import requests from bs4 import BeautifulSoup allUniv = [] def getHTMLText(url): try: r = requests.get(url,timeout=30) r.raise_for_status() r.encoding = 'utf-8' return r.text except: return "" def fillUnivList(soup): data = soup.find_all('tr') for tr in data: ltd = tr.find_all('td') if len(ltd) == 0: continue singleUniv = [] for td in ltd: singleUniv.append(td.string) allUniv.append(singleUniv) def printUnivList(num): print("{:^4}{:^10}{:^5}{:^8}{:^10}".format("排名","学校名称","省份","总分","培养规模")) for i in range(num): u=allUniv[i] print("{:^4}{:^10}{:^5}{:^8}{:^10}".format(u[0],u[1],u[2],u[3],u[6])) def main(num): url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html' html = getHTMLText(url) soup = BeautifulSoup(html,"html.parser") fillUnivList(soup) printUnivList(num) main(10)数组超出范围
时间: 2024-03-22 20:40:53 浏览: 19
根据你提供的代码,问题出现在访问 `allUniv` 数组时,数组索引超出了范围。具体来说,当 `num` 大于 `allUniv` 的长度时,执行 `printUnivList` 函数时会抛出 `IndexError` 异常。
你可以在调用 `printUnivList` 函数前,先判断一下 `num` 是否超出了 `allUniv` 的长度,如果超出了则将 `num` 赋值为 `allUniv` 的长度,这样就可以避免数组越界的问题。修改后的代码如下:
```python
import requests
from bs4 import BeautifulSoup
allUniv = []
def getHTMLText(url):
try:
r = requests.get(url, timeout=30)
r.raise_for_status()
r.encoding = 'utf-8'
return r.text
except:
return ""
def fillUnivList(soup):
data = soup.find_all('tr')
for tr in data:
ltd = tr.find_all('td')
if len(ltd) == 0:
continue
singleUniv = []
for td in ltd:
singleUniv.append(td.string)
allUniv.append(singleUniv)
def printUnivList(num):
if num > len(allUniv):
num = len(allUniv) # 将 num 赋值为 allUniv 的长度
print("{:^4}{:^10}{:^5}{:^8}{:^10}".format("排名", "学校名称", "省份", "总分", "培养规模"))
for i in range(num):
u = allUniv[i]
print("{:^4}{:^10}{:^5}{:^8}{:^10}".format(u[0], u[1], u[2], u[3], u[6]))
def main(num):
url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
html = getHTMLText(url)
soup = BeautifulSoup(html, "html.parser")
fillUnivList(soup)
printUnivList(num)
main(10)
```
这样就可以避免数组越界的问题了。