Real-time collaboration for Jupyter Notebooks, Linux Terminals, LaTeX, VS Code, R IDE, and more,
all in one place.

1
require 'anemone'
2
require 'optparse'
3
require 'ostruct'
4

5
options = OpenStruct.new
6
options.relative = false
7

8
begin
9
  # make sure that the last option is a URL we can crawl
10
  root = URI(ARGV.last)
11
rescue
12
  puts <<-INFO
13
Usage:
14
  anemone url-list [options] <url>
15
    
16
Synopsis:
17
  Crawls a site starting at the given URL, and outputs the URL of each page
18
  in the domain as they are encountered.
19

20
Options:
21
  -r, --relative      Output relative URLs (rather than absolute)
22
INFO
23
  exit(0)
24
end
25

26
# parse command-line options
27
opts = OptionParser.new
28
opts.on('-r', '--relative') { options.relative = true }
29
opts.parse!(ARGV)
30

31
Anemone.crawl(root, :discard_page_bodies => true) do |anemone|
32
  
33
  anemone.on_every_page do |page|
34
    if options.relative
35
      puts page.url.path
36
    else
37
      puts page.url
38
    end
39
  end
40
  
41
end
42

43