QzZq博客

网址https://www.cnblogs.com/zhangzhangtabszj/p/14592061.html

 1 # -- coding:UTF-8 --<code>
 2 import requests
 3 import re
 4 from io import BytesIO
 5 
 6 file = open("E:/cnf/test.txt")  # 打开存放链接的TXT文档
 7 num = 0
 8 while 1:
 9     line = file.readline()  # 逐行读链接
10     if not line:
11         break
12     print("正在下载 第 %d cnf...." % num)
13     num += 1
14     image_url = line
15     ima = image_url.replace('\n','') #去除每行的'\n'，不然会404
16     try:
17         requests.packages.urllib3.disable_warnings()
18         r = requests.get(ima, verify=False)  # 创建响应对象
19         path = re.sub("https://gbd.iti.kit.edu/file/", "E:/cnf/", line)
20         # 通过re模块的搜索和替换功能，生成下载文档的保存地址
21         path = re.sub('\n', '', path + ".cnf.zip")  # 删除path末尾的换行符'\n'
22         f = open(path, "wb")
23         f.write(r.content)  # 将响应对象的内容写下来
24         f.close()
25     except Exception as e:
26          print('无法下载，%s' % e)
27          continue
28 file.close()

chenzhen0530的博客

网址：https://www.cnblogs.com/chenzhen0530/p/10619668.html

 1 #coding=utf-8
 2 """
 3 目标：提供一个函数能够从网上下载资源
 4 输入：
 5     url列表
 6     保存路径
 7 输出：
 8     保存到指定路径中的文件
 9 要求：
10     能够实现下载过程，即从0%到100%可视化
11 """
12 # =====================================================
13 from six.moves import urllib
14 import os
15 import sys
16 
17 
18 def download_and_extract(filepath, save_dir):
19     """根据给定的URL地址下载文件
20 
21     Parameter:
22         filepath: list 文件的URL路径地址
23         save_dir: str  保存路径
24     Return:
25         None
26     """
27     for url, index in zip(filepath, range(len(filepath))):
28         filename = url.split('/')[-1]
29         save_path = os.path.join(save_dir, filename)
30         urllib.request.urlretrieve(url, save_path)
31         sys.stdout.write('\r>> Downloading %.1f%%' % 
                              (float(index + 1) / float(len(filepath)) * 100.0))
32         sys.stdout.flush()
33     print('\nSuccessfully downloaded')
34 
35 
36 def _get_file_urls(file_url_txt):
37     """根据URL路径txt文件，获取URL地址列表
38 
39     Parameter:
40         file_url_txt: str  txt文件本地路径
41     Return:
42         filepath: list  URL列表
43     """
44     filepath = []
45     file = open(file_url_txt, 'r')
46     for line in file.readlines():
47         line = line.strip()
48         filepath.append(line)
49     file.close()
50     return filepath
51 
52 
53 if __name__ == '__main__':
54     file_url_txt = 'file_url_txt.txt'
55     save_dir = 'save_dir/'
56     filepath = _get_file_urls(file_url_txt)
57     download_and_extract(filepath, save_dir)

1 import requests
2 url = "https://gbd.iti.kit.edu/file/002a0330958a14deb23dcc84b5489e8a/"
3 r = requests.get(url)
4 with open("uri2022/cnf02.xz","wb") as f:
5     f.write(r.content)

缺点：没有保留原有文件名。

1 import requests
2 file_url = 'https://gbd.iti.kit.edu/file/002a0330958a14deb23dcc84b5489e8a/'
3 r = requests.get(file_url, stream = True)
4 with open("uri2022/cnf01.xz","wb") as f:
5     for chunk in r.iter_content(chunk_size = 1024**2):
6         if chunk:
7             f.write(chunk)

1 import wget
2 url = 'https://gbd.iti.kit.edu/file/002a0330958a14deb23dcc84b5489e8a/'
3 #filename = wget.download(url)
4 filename = wget.download(url, out="uri2022/")

 1 # -- coding:UTF-8 --<code>
 2 import requests
 3 import re
 4 import wget
 5 
 6 file = open("track_main_2022.uri")  # 打开存放链接的TXT文档
 7 num = 0
 8 while 1:
 9     line = file.readline()  # 逐行读链接
10     if not line:
11         break
12     print("正在下载 第 %d cnf...." % num)
13     num += 1
14     image_url = line
15     ima = image_url.replace('\n','') #去除每行的'\n'，不然会404
16     try:
17         url = ima
18         filename = wget.download(url, out="uri2022/")
19     except Exception as e:
20          print('无法下载，%s' % e)
21          continue
22 file.close()