Created
July 4, 2017 12:57
-
-
Save vihari/554df24072a605bec059b57bf58814ec to your computer and use it in GitHub Desktop.
A PERL script to grep CommonCrwal dataset on Amazon's S3 storage. Configure your AWS account (http://tech.marksblogg.com/petabytes-of-website-data-spark-emr.html) before using the script.
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
#!/usr/bin/perl -w | |
# set the query | |
$query = "www.google.com\\\/maps\\\/embed"; | |
# path to CommonCrawl dataset | |
$S3_URL = "s3://commoncrawl/crawl-data/CC-MAIN-2017-26/segments/"; | |
$all = `aws s3 ls $S3_URL|perl -ane 'print "\$F[1]\n"'`; | |
print "Launching search for: $query...\n"; | |
@segs = split(/[\n\s]+/, $all); | |
$nf=0; | |
for ($i=0;$i<=$#segs;$i++){ | |
$all = "aws s3 ls $S3_URL"."$segs[$i]"."warc/"; | |
$all = `$all|perl -ane 'print "\$F[3]\n"'`; | |
@seg_files = split(/[\n\s]+/, $all); | |
$total = ($#segs+1)*($#seg_files+1); | |
for ($j=0;$j<=$#seg_files;$j++){ | |
$f = "$S3_URL/$segs[$i]/warc/$seg_files[$i]"; | |
# print "searching $f...\n"; | |
$cmd = "aws s3 cp $S3_URL".$segs[$i]."warc/$seg_files[$i] -|zcat| perl -ane 'BEGIN{\$prev=0;\$pr_end=0;\$cur=0;\$prev_loc=0} \$cur+=length();if(/$query/i){print \"Doc: $f -- [\$prev-]\$_\"; \$pr_end=1;}if(/^Content-Location:/){\$prev_loc=\$_;} if(/^WARC\\\/1\.0/){\$prev=\$cur; if(\$pr_end>0){print \"Location: \$prev_loc End: \$cur\n\"; \$pr_end=0}}'"; | |
print "$cmd\n"; | |
print `$cmd`; | |
if ($nf%100 == 0){ | |
print STDOUT "Progress ~ $nf\/$total\n"; | |
} | |
$nf += 1; | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment