定向爬虫

功能描述

还得确定排名信息是不是写在HTML里面

程序设计

实例代码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
import requests
from bs4 import BeautifulSoup
import bs4
def getHTMLTest(url):
try:
r = requests.get(url)
r.raise_for_status()
r.encoding = r.apparent_encoding
return r.text
except:
return ""

def fillUnivList(ulist, html):
soup = BeautifulSoup(html, "html.parser")
for tr in soup.find('tbody').children:
if isinstance(tr, bs4.element.Tag):
tds = tr('td')
ulist.append([tds[0].string, tds[1].string, tds[2].string, tds[3].string])

def printUnivLIst(ulist, num):
tplt = "{0:^10}\t{1:^10}\t{2:{4}^10}\t{3:^10}"
print(tplt.format("排名", "学校名称", "地区", "分数", chr(12288)))
for i in range(num):
u = ulist[i]
print(tplt.format(u[0], u[1], u[2], u[3], chr(12288)))

def main():
uinfo = []
url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2018.html'
html = getHTMLTest(url)
fillUnivList(uinfo, html)
printUnivLIst(uinfo, 20)
main()