aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorDaniel Stenberg <daniel@haxx.se>2005-12-06 13:56:56 +0000
committerDaniel Stenberg <daniel@haxx.se>2005-12-06 13:56:56 +0000
commit952bbc441047f023debf08275162dce866d04025 (patch)
tree5313dbd73b5eb25fcea399982dc0eb4dbb073bf9
parent1eb4b85d72c4bb4f56863b374bacf5b095308365 (diff)
my first collect-random-urls script, just for reference
-rwxr-xr-xhiper/collecturls.pl34
1 files changed, 34 insertions, 0 deletions
diff --git a/hiper/collecturls.pl b/hiper/collecturls.pl
new file mode 100755
index 000000000..6a0da3686
--- /dev/null
+++ b/hiper/collecturls.pl
@@ -0,0 +1,34 @@
+#!/usr/bin/perl
+
+# 1) http://randomurl.com/body.php
+# 2) http://random.yahoo.com/fast/ryl
+# 3) http://www.uroulette.com/visit
+
+# 1) very slow, responds with URL in body meta style:
+# <meta http-equiv="refresh" content="0; url=http://www.webmasterworld.com/forum85/735.htm">
+
+# 2) Responds with non-HTTP headers like:
+# Status: 301
+# Location: http://www.adaptive.net/
+
+# 3) ordinary 30X code and Location:
+
+my $url;
+map { $url .= " http://www.uroulette.com/visit"; } (1 .. 12);
+
+print $url."\n";
+
+my $count=0;
+
+open(DUMP, ">>dump");
+
+while(1) {
+ my @getit = `curl -si $url`;
+ for my $l (@getit) {
+ if($l =~ /^Location: (.*)/) {
+ print DUMP "$1\n";
+ print STDERR "$count\r";
+ $count++;
+ }
+ }
+}