1 # -*- coding: utf-8 -*-
2 '''
3 获取中国大学的排名
4 @author: bpf
5 '''
6 import requests
7 from bs4 import BeautifulSoup
8 import pandas
9 # 1. 获取网页内容
10 def getHTMLText(url):
11 try:
12 r = requests.get(url, timeout = 30)
13 r.raise_for_status()
14 r.encoding = 'utf-8'
15 return r.text
16 except Exception as e:
17 print("Error:", e)
18 return ""
19
20 # 2. 分析网页内容并提取有用数据
21 def fillTabelList(soup): # 获取表格的数据
22 tabel_list = [] # 存储整个表格数据
23 Tr = soup.find_all('tr')
24 for tr in Tr:
25 Td = tr.find_all('td')
26 if len(Td) == 0:
27 continue
28 tr_list = [] # 存储一行的数据
29 for td in Td:
30 tr_list.append(td.string)
31 tabel_list.append(tr_list)
32 return tabel_list
33
34 # 3. 可视化展示数据
35 def PrintTableList(tabel_list, num):
36 # 输出前num行数据
37 print("{1:^2}{2:{0}^10}{3:{0}^5}{4:{0}^5}{5:{0}^8}".format(chr(12288), "排名", "学校名称", "省市", "总分", "生涯质量"))
38 for i in range(num):
39 text = tabel_list[i]
40 print("{1:{0}^2}{2:{0}^10}{3:{0}^5}{4:{0}^8}{5:{0}^10}".format(chr(12288), *text))
41
42 # 4. 将数据存储为csv文件
43 def saveAsCsv(filename, tabel_list):
44 FormData = pandas.DataFrame(tabel_list)
45 FormData.columns = ["排名", "学校名称", "省市", "总分", "生涯质量", "培养结果", "科研规模", "科研质量", "顶尖成果", "顶尖人才", "科技服务", "产学研合作", "成果转化"]
46 FormData.to_csv(filename, encoding='utf-8', index=False)
47
48 if __name__ == "__main__":
49 url = "http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html"
50 html = getHTMLText(url)
51 soup = BeautifulSoup(html, features="html.parser")
52 data = fillTabelList(soup)
53 #print(data)
54 PrintTableList(data, 10) # 输出前10行数据
55 saveAsCsv("D:\University_Rank.csv", data)
运行结果：
