mirror of
https://github.com/freedombox/FreedomBox.git
synced 2026-02-04 08:13:38 +00:00
4064d6e231
Closes #930 - Make targets to download wiki pages of each service - Add post-processor script for DocBook file processing Signed-off-by: Joseph Nuthalapati <njoseph@thoughtworks.com> Reviewed-by: James Valleroy <jvalleroy@mailbox.org>
66 lines
2.2 KiB
Python
Executable File
66 lines
2.2 KiB
Python
Executable File
#!/usr/bin/python3
|
|
#
|
|
# This file is part of FreedomBox.
|
|
#
|
|
# 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 <http://www.gnu.org/licenses/>.
|
|
#
|
|
|
|
import re
|
|
import urllib.request
|
|
from subprocess import PIPE, Popen
|
|
|
|
MANUAL_PAGE_URL = "https://wiki.debian.org/FreedomBox/Manual/{}?action=show&mimetype=text%2Fdocbook"
|
|
|
|
MANUAL_INDEX_RAW_URL = "https://wiki.debian.org/FreedomBox/Manual?action=raw"
|
|
|
|
manual_pages = []
|
|
|
|
to_remove = ['QuickStart', 'GettingHelp', 'Developer']
|
|
|
|
|
|
def write_manual_pages():
|
|
pattern = 'FreedomBox/Manual/\w+'
|
|
lst = list(urllib.request.urlopen(MANUAL_INDEX_RAW_URL))
|
|
global manual_pages
|
|
manual_pages = list(l[0].split('/')[-1] for l in filter(
|
|
None, map(lambda x: re.findall(pattern, x.decode()), lst)))
|
|
for entry in to_remove:
|
|
if entry in manual_pages:
|
|
manual_pages.remove(entry)
|
|
with open('manual-pages.list', 'w') as lst_file:
|
|
lst_file.write('\n'.join(manual_pages))
|
|
|
|
|
|
def fetch_manual_pages_in_docbook_format():
|
|
for page in manual_pages:
|
|
url = MANUAL_PAGE_URL.format(page)
|
|
p1 = Popen(['wget', '--quiet', '-O', '-', url], stdout=PIPE)
|
|
p2 = Popen(['xmllint', '--format', '-'], stdin=p1.stdout, stdout=PIPE)
|
|
p1.stdout.close()
|
|
with open('{}.raw.xml'.format(page), 'w') as docbook:
|
|
p3 = Popen(
|
|
['egrep', '-v', 'linkend|Category|Commons|HELP|Back to'],
|
|
stdin=p2.stdout, stdout=docbook)
|
|
p2.stdout.close()
|
|
p3.communicate()
|
|
|
|
|
|
def main():
|
|
write_manual_pages()
|
|
fetch_manual_pages_in_docbook_format()
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main()
|