Created
November 21, 2011 03:50
-
-
Save kiyotakagoto/1381564 to your computer and use it in GitHub Desktop.
HTML::ExtractContentで本文抽出
This file contains hidden or 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
| sub url2text{ | |
| my $url = shift; | |
| my $ua = LWP::UserAgent->new; | |
| my $res = $ua->get( $url ); | |
| if( $res->is_error ){ | |
| print 'some error: ', $res->status_line; | |
| } | |
| my $html = $res->decoded_content; | |
| my $ex = HTML::ExtractContent->new; | |
| $ex->extract( $html ); | |
| return $ex->as_text; | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment