实战:中国大学排名定向爬取
- 爬取url:http://www.zuihaodaxue.cn/zuihaodaxuepaiming2019.html
- 爬取思路:
- 从网络上获取大学排名网页内容
- 提取网页内容中信息到合适的数据结构 (排名,学校名称,总分)
- 利用数据结构展示并输出结果
import requests
from bs4 import BeautifulSoup
import bs4
- 定义获取大学排名的函数:
def getHTMLText(url):
try:
r = requests.get(url, timeout = 30)
r.raise_for_status()
r.encoding = r.apparent_encoding
return r.text
except:
return ""
- 提取网页信息:
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])
- 按格式打印结果:
def printUnivList(ulist, num):
tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
print(tplt.format("排名","学校名称","总分",chr(12288)))
for i in range(num):
u=ulist[i]
print(tplt.format(u[0],u[1],u[2],chr(12288)))
print("Suc" + str(num))
uinfo = []
url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2019.html'
html = getHTMLText(url)
fillUnivList(uinfo, html)
printUnivList(uinfo, 20)