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
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
|
#!/usr/bin/env python3
# encoding: utf-8
#
# Copyright (C) 2020-2024 Denis 'GNUtoo' Carikli <GNUtoo@cyberdimension.org>
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <https://www.gnu.org/licenses/>.
from bs4 import BeautifulSoup
from html2text import config, HTML2Text
import os
import re
import sh
import sys
def usage(progname):
print("{} path/to/file.html".format(progname))
sys.exit(1)
# A "[1]" in the html becomes "[[1]][6]" in text.
# As we already uses references at the end a [6] would
# be enough.
def fix_wordpress_references_link(string):
open_square_bracket = re.escape('[')
close_square_bracket = re.escape(']')
whitespaces = '\s*'
numbers = '\d+'
# [ [ 1 ] ] [ 6 ]
wordpress_link_regex = \
\
open_square_bracket + whitespaces \
+ open_square_bracket + whitespaces \
+ numbers + whitespaces \
+ close_square_bracket + whitespaces \
+ close_square_bracket + whitespaces \
\
+ open_square_bracket + whitespaces \
+ numbers + whitespaces \
+ close_square_bracket + whitespaces \
results = re.findall(wordpress_link_regex, string)
part_to_remove = '^' \
+ open_square_bracket + whitespaces \
+ open_square_bracket + whitespaces \
+ numbers + whitespaces \
+ close_square_bracket + whitespaces \
+ close_square_bracket + whitespaces \
for result in results:
replacement = re.sub(part_to_remove, '', result)
string = string.replace(result, replacement)
return string
def fix_alignment(string):
new_string = ""
for line in string.split(os.linesep):
new_line = re.sub('^ ', '', line)
new_string += (new_line + os.linesep)
return new_string
# Emacs breaks lists when doing a fill-paragraph to adjust a paragraph to the
# maximum width so we make sure that there is at least one blank line before
# the '*'
def fix_lists(string):
new_string = ''
nr_lineseps_before_star = 0
for c in string:
if c == '*' and nr_lineseps_before_star == 1:
new_string += os.linesep
if c == os.linesep:
nr_lineseps_before_star += 1
else:
nr_lineseps_before_star = 0
new_string += c
return new_string
def convert(html_file_path):
with open(html_file_path) as html_file:
soup = BeautifulSoup(html_file, features="html5lib").article
# Format the output to be compatible with mail conventions but make sure
# that the links are not split between two lines
config.INLINE_LINKS = False
config.PROTECT_LINKS = True
config.WRAP_LIST_ITEMS = True
config.BODY_WIDTH = 70
parser = HTML2Text()
article = soup.find('div', class_='entry-content')
text = parser.handle(article.decode())
text = fix_wordpress_references_link(text)
text = fix_alignment(text)
text = fix_lists(text)
return text
def _get_metadata(html_file_path, func):
with open(html_file_path) as html_file:
soup = BeautifulSoup(html_file, features="html5lib")
return func(soup)
def get_metadata(html_file_path):
metadata = ""
def get_date(soup):
date_metadata = None
entries = soup.article.find_all('a')
for entry in entries:
date_elements = entry.find_all('time', class_='entry-date')
for date_element in date_elements:
if date_element.get('datetime', None):
new_date = date_element['datetime']
assert(date_metadata == None or date_metadata == new_date)
date_metadata = new_date
return date_metadata
def get_tags(soup):
results = []
tags = soup.article.find_all('footer', class_='entry-meta')
assert(len(tags) == 1)
links = tags[0].find_all('a')
for link in links:
text = link.string
if text != 'permalink':
results.append(text)
return ', '.join(results)
def get_title(soup):
title = soup.title.string
title = title.replace(os.linesep, '')
title = title.replace('\t', '')
title = re.sub('\|.*', '', title)
title = title.lstrip().rstrip()
return title
date_metadata = _get_metadata(html_file_path, get_date)
assert(date_metadata != None)
metadata += "date: {}".format(date_metadata) + os.linesep
title_metadata = _get_metadata(html_file_path, get_title)
# assert(title_metadata != None)
metadata += "title: {}".format(title_metadata) + os.linesep
# assert(title_metadata != None)
# metadata += "title: {}".format(title_metadata)
tags_metadata = _get_metadata(html_file_path, get_tags)
if tags_metadata:
print("tags: {}".format(tags_metadata))
metadata += "---" + os.linesep
return metadata
def main():
if len(sys.argv) != 2:
usage(sys.argv[0])
html_file_path = sys.argv[1]
text = get_metadata(html_file_path)
text += convert(html_file_path)
sys.stdout.write(text)
if __name__ == '__main__':
main()
|
