e5k.github.io/tag_generator.py at master · e5k/e5k.github.io · GitHub

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
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
#!/usr/bin/env python

'''
tag_generator.py
Copyright 2017 Long Qian
Contact: lqian8@jhu.edu
This script creates tags for your Jekyll blog hosted by Github page.
No plugins required.
'''

import glob
import os
tag_dir 	= 'tag/'
post_dir 	= '_posts/'
filenames 	= glob.glob(post_dir + '*md')

page_dir    = 'pages/'
filenames 	= filenames + glob.glob(page_dir + '*md')

#post_dir 	= 'pages/'

#filenames = filenames + [os.path.join(root, name)
#             for root, dirs, files in os.walk(post_dir)
#             for name in files
#             if name.endswith(('md'))]


print filenames

total_tags = []
for filename in filenames:
    f = open(filename, 'r')
    crawl = False
    for line in f:
        if crawl:
            current_tags = line.strip().split()
            if current_tags[0] == 'tags:':
                total_tags.extend(current_tags[1:])
                crawl = False
                break
        if line.strip() == '---':
            if not crawl:
                crawl = True
            else:
                crawl = False
                break
    f.close()


total_tags = set(total_tags)

old_tags = glob.glob(tag_dir + '*.md')
for tag in old_tags:
    os.remove(tag)

for tag in total_tags:
    tag_filename = tag_dir + tag + '.md'
    f = open(tag_filename, 'a')
    write_str = '---\nlayout: tagpage\ntitle: \"Tag: ' + tag + '\"\ntag: ' + tag + '\nrobots: noindex\n---\n'
    f.write(write_str)
    f.close()
print("Tags generated, count", total_tags.__len__())


category_dir = 'category/'

total_categories = []
for filename in filenames:
    f = open(filename, 'r')
    crawl = False
    for line in f:
        if crawl:
            current_categories = line.strip().split()
            if current_categories[0] == 'categories:':
                total_categories.extend(current_categories[1:])
                crawl = False
                break
        if line.strip() == '---':
            if not crawl:
                crawl = True
            else:
                crawl = False
                break
    f.close()
total_categories = set(total_categories)

old_categories = glob.glob(category_dir + '*.md')
for category in old_categories:
    os.remove(category)

for category in total_categories:
    category_filename = category_dir + category + '.md'
    f = open(category_filename, 'a')
    write_str = '---\nlayout: categorypage\ntitle: \"Category: ' + category + '\"\ncategories: ' + category + '\nrobots: noindex\n---\n'
    f.write(write_str)
    f.close()
print("Categories generated, count", total_categories.__len__())