File: href.py
   1 #!/usr/bin/python3
   2 
   3 # The MIT License (MIT)
   4 #
   5 # Copyright © 2020-2025 pacman64
   6 #
   7 # Permission is hereby granted, free of charge, to any person obtaining a copy
   8 # of this software and associated documentation files (the “Software”), to deal
   9 # in the Software without restriction, including without limitation the rights
  10 # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
  11 # copies of the Software, and to permit persons to whom the Software is
  12 # furnished to do so, subject to the following conditions:
  13 #
  14 # The above copyright notice and this permission notice shall be included in
  15 # all copies or substantial portions of the Software.
  16 #
  17 # THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  18 # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  19 # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
  20 # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  21 # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
  22 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  23 # SOFTWARE.
  24 
  25 
  26 from re import compile, IGNORECASE, Pattern
  27 from sys import argv, exit, stderr, stdin, stdout
  28 
  29 
  30 info = '''
  31 href [options...] [filepaths/URIs...]
  32 
  33 This script finds all (hyper)links inside `href` attributes in the input(s)
  34 given, showing each match on its own output line. It can match multiple links
  35 on each input line.
  36 '''
  37 
  38 # no args or a leading help-option arg means show the help message and quit
  39 if len(argv) > 1 and argv[1] in ('-h', '--h', '-help', '--help'):
  40     print(info.strip())
  41     exit(0)
  42 
  43 
  44 def seems_url(s: str) -> bool:
  45     protocols = ('https://', 'http://', 'file://', 'ftp://', 'data:')
  46     return any(s.startswith(p) for p in protocols)
  47 
  48 
  49 def handle_lines(w, src, links: Pattern) -> None:
  50     extra = len('href="')
  51     for line in src:
  52         for match in links.finditer(line):
  53             start = match.start() + extra
  54             end = match.end() - 1
  55             w.write(line[start:end])
  56             w.write('\n')
  57             w.flush()
  58 
  59 
  60 if any(seems_url(e) for e in argv):
  61     from io import TextIOWrapper
  62     from urllib.request import urlopen
  63 
  64 links = compile(
  65     'href="[^"]+"',
  66     flags=IGNORECASE,
  67 )
  68 
  69 try:
  70     if argv.count('-') > 1:
  71         msg = 'reading from `-` (standard input) more than once not allowed'
  72         raise ValueError(msg)
  73 
  74     # handle all named inputs given
  75     for path in argv[1:]:
  76         if path == '-':
  77             handle_lines(stdout, stdin, links)
  78             continue
  79 
  80         if seems_url(path):
  81             with urlopen(path) as inp:
  82                 with TextIOWrapper(inp, encoding='utf-8') as txt:
  83                     handle_lines(stdout, txt, links)
  84             continue
  85 
  86         with open(path, encoding='utf-8') as inp:
  87             handle_lines(stdout, inp, links)
  88 
  89     if len(argv) == 1:
  90         handle_lines(stdout, stdin, links)
  91 except BrokenPipeError:
  92     # quit quietly, instead of showing a confusing error message
  93     stderr.close()
  94     exit(0)
  95 except KeyboardInterrupt:
  96     stderr.close()
  97     exit(2)
  98 except Exception as e:
  99     print(f'\x1b[31m{e}\x1b[0m', file=stderr)
 100     exit(1)