import requests
from bs4 import BeautifulSoup
import re
import pymysql

url = 'https://openaccess.thecvf.com/CVPR2020?day=2020-06-18'
response = requests.get(url)

obj1 = re.compile(r'<dt class="ptitle"><br>.*?.html">(?P<name>.*?)</a></dt>.*?'
                  r'\[<a href="(?P<pdf>.*?)">pdf</a>].*?
 
'
                  r'author = {(?P<author>.*?)},<br>.*?'
                  r'title = {(?P<title>.*?)},<br>.*?'
                  r'booktitle = {(?P<booktitle>.*?)},<br>', re.S)

result = obj1.finditer(response.text)

# 連線資料庫
conn = pymysql.connect(host='localhost
 
', user='root', password='123456', database='exercise', charset='utf8', port=3306)
# 建立遊標物件
cursor = conn.cursor()
sql = 'INSERT INTO cvpr(`name`, pdf, author, title, booktitle, `date`) values(%s,%s,%s,%s,%s,%s)'

for it in result:
    try:
        data = [it.group('name'), it.group('pdf'), it.group('
 
author'), it.group('title'), it.group('booktitle'), 20200618]
        cursor.execute(sql, data)
        conn.commit()
    except Exception as e:
        print(e)


response.close()

# 關閉遊標
cursor.close()
# 關閉連線
conn.close()

print('over!!!')

　　不足的一點：你需要手動更換網址來爬取不同日期的論文資訊。

　　相關資料庫結構也貼在這裡：