最近项目需要将批量链接中的pdf文档爬下来处理,根据以下步骤完成了任务:
参考资料:
1 import urllib.request
2 import os
3
4 def getFile(url):
5 file_name = url.split('/')[-1]
6 u = urllib.request.urlopen(url)
7 f = open(file_name, 'wb')
8 block_sz = 8192
9 while True:
10 buffer = u.read(block_sz)
11 if not buffer:
12 break
13 f.write(buffer)
14 f.close()
15 print("Sucessful to download" + " " + file_name)
16
17 os.chdir(os.path.join(os.getcwd(), 'pdf_download'))
18
19 f=open('E:/VGID_Text/url_list.txt')
20 url_list=f.readlines()
21 url_lst=[]
22 for line in url_list:
23 line=line.rstrip("\n")
24 getFile(line)