案例(一)python预热
项目三:爬取某省的大学排名
输入某省名称,从上海交通大学研发的“软科中国最好大学排名2020”(http://www.zuihaodaxue.cn/zuihaodaxuepaiming2020.html)爬取数据,输出该省2020年的大学排名。
输入: 广东
输出:
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):
tds = tr('td')
ulist.append([tds[0].string, tds[1].string, tds[2].string])
def printUnivList(ulist, num, place):
tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
print("{:^10}\t{:^6}\t{:^10}".format("排名", "学校名称", "省市"))
for i in range(num):
u = ulist[i]
if u[2] == place:
print(tplt.format(u[0], u[1], u[2], chr(12288)))
# print("{:^10}\t{:^6}\t{:^10}".format(u[0], u[1], u[2]))
else:
continue
def main():
uinfo = []
url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2019.html'
html = getHTMLText(url)
fillUnivList(uinfo, html)
printUnivList(uinfo, 549, "广东") # 20 univs
main()
运行结果: