blob: c605b39123eb9a3fda05981ccf48ce88ed5beda7 (
plain)
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
|
#!/usr/bin/env python3
# encoding: utf-8
#
# Copyright (C) 2020-2023 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 sys
def usage(progname):
print("Usage: {} path/to/file.html".format(progname))
sys.exit(1)
def get_article_links(html_file_path):
with open(html_file_path) as html_file:
soup = BeautifulSoup(html_file, 'html.parser')
# print(soup.prettify())
entries = soup.find_all('article') # class_='entry-title')
for entry in entries:
titles = entry.find_all('h1', class_='entry-title')
for title in titles:
links = title.find_all('a')
for link in links:
print(link['href'])
return None
def main():
if len(sys.argv) != 2:
usage(sys.argv[0])
html_file_path = sys.argv[1]
text = get_article_links(html_file_path)
if __name__ == '__main__':
main()
|
