#!/usr/bin/perl

use WWW::Mechanize;

#!/usr/bin/perl -w

use strict;
use Win32::OLE qw(in with);
use Win32::OLE::Const 'Microsoft Excel';

$Win32::OLE::Warn = 3;                                # die on errors.
+..

# get already active Excel application or open new
my $Excel = Win32::OLE->GetActiveObject('Excel.Application')
    || Win32::OLE->new('Excel.Application', 'Quit');  

# open Excel file
my $Book = $Excel->Workbooks->Open("C:/Documents and Settings/rto5u/My
+ Documents/CV.xls"); 

# select worksheet number 1 (you can also select a worksheet by name)
my $Sheet = $Book->Worksheets(1);

foreach my $row (2..4)
{
 foreach my $col (1..1)
 {
  # skip empty cells
  next unless defined $Sheet->Cells($row,$col)->{'Value'};


        my $URL = 'http://scholar.google.com/advanced_scholar_search';
        my $FORM_NAME = 'f';
        #print "Author Name: ";
        #chomp ($AUTHOR = <>);
        my $AUTHOR = "MD Li";
        #print "Paper Title: ";
        #chomp ($TITLE = <>);
        my $TITLE = $Sheet->Cells($row,$col)->{'Value'};
        print "$TITLE";
        #my $TITLE = "Region-specific transcriptional response to chro
+nic nicotine in rat brain";

        my $mech = WWW::Mechanize->new(stack_depth=>10);

        $mech->get($URL) || die ("Could not connect to $URL.\n");

        my $res = $mech->submit_form(
            form_name => $FORM_NAME,
            fields => {
                'num' => 100,
                'as_epq' => $TITLE,
                'as_occt' => 'title',
                'as_sauthors' => $AUTHOR,
                'as_allsubj' => 'all',
            },
        );

        while ($res && $res->is_success()){
            my $content = $res->content;
            #print $content;
            while ($content =~ /<p class=g>(.*?)<\/font>\s\s\s/gs){
                my $section = $1;
            
                my $title    = "";
                my $citedby    = 0;

                # get title
                $title = getTitle($section);
                $title =~ s/<.*?>//g;
                $title =~ s/&hellip;/\.\.\./g;
    
                # get citedby #
                $citedby = getCitedBy($section);
        
                if ($citedby){
                    print "\"$title\"\nCited by: $citedby\n\n";
                }
            }
            $res = $mech->follow_link( text_regex => qr/Next/i);
        }
    }
}

$Book->Close;
######################################################################
+#######

sub getTitle($){
    my ($section) = @_;
    my $title;

    if ($section =~ /<span class="w">.*?<a href.*?>(.*?)<\/a><\/span>/
+s){     # papers with a link
        $title = $1;
        
    }elsif ($section =~ /&nbsp;(.*?)<font size=-1>/s){            # pa
+pers w/o a link
        $title = $1;
    }else{
        $title = $1;
    }
    return $title;
}

#---------------------------------------------------------------------
+-------
sub getCitedBy($){
    my ($section) = @_;
    my $citedby;

    if ($section =~ />Cited by (\d+)</s){
        $citedby = $1;
    }
    return $citedby;
}

#---------------------------------------------------------------------
+-------

[download]

The two programs work separately. I tried to put the fetch.pl program within the for loop that goes through the paper titles in the excel spreadsheet...I tried trouble shooting the best I could, but the problem consistently turns about to be, "Can't call method "url" on an undefined value at C:/strawberry/perl/site/lib/WWW/Mechanize.pm line 707"
Again I apologize for my lack of familiarity with the customs of this forum. I'm not necessarily new to programming, but I am extremely new to Perl syntax

In reply to Re^4: Combining Excel Parser with Google Scholar Scraper by ochez
in thread Combining Excel Parser with Google Scholar Scraper by ochez

Title:
Use:  <p> text here (a paragraph) </p>
and:  <code> code here </code>
to format your post, it's "PerlMonks-approved HTML":


  • Posts are HTML formatted. Put <p> </p> tags around your paragraphs. Put <code> </code> tags around your code and data!
  • Titles consisting of a single word are discouraged, and in most cases are disallowed outright.
  • Read Where should I post X? if you're not absolutely sure you're posting in the right place.
  • Please read these before you post! —
  • Posts may use any of the Perl Monks Approved HTML tags:
    a, abbr, b, big, blockquote, br, caption, center, col, colgroup, dd, del, details, div, dl, dt, em, font, h1, h2, h3, h4, h5, h6, hr, i, ins, li, ol, p, pre, readmore, small, span, spoiler, strike, strong, sub, summary, sup, table, tbody, td, tfoot, th, thead, tr, tt, u, ul, wbr
  • You may need to use entities for some characters, as follows. (Exception: Within code tags, you can put the characters literally.)
            For:     Use:
    & &amp;
    < &lt;
    > &gt;
    [ &#91;
    ] &#93;
  • Link using PerlMonks shortcuts! What shortcuts can I use for linking?
  • See Writeup Formatting Tips and other pages linked from there for more info.