Preface
QS World University Rankings is an annual world university ranking published by Quacquarelli Symonds (QS), a British international education market consulting company.
Collect global university ranking data (source code has been packaged, share it with private messages for free and get it yourself)
import requests # 发送请求
import re
import csv
with open('rank.csv', mode='a', encoding='utf-8', newline='') as f:
csv_writer = csv.writer(f)
csv_writer.writerow(['country', 'rank', 'region', 'score_1', 'score_2', 'score_3', 'score_4', 'score_5', 'score_6', 'total_score', 'stars', 'university', 'year'])
def replace(str_):
str_ = re.findall('<div class="td-wrap"><div class="td-wrap-in">(.*?)</div></div>', str_)[0]
return str_
url = 'https://www.qschina.cn/sites/default/files/qs-rankings-data/cn/2057712_indicators.txt'
# 1. 发送请求
response = requests.get(url)
# <Response [200]>: 请求成功
# 2. 获取数据
json_data = response.json() # Python 字典
# 3. 解析数据
# 字典
data_list = json_data['data']
for i in data_list:
country = i['location'] # 国家/地区
rank = i['overall_rank'] # 排名
region = i['region'] # 大洲
score_1 = replace(i['ind_76']) # 学术声誉
score_2 = replace(i['ind_77']) # 雇主声誉
score_3 = replace(i['ind_36']) # 师生比
score_4 = replace(i['ind_73']) # 教员引用率
score_5 = replace(i['ind_18']) # 国际教师
score_6 = replace(i['ind_14']) # 国际学生
total_score = replace(i['overall']) # 总分
stars = i['stars'] # 星级
uni = i['uni'] # 大学名称
university = re.findall('<div class="td-wrap"><div class="td-wrap-in"><a href=".*?" class="uni-link">(.*?)</a></div></div>', uni)[0]
year = "2021" # 年份
print(country, rank, region, score_1, score_2, score_3, score_4, score_5, score_6, total_score, stars, university, year)
with open('rank.csv', mode='a', encoding='utf-8', newline='') as f:
csv_writer = csv.writer(f)
csv_writer.writerow([country, rank, region, score_1, score_2, score_3, score_4, score_5, score_6, total_score, stars, university, year])
Visual display
Import required modules
from pyecharts.charts import *
from pyecharts import options as opts
from pyecharts.commons.utils import JsCode
from pyecharts.components import Table
import re
import pandas as pd
Import Data
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)
2021 World University Rankings (QS) TOP 100
bar = (Bar()
.add_xaxis(university)
.add_yaxis('', score, category_gap='30%')
.set_global_opts(title_opts=opts.TitleOpts(title="2021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_notebook()
Chinese Universities in TOP 500
Distribution of TOP 1000 Universities by Continent
fmt_js = """function (params) {
return params.name+': '+Number(params.value[2]);}"""
mp = Map()
mp.add(
"高校数量",
data_pair,
"world",
is_map_symbol_show=False,
is_roam=False)
mp.set_series_opts(label_opts=opts.LabelOpts(is_show=False),
itemstyle_opts={
'normal': {
'areaColor': '#191970',
'borderColor': '#1773c3',
'shadowColor': '#1773c3',
'shadowBlur': 20,
'opacity': 0.8
}
})
mp.set_global_opts(
title_opts=opts.TitleOpts(title="TOP 1000高校按国家分布", pos_left='center',
title_textstyle_opts=opts.TextStyleOpts(font_size=18)),
legend_opts=opts.LegendOpts(is_show=False),
visualmap_opts=opts.VisualMapOpts(is_show=False,
max_=100,
is_piecewise=False,
dimension=0,
range_color=['rgba(255,228,225,0.6)', 'rgba(255,0,0,0.9)', 'rgba(255,0,0,1)'])
)
data_pair = [[x, y] for x, y in data_pair if x in country_list]
geo = Geo()
# 需要先将几个国家的经纬度信息加入到geo中
for k, v in loc.items():
geo.add_coordinate(k, v[0], v[1])
# 这里将geo的地图透明度配置为0
geo.add_schema(maptype="world", is_roam=False, itemstyle_opts={
'normal': {
'opacity': 0}})
geo.add("", data_pair, symbol_size=1)
# 显示标签配置
geo.set_series_opts(
label_opts=opts.LabelOpts(
is_show=True,
position='right',
color='white',
font_size=12,
font_weight='bold',
formatter=JsCode(fmt_js)),
)
grid = (
Grid(init_opts=opts.InitOpts(theme='chalk', width='1000px', height='600px'))
.add(mp, grid_opts=opts.GridOpts(pos_top="12%"))
.add(geo, grid_opts=opts.GridOpts(pos_bottom="12%"))
)
grid.render_notebook()
Continent-Country Distribution
c = (Sunburst(
init_opts=opts.InitOpts(
theme='purple-passion',
width="1000px",
height="1000px"))
.add(
"",
data_pair=data_pair,
highlight_policy="ancestor",
radius=[0, "100%"],
sort_='null',
levels=[
{
},
{
"r0": "20%",
"r": "48%",
"itemStyle": {
"borderColor": 'rgb(220,220,220)', "borderWidth": 2}
},
{
"r0": "50%", "r": "80%", "label": {
"align": "right"},
"itemStyle": {
"borderColor": 'rgb(220,220,220)', "borderWidth": 1}}
],
)
.set_global_opts(
visualmap_opts=opts.VisualMapOpts(is_show=False, max_=300, min_=0, is_piecewise=False,
range_color=['#4285f4', '#34a853', '#fbbc05', '#ea4335', '#ea4335']),
title_opts=opts.TitleOpts(title="TOP 1000\n\n大学地理分布",
pos_left="center",
pos_top="center",
title_textstyle_opts=opts.TextStyleOpts(font_style='oblique', font_size=20),))
.set_series_opts(label_opts=opts.LabelOpts(font_size=14, formatter="{b}: {c}"))
)
c.render_notebook()
Python crawls world university rankings + data visualization