,rank,year) # with open('rank.csv',encoding='utf-8',newline='',mode='a')as f: # csv_writer=csv.writer(f) # csv_writer.writerow([university,region,country,score,rank,year]) from pyecharts.charts import * from pyecharts import options as opts import pandas as pd pd.set_option('display.max_columns', None) # 展示所有列 df = pd.read_csv('rank.csv') # 香港，澳门与中国大陆地区等在榜单中是分开的记录的，这边都归为china df['loc'] = df['country'] df['country'].replace(['China (Mainland)', 'Hong Kong SAR', 'Taiwan', 'Macau SAR'],'China',inplace=True) tool_js = """ <div style="border-bottom: 1px solid rgba(255,255,255,.3); font-size: 18px;padding-bottom: 7px;margin-bottom: 7px"> {} </div> 排名：{} <br> 国家地区：{} <br> 加权总分：{} <br> """ """ 国际学生：{} <br> 国际教师：{} <br> 师生比例：{} <br> 学术声誉：{} <br> 雇主声誉：{} <br> 教员引用率：{} <br> """ df['rank']=pd.to_numeric(df['rank'],errors='coerce') # print(df.info()) t_data = df[(df.year =='2023') & (df['rank'] <= 100)] # print(t_data.head()) t_data = t_data.sort_values(by="score" , ascending=True) print(t_data.head()) university, score = [], [] for idx, row in t_data.iterrows(): tjs = tool_js.format(row['university'], row['rank'], row['country'],row['score']) if row['country'] == 'China': university.append('🇨🇳 {}'.format(re.sub( '(.*?)','',row['university']))) else: university.append(re.sub('(.*?)', '',row['university'])) score.append(opts.BarItem(name='', value=row['score'], tooltip_opts=opts.TooltipOpts(formatter=tjs))) bar = (Bar() .add_xaxis(university) .add_yaxis('', score, category_gap='30%') .set_global_opts(title_opts=opts.TitleOpts(title="2023年世界大学排名（QS） TOP 100", pos_left="center", title_textstyle_opts=opts.TextStyleOpts(font_size=20)), datazoom_opts=opts.DataZoomOpts(range_start=70, range_end=100, orient='vertical'), visualmap_opts=opts.VisualMapOpts(is_show=False, max_=100, min_=60, dimension=0, range_color=['#00FFFF', '#FF7F50']), legend_opts=opts.LegendOpts(is_show=False), xaxis_opts=opts.AxisOpts(is_show=False, is_scale=True), yaxis_opts=opts.AxisOpts(axistick_opts=opts.AxisTickOpts(is_show=False), axisline_opts=opts.AxisLineOpts(is_show=False), axislabel_opts=opts.LabelOpts(font_size=12))) .set_series_opts(label_opts=opts.LabelOpts(is_show=True, position='right', font_style='italic'), itemstyle_opts={"normal": { "barBorderRadius": [30, 30, 30, 30], 'shadowBlur': 10, 'shadowColor': 'rgba(120, 36, 50, 0.5)', 'shadowOffsetY': 5, } } ).reversal_axis()) grid = ( Grid(init_opts=opts.InitOpts(theme='purple-passion', width='1000px', height='1200px')) .add(bar, grid_opts=opts.GridOpts(pos_right='10%', pos_left='20%')) ) grid.render('3.html')