IJCAI2017论文下载python脚本

最新推荐文章于 2022-09-25 15:51:38 发布

NanfengDai

最新推荐文章于 2022-09-25 15:51:38 发布

阅读量257

点赞数 1

本文链接：https://blog.csdn.net/qq_25905637/article/details/77504529

版权

# ！、usr/bin/env.python
# ._*_ coding:utf-8 _*_

import re
import requests
import urllib.request
import os

r = requests.get('http://www.ijcai.org/proceedings/2017/')
data = r.text

link_list = re.findall(r"(?<=href=\").+?pdf(?=\">PDF)|(?<=href=\').+?pdf(?=\">PDF)", data)
name_list = re.findall(r"(?<=\"title\">).+?(?=</div>)", data)
cnt = 0
num = len(link_list)

localDir = 'C:\IJCAI2017\\'
if not os.path.exists(localDir):
    os.makedirs(localDir)

while cnt < num:
    url = link_list[cnt]
    if cnt > 0:
        url = url[-8:]
    file_name = name_list[cnt]
    file_name = file_name.replace('\"', '_')
    file_name = file_name.replace('?', '_')
    file_name = file_name.replace('/', '_')
    file_name = file_name.replace(' (Extended Abstract)', '')
    file_path = localDir + file_name + '.pdf'
    # download pdf files
    print('[' + str(cnt+1) + '/' + str(num) + "]  Downloading -> " + file_path)

    urllib.request.urlretrieve('http://www.ijcai.org/proceedings/2017/'+url, file_path)
    cnt = cnt + 1
print("all download finished")

Python的版本是3.5，网速下得可能会比较慢