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
|
#!/usr/bin/env python3
# encoding: utf-8
# Copyright (C) 2020 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 Affero 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 Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program. If not, see <https://www.gnu.org/licenses/>.
# How to use:
# - Download the release notes from Wordpress. If it's not published yet you
# can still click on preview and save-as the page
# - Point this program to the resulting html file, it will generate a text
# version of it.
from bs4 import BeautifulSoup
from html2text import config, HTML2Text
try:
# This has been removed in more recent
# versions of python-html2text. See commit
# b361467894fb277563b4547ec9d4df49f5e0c6e3
# (b361467 Remove support for Python ≤ 3.4)
# in https://github.com/Alir3z4/html2text.git
from html2text.utils import wrapwrite
except:
pass
import os
import re
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 convert(html_file_path):
with open(html_file_path) as html_file:
try:
soup = BeautifulSoup(html_file, features="html5lib").article
except:
try:
# For some reason the lxml parser isn't found with
# python-beautifulsoup4 4.9.3-3.0 on Parabola. It's
# probably better to use an html5 parser anyway as the
# Replicant blog (now?) uses the html doctype and the
# theme seems to include an html5.js file for the IE 9
# browser.
soup = BeautifulSoup(html_file, features="lxml").article
except:
print("Cannot find html5lib or lxml parsers")
sys.exit(1)
# 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)
return text
def main():
if len(sys.argv) != 2:
usage(sys.argv[0])
html_file_path = sys.argv[1]
text = convert(html_file_path)
try:
wrapwrite(text)
except:
sys.stdout.write(text)
if __name__ == '__main__':
main()
|
