此处所写的爬虫是基于requests+bs4库实现的,通过给定一个固定URL:http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html,获取其中的排名、学校名称、总分等三项信息,该URL指向的页面如下所示:
代码实现如下所示:
import requests
from bs4 import BeautifulSoup
import bs4
def getHTMLText(url):
try:
r = requests.get(url, timeout = 30)
#检查Response对象的状态码,若不是200抛出异常
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')#等价于tr.find_all('td')
uList.append([tds[0].string, tds[1].string, tds[3].string])
def printUnivList(uList, num):
#此处format函数的应用可参考:http://blog.csdn.net/hduxiejun/article/details/56312762
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)))
def main():
uinfo = []
url = "http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html"
html = getHTMLText(url)
fillUnivList(uinfo, html)
printUnivList(uinfo, 20)#只获取排名前20的大学
main()
运行效果如下所示: