[已解决]一个简单的网页排名爬取，但是返回的内容是空的

CsY光子精灵

爬虫的目的是爬取http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html这个网页上的大学排名列表。但是返回的内容是空的。

1. import requests
   
2. from bs4 import BeautifulSoup
   
3. import bs4
   
4. 
   
5. def getHTMLText(url):
   
6.     try:
   
7.         r = requests.get(url,timeout = 30)
   
8.         r.raise_for_status()
   
9.         r.encoding = r.apparent_encoding
   
10.         return r.text
    
11.     except:
    
12.         return""
    
13.    
    
14. 
    
15. def fillUnivList(ulist,html):
    
16.     soup = BeautifulSoup(html,"html.parser")
    
17.                         
    
18.     for tr in soup.find('tbody').children:
    
19.         if isinstance(tr,bs4.element.Tag):
    
20.             tds = tr('td')
    
21.             ulist.append([tds[0].string,tds[1].string,tds[2].string])
    
22.                         
    
23.    
    
24. 
    
25. def printUnivList(ulist,num):
    
26.     print("{:^10}\t{:^6}\t{:^10}".format("排名","学校名称","总分"))
    
27.     for i in range(num):
    
28.         u=ulist[i]
    
29.         print("{:^10}\t{:^6}\t{:^10}".format("u[0]","u[1]","u[2]"))
    
30.         
    
31.    
    
32. 
    
33. def  main():
    
34.     uinfo=[]
    
35.     url=" http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html"
    
36.     html = getHTMLText(url)
    
37.     fillUnivList(uinfo,html)
    
38.     printUnivList(uinfo,20)
    
39. 
    
40. main()
    

复制代码

最佳答案

月排行榜 / 总排行榜

Twilight6

2020-4-30 17:49:27

1. import requests
   
2. from bs4 import BeautifulSoup
   
3. import bs4
   
4. 
   
5. 
   
6. def getHTMLText(url):
   
7.     try:
   
8.         r = requests.get(url, timeout=30)
   
9.         r.raise_for_status()
   
10.         r.encoding = r.apparent_encoding
    
11.         return r.text
    
12.     except:
    
13.         return ""
    
14. 
    
15. 
    
16. def fillUnivList(ulist, html):
    
17.     soup = BeautifulSoup(html, "html.parser")
    
18. 
    
19.     for tr in soup.find('tbody').children:
    
20.         if isinstance(tr, bs4.element.Tag):
    
21.             tds = tr('td')
    
22.             ulist.append([tds[0].string, tds[1].string, tds[3].string])
    
23. 
    
24. 
    
25. 
    
26. 
    
27. def printUnivList(ulist, num):
    
28.     print("{:^10}\t{:^6}\t{:^10}".format("排名", "学校名称", "总分"))
    
29.     for i in range(num):
    
30.         u = ulist[i]
    
31.         print("{:^10}\t{:^10}\t{:^10}".format(u[0], u[1], u[2]))
    
32. 
    
33. 
    
34. def main():
    
35.     uinfo = []
    
36.     url = " http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html"
    
37.     html = getHTMLText(url)
    
38.     fillUnivList(uinfo, html)
    
39.     return printUnivList(uinfo, 20)
    
40. 
    
41. 
    
42. main()

复制代码

都帮你改了下，就是总分那边不居中

跳转到最佳答案楼层

Twilight6

你没有设置函数的retuen吧 最后

1. def main():
   
2.     uinfo = []
   
3.     url = " http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html"
   
4.     html = getHTMLText(url)
   
5.     fillUnivList(uinfo, html)
   
6.     return printUnivList(uinfo, 20)

复制代码

要retuen才有返回值

还有这

1. def printUnivList(ulist, num):
   
2.     print("{:^10}\t{:^6}\t{:^10}".format("排名", "学校名称", "总分"))
   
3.     for i in range(num):
   
4.         u = ulist[i]
   
5.         print("{:^10}\t{:^6}\t{:^10}".format(u[0], u[1], u[2]))

复制代码

这里你把u[0], u[1], u[2],加上了引号应该去掉把

March2615

我这里显示是可以得到结果的
另外，你总分爬取写错了

Twilight6

1. import requests
   
2. from bs4 import BeautifulSoup
   
3. import bs4
   
4. 
   
5. 
   
6. def getHTMLText(url):
   
7.     try:
   
8.         r = requests.get(url, timeout=30)
   
9.         r.raise_for_status()
   
10.         r.encoding = r.apparent_encoding
    
11.         return r.text
    
12.     except:
    
13.         return ""
    
14. 
    
15. 
    
16. def fillUnivList(ulist, html):
    
17.     soup = BeautifulSoup(html, "html.parser")
    
18. 
    
19.     for tr in soup.find('tbody').children:
    
20.         if isinstance(tr, bs4.element.Tag):
    
21.             tds = tr('td')
    
22.             ulist.append([tds[0].string, tds[1].string, tds[3].string])
    
23. 
    
24. 
    
25. 
    
26. 
    
27. def printUnivList(ulist, num):
    
28.     print("{:^10}\t{:^6}\t{:^10}".format("排名", "学校名称", "总分"))
    
29.     for i in range(num):
    
30.         u = ulist[i]
    
31.         print("{:^10}\t{:^10}\t{:^10}".format(u[0], u[1], u[2]))
    
32. 
    
33. 
    
34. def main():
    
35.     uinfo = []
    
36.     url = " http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html"
    
37.     html = getHTMLText(url)
    
38.     fillUnivList(uinfo, html)
    
39.     return printUnivList(uinfo, 20)
    
40. 
    
41. 
    
42. main()

复制代码

都帮你改了下，就是总分那边不居中