Created
April 9, 2012 00:44
-
-
Save hoehrmann/2340570 to your computer and use it in GitHub Desktop.
Download plain text versions of public domain books from EXAMPLE Books.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!perl -w | |
| use strict; | |
| use warnings; | |
| use LWP::UserAgent; | |
| use HTML::FormatText; | |
| die "Usage: $0 bookid > example.txt\n" unless @ARGV == 1; | |
| my $book = shift @ARGV; | |
| my %seen; | |
| my $next = "PP1"; | |
| my $ua = LWP::UserAgent->new; | |
| $ua->agent('Mozilla/5.0'); | |
| binmode STDOUT, ':utf8'; | |
| $|++; | |
| while (1) { | |
| last if $seen{ $next }++; | |
| my $uri = "http://books.EXAMPLE.com/books?id=${book}&pg=${next}&hl=en&output=text"; | |
| warn "Retrieving $next"; | |
| my $response = $ua->get($uri); | |
| my $content = $response->decoded_content; | |
| if ($content =~ /pg=([a-zA-Z0-9_-]+)[^"]*" accesskey="n"/) { | |
| $next = $1; | |
| } else { | |
| warn "found no next page!\n"; | |
| } | |
| $content =~ s/<body.*?<div id='flow-top-div' class='flow-top-div'>/<body><div>/s; | |
| $content =~ s(</div>\s*</div>\s*</div>\s*</div>\s*.*$)()s; | |
| my $fmt = HTML::FormatText->new; | |
| print $fmt->format_string($content); | |
| sleep 1; | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment