python编程-24：实例1-中国大学排名爬虫

源码：

输出优化前

1. #CrawUnivRankingA.py
2. import requests
3. from bs4 import BeautifulSoup
4. import bs4
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. def fillUnivList(ulist, html):
16.     soup = BeautifulSoup(html, "html.parser")
17.     for tr in soup.find('tbody').children:
18.         if isinstance(tr, bs4.element.Tag):
19.             tds = tr('td')
20.             ulist.append([tds[0].string, tds[1].string, tds[3].string])
21.  
22. def printUnivList(ulist, num):
23.     print("{:^10}\t{:^6}\t{:^10}".format("排名","学校名称","总分"))
24.     for i in range(num):
25.         u=ulist[i]
26.         print("{:^10}\t{:^6}\t{:^10}".format(u[0],u[1],u[2]))
27.      
28. def main():
29.     uinfo = []
30.     url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
31.     html = getHTMLText(url)
32.     fillUnivList(uinfo, html)
33.     printUnivList(uinfo, 20) # 20 univs
34. main()

输出优化后：

1. #CrawUnivRankingB.py
2. import requests
3. from bs4 import BeautifulSoup
4. import bs4
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. def fillUnivList(ulist, html):
16.     soup = BeautifulSoup(html, "html.parser")
17.     for tr in soup.find('tbody').children:
18.         if isinstance(tr, bs4.element.Tag):
19.             tds = tr('td')
20.             ulist.append([tds[0].string, tds[1].string, tds[3].string])
21.  
22. def printUnivList(ulist, num):
23.     tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
24.     print(tplt.format("排名","学校名称","总分",chr(12288)))
25.     for i in range(num):
26.         u=ulist[i]
27.         print(tplt.format(u[0],u[1],u[2],chr(12288)))
28.      
29. def main():
30.     uinfo = []
31.     url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
32.     html = getHTMLText(url)
33.     fillUnivList(uinfo, html)
34.     printUnivList(uinfo, 20) # 20 univs
35. main()

原文地址： http://www.icourse163.org/learn/BIT-1001870001?tid=1001962001#/learn/content?type=detail&id=1002702163&cid=1003075396