用requests + bs4库做的小练习:定向爬取中国大学排名
url : http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html
import requests
from bs4 import BeautifulSoup
import bs4
def getHTMLText(url):
try:
r = requests.get(url, timeout = 30)
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):
#将每一个tr标签中的td标签存入一个列表tds中
tds = tr('td')
#向ulist中增加我们需要的字段,比如大学排名、大学名称,大学排分等
ulist.append([tds[0].string, tds[1].string, tds[2].string])
def printUnivList(ulist, num):
tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
#打印表头
print(tplt.format("排名", "学校名称", "学校分数", chr(12288)))
for i in range(num):
u = ulist[i]
#表中其他信息输入格式要与表头相一致
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)
if __name__ == '__main__':
main()
经验总结:
1. 学习了用print.format函数进行排版输出
2. 利用 chr(12288)进行设置中文间隔对齐