import requests
from bs4 import BeautifulSoup
import bs4
target = "http://www.zuihaodaxue.cn/zuihaodaxuepaiming2019.html"
def start_page(url,callback):
resp = requests.get(url)
callback(resp.content)
def printHtml(text):
soup = BeautifulSoup(text, "html.parser")
# print(soup)
table = soup.find('tbody')
list = []
for tr in table.find_all('tr'):
if isinstance(tr ,bs4.element.Tag):
tds = tr('td')
list.append([tds[0].string,tds[1].string,tds[3].string])
print("大学排名 大学名字 分数")
for school in list:
print("{} {} {}" .format(school[0],school[1],school[2]))
start_page(target,callback=printHtml)
#python爬虫实战,爬取学校排名
最新推荐文章于 2024-04-29 21:26:07 发布