Last active
August 29, 2015 14:27
-
-
Save laszlo91/c0adc4f0c1fb5bc4912a to your computer and use it in GitHub Desktop.
Make a two columns spreadsheet (user and text, comma separated) from a single line html of your facebook conversation. User: guy you chat with. Text: what you write to him.
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
# by phil Bonora for nlpspoiler.it | |
use strict; | |
use warnings; | |
use utf8; | |
my @t; | |
my $name="PUT YOUR NAME HERE"; #STDIN html (all in one line) | |
print "user,text\n2"; | |
while (my $ligne = <STDIN>) { | |
chomp $ligne; | |
while ($ligne =~ /<.[^<>]*>(.[^<>]*)<.[^<>]*>/g ) { | |
if ($1 !~/[MTWFS]\w+day,\s\d+\s.*$/){ | |
push (@t, $1); | |
} | |
} | |
} | |
my $loc; | |
my $txt; | |
for (my $i=0; $i<=$#t; $i++){ | |
if ($t[$i]=~/$name,\s(.[^,]*)$/ or $t[$i]=~/(.[^,]*),\s$name$/ ){ | |
print "\n"; | |
$loc=$1; | |
print "$loc,"; | |
} | |
elsif ($t[$i]=~/$name$/){ | |
print "$t[$i+1] | "; | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment