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: if '大学' in td.text: field=td.text.split(' ')[1] else: field=td.text.replace('\n','').replace(' ','') singleUniv.append(field) allUniv.append(singleUniv) def printUnivList(num): print('{:<4}{:<10}{:<5}{:<8}{:<8}'.format('排名','学校名称','省市','总分','人才培养')) for i in range(num): u=allUniv[i] print('{:<4}{:<10}{:<5}{:<8}{:<8}'.format(u[0],u[1],u[2],u[4],u[5])) def main(): url = 'https://www.shanghairanking.cn/rankings/bcur/2023' html = getHTMLText(url) soup = BeautifulSoup(html, 'html.parser') fillUnivList(soup) printUnivList(10) main()

这段代码是爬取 2023 年上海交通大学世界大学学术排名的前 10 名大学，并输出这些大学的排名、名称、省市、总分、人才培养等信息。具体实现过程包括：定义 getHTMLText 函数获取指定 url 的 html 文本，定义 fillUnivList 函数解析 html 并将所需信息存入 allUniv 列表中，定义 printUnivList 函数输出前 num 个大学的信息，最后在 main 函数中调用以上三个函数实现主要功能。

相关问题

import requests from bs4 import BeautifulSoup def getHTMLText(url): try: r = requests.get(url,timeout=30) r.raise_for_status() r.encoding = r.apparent_encoding return r.text except: return "产生异常" def jiexi(html_doc): soup = BeautifulSoup(html_doc,"html.parser") links = soup.find_all('a') for link in links: print(link.name,link["nref"],link.get.next()) if __name__ == 'main': url = "https://wallhaven.cc/toplist?page=7" print(getHTMLText(url))改进代码

这段代码可以改进的地方有：

1. 函数名jiexi不太直观，可以改为更明确的parse_links。

2. 在解析链接时，可以加上判断，如果链接是以http或https开头的，才输出链接信息，否则忽略。

3. 在主程序中，应该调用parse_links函数，而不是直接打印HTML页面内容。

改进后的代码如下：

import requests
from bs4 import BeautifulSoup

def get_html_text(url):
    try:
        r = requests.get(url, timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return "产生异常"
    
def parse_links(html_doc):
    soup = BeautifulSoup(html_doc, "html.parser")
    links = soup.find_all('a')
    for link in links:
        if link.has_attr('href') and (link['href'].startswith('http') or link['href'].startswith('https')):
            print(link.name, link['href'], link.get_text())

if __name__ == '__main__':
    url = "https://wallhaven.cc/toplist?page=7"
    html_text = get_html_text(url)
    parse_links(html_text)

这样修改后，代码更加清晰易懂，功能也更加完善。

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

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：

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。