1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72

#!/usr/bin/env python3
# coding=utf-8

#main.py

__author__  = 'https://blog.mzh.ren/zh/'
__version__ = (0, 1, 0)

import re
import os,sys
import requests

def get_all_markdown_files(path):
    """Get all the markdown files with all depth"""
    markdown_files = []
    for root, dirs, files in os.walk(path):
        for file in files:
            if file.endswith('.md'):
                markdown_files.append(os.path.join(root, file))
    return markdown_files

def download_files_from_markdown(markdown_file):
    """Download all the files from the markdown file"""
    markdown_file_path = os.path.dirname(markdown_file)
    items = get_date_links_from_markdown(markdown_file)
    for item in items:
        filename = markdown_file_path + '/' + get_filename_from_url(item)
        download_file(item[1], filename)

def get_date_links_from_markdown(markdown_file):
    """Get all the links from the markdown file"""
    content = read_markdown_file(markdown_file)
    date_and_links = re.findall(r'(\d{4}-\d{2}-\d{2}) \[download 4k\]\((https[^\)]+)\)', content)
    return date_and_links

def read_markdown_file(markdown_file):
    """Read the markdown file and return the content"""
    with open(markdown_file, 'r') as f:
        content = f.read()
    return content

def download_file(url, filename):
    """Download the file from the url and save it as filename"""
    if not check_file_exist(filename):
        print('Downloading {} to {}'.format(url, filename))
        r = requests.get(url)
        with open(filename, 'wb') as f:
            f.write(r.content)

def get_filename_from_url(date_and_link):
    """Get the filename from the date_and_link"""
    # ('2022-10-09', 'https://cn.bing.com/th?id=OHR.GlassOctopus_EN-US6394802515_UHD.jpg')
    return date_and_link[0] + '_' +  get_url_pram_value(date_and_link[1], 'id')

def get_url_pram_value(url, param):
    """Get the value of the param from the url"""
    regResult = re.search(r'{}=([^&]+)'.format(param), url)
    if regResult:
        return regResult.group(1)

def check_file_exist(filename):
    """Check if the file exists"""
    return os.path.exists(filename)

if __name__ == '__main__':
    if len(sys.argv) > 1:
        path = sys.argv[1]
    else:   
        path = './picture'
    markdown_files = get_all_markdown_files(path)
    for markdown_file in markdown_files:
        download_files_from_markdown(markdown_file)

1

python main.py

1

python main.py ./picture

1

python main.py ./picture/2022-11