Mercurial > public > pelican-blog

comparison __bgn/import_blogophile.py @ 2:b7be75ff95b0

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Created a script to convert my Blogofile posts to Pelican.
author Brian Neal <bgneal@gmail.com>
date Wed, 29 Jan 2014 21:32:04 -0600
parents
children c3115da3ff73
comparison
equal deleted inserted replaced
1:64edb34396b6 2:b7be75ff95b0
1 #!/usr/bin/env python
2 """
3 A simple script to convert my Blogofile restructured text posts into the format
4 expected by Pelican.
5
6 """
7 # Copyright (C) 2014 by Brian Neal.
8 #
9 # Permission is hereby granted, free of charge, to any person obtaining a copy
10 # of this software and associated documentation files (the "Software"), to deal
11 # in the Software without restriction, including without limitation the rights
12 # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
13 # copies of the Software, and to permit persons to whom the Software is
14 # furnished to do so, subject to the following conditions:
15 #
16 # The above copyright notice and this permission notice shall be included in
17 # all copies or substantial portions of the Software.
18 #
19 # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
20 # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
21 # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
22 # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
23 # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
24 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
25 # THE SOFTWARE.
26
27 import datetime
28 import os
29 import re
30 import time
31
32
33 SRC_DIR = os.path.expanduser('~/coding/python/virtualenvs/blogofile/blog/_posts')
34 DST_DIR = os.path.expanduser('~/coding/python/venvs/blog/blog-pelican/content')
35
36 TITLE_RE = re.compile(r'^title: (?P<title>.*)$')
37 DATE_RE = re.compile(r'^date: (?P<year>\d{4})/'
38 r'(?P<month>\d{1,2})/'
39 r'(?P<day>\d{1,2})\s*'
40 r'(?P<time>\d{2}:\d{2}:\d{2})\s*$')
41 CAT_RE = re.compile(r'^categories: (?P<cats>.*)$')
42
43 PELICAN_FMT = """\
44 {title}
45 {title_underline}
46
47 :date: {date}
48 :category: coding
49 :tags: {tags}
50 :slug: {slug}
51 :author: Brian Neal
52
53 {content}
54 """
55
56
57 class ConvertError(Exception):
58 """Exception class for the conversion process"""
59
60
61 def slugify(s):
62 """Return a slug from the string s.
63
64 This code must match what Blogofile was doing in order to keep the URLs the
65 same. In this case I had customized Blogfile's functionality based on a tip
66 by Mike Bayer: http://techspot.zzzeek.org/2010/12/06/my-blogofile-hacks/
67
68 """
69 slug = s.lower()
70
71 # convert ellipses to spaces
72 slug = re.sub(r'\.{2,}', ' ', slug)
73
74 # flatten everything non alpha or . into a single -
75 slug = re.sub(r'[^0-9a-zA-Z\.]+', '-', slug)
76
77 # trim off leading/trailing -
78 slug = re.sub(r'^-+|-+$', '', slug)
79 return slug
80
81
82 def convert(src, dst):
83 """Convert Blogofile to Pelican."""
84 print '{} -> {}'.format(src, dst)
85 meta, content = parse_input(src)
86 write_output(meta, content, dst)
87
88
89 def parse_input(src):
90 """Parse input Blogofile .rst input.
91
92 Returns a 2-tuple:
93 meta - dictionary of Blogofile metadata
94 content - blog post body as a string
95
96 """
97 with open(src, 'r') as fp:
98 lines = fp.readlines()
99
100 # Find meta block
101 for i, line in enumerate(lines):
102 if line == '---\n':
103 meta_start = i
104 break
105 else:
106 raise ConvertError("Can't find start of meta block")
107
108 for i, line in enumerate(lines[meta_start + 1 :]):
109 if line == '---\n':
110 meta_end = meta_start + 1 + i
111 break
112 else:
113 raise ConvertError("Can't find end of meta block")
114
115 meta_lines = lines[meta_start + 1 : meta_end]
116 meta = {}
117 for line in meta_lines:
118 m = TITLE_RE.match(line)
119 if m:
120 meta['title'] = m.group('title').strip()
121 continue
122 m = DATE_RE.match(line)
123 if m:
124 year = int(m.group('year'))
125 month = int(m.group('month'))
126 day = int(m.group('day'))
127 t = time.strptime(m.group('time'), '%H:%M:%S')
128 meta['date'] = datetime.datetime.combine(
129 datetime.date(year, month, day),
130 datetime.time(t.tm_hour, t.tm_min, t.tm_sec))
131 continue
132 m = CAT_RE.match(line)
133 if m:
134 meta['categories'] = m.group('cats').replace(' ', '').split(',')
135 continue
136
137 for k in ['title', 'date', 'categories']:
138 if k not in meta:
139 raise ConvertError("Missing {} in metadata".format(k))
140
141 content = ''.join(lines[meta_end + 1:]).strip()
142 return meta, content
143
144
145 def write_output(meta, content, dst):
146 """Create the Pelican style .rst file from the Blogofile metadata and
147 content. Output is written to the file specified by dst.
148
149 """
150 title = meta['title']
151 date = meta['date'].strftime('%Y-%m-%d %H:%M')
152 tags = ', '.join(meta['categories'])
153 slug = slugify(title)
154
155 post = PELICAN_FMT.format(title=title,
156 title_underline='#'*len(title),
157 date=date,
158 tags=tags,
159 slug=slug,
160 content=content)
161
162 with open(dst, 'w') as fp:
163 fp.write(post)
164
165
166 if __name__ == '__main__':
167 for name in os.listdir(SRC_DIR):
168 if name.endswith('.rst'):
169 src = os.path.join(SRC_DIR, name)
170 dst = os.path.join(DST_DIR, name)
171
172 try:
173 convert(src, dst)
174 except ConvertError as ex:
175 print "Error converting {}: {}".format(name, ex)