爬取学校学术报告信息
import requests
import re
def get_page(url):
req = requests.get(url)
req.encoding = 'utf-8'
return req.text
def bg(page_text):
key = re.findall('target="_blank" title="(.*?)">',page_text)
print(key)
if __name__ == '__main__':
url = 'http://www.xiyou.edu.cn/tzxx/xsxx.htm'
page_text = get_page(url)
bg(page_text)
运行结果如下
