[Python知识库]Python3 批量下载并保存PDF文件

Python3 批量下载并保存PDF文件

from urllib.request import urlopen
from bs4 import BeautifulSoup
import requests

url = 'PDF列表地址'
html = urlopen(url)
bs = BeautifulSoup(html, 'html.parser')
# 使用bs.findAll()方法获取所有PDF链接
linkList = bs.findAll('a',{'class':'classname'}) 
links = []
# 获取链接地址
for link in linkList:
    links.append(link.get('href'))
i = 1
# 逐一保存PDF文件
for link in links:
    localfile = 'D:/papers/paper_' + str(i) + '.pdf'
    urlfile = requests.get(link)
    with open(localfile, 'wb+') as f:
        f.write(urlfile.content)
    i += 1

下载过程慢，以后有时间再做优化。

处理过程中发现总是在请求过程中，程序会中断，在请求之前等待两秒

import time
for link in links:
    localfile = 'D:/papers/paper_' + str(i) + '.pdf'
    time.sleep(2)
    urlfile = requests.get(link)
    with open(localfile, 'wb+') as f:
        f.write(urlfile.content)
    i += 1