#!/usr/bin/python3

# The MIT License (MIT)
#
# Copyright © 2020-2025 pacman64
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the “Software”), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.


from re import compile, IGNORECASE, Pattern
from sys import argv, exit, stderr, stdin, stdout


info = '''
links [options...] [filepaths/URIs...]

This script finds all web (hyper)links in the input(s) given, specifically
HTTP/HTTPS links, showing each match on its own output line. It can match
multiple links on each input line.
'''

# no args or a leading help-option arg means show the help message and quit
if len(argv) > 1 and argv[1] in ('-h', '--h', '-help', '--help'):
    print(info.strip())
    exit(0)


def seems_url(s: str) -> bool:
    protocols = ('https://', 'http://', 'file://', 'ftp://', 'data:')
    return any(s.startswith(p) for p in protocols)


def handle_lines(w, src, links: Pattern) -> None:
    for line in src:
        for match in links.finditer(line):
            w.write(line[match.start():match.end()])
            w.write('\n')
            w.flush()


if any(seems_url(e) for e in argv):
    from io import TextIOWrapper
    from urllib.request import urlopen

links = compile(
    'https?://[A-Za-z0-9+_.:%-]+(/[A-Za-z0-9+_.%/,#?&=-]*)*',
    flags=IGNORECASE,
)

try:
    if argv.count('-') > 1:
        msg = 'reading from `-` (standard input) more than once not allowed'
        raise ValueError(msg)

    # handle all named inputs given
    for path in argv[1:]:
        if path == '-':
            handle_lines(stdout, stdin, links)
            continue

        if seems_url(path):
            with urlopen(path) as inp:
                with TextIOWrapper(inp, encoding='utf-8') as txt:
                    handle_lines(stdout, txt, links)
            continue

        with open(path, encoding='utf-8') as inp:
            handle_lines(stdout, inp, links)

    if len(argv) == 1:
        handle_lines(stdout, stdin, links)
except BrokenPipeError:
    # quit quietly, instead of showing a confusing error message
    stderr.close()
    exit(0)
except KeyboardInterrupt:
    stderr.close()
    exit(2)
except Exception as e:
    print(f'\x1b[31m{e}\x1b[0m', file=stderr)
    exit(1)