FlickrGrab

SGML
 
Flickr := Object clone do(
	PhotoCount := 0
 
	run := method(username, pagecount, directory,
		for (run, 1, pagecount, self grab(username, run, directory))
		writeln(self PhotoCount .. " photos successfully downloaded")
	)
 
	getPhotoId := method(src,
		id := src split("_") at(0) split("/")
		return id at(id size-1)
	)
 
	grab := method(username, pagenumber, destDirectory,
		userpageHtml := URL with("http://flickr.com/photos/" .. username .. "/page" .. pagenumber .. "/") fetch asHTML
		ImageLinks := userpageHtml elementsWithNameAndClass("img", "pc_img") map(attributes at("src"))
		ImageLinks foreach(ImageSrc,
			photoID := self getPhotoId(ImageSrc)
			photoSingleEntryHtml := URL with("http://flickr.com/photos/" .. username .. "/" .. photoID .. "/sizes/o/") fetch asHTML
			SingleEntryImageLinks := photoSingleEntryHtml elementsWithName("img") map(attributes at("src"))
			SingleEntryImageLinks foreach(ImageSrc, 
				if ((ImageSrc split(photoID) size)==2, 
					write("grabbing " .. ImageSrc .. "...")
					photoExt := ImageSrc split(".")
					photoExt := "." .. photoExt at(photoExt size -1)
					File with(destDirectory .. "/" .. photoID .. photoExt) setContents(URL with(ImageSrc) fetch)
					write("done.\n")
					self PhotoCount = self PhotoCount + 1
				)
			)
		)
	)
) run("schipplock", 118, "./photos")

#!/usr/bin/perl -w
use strict;
 
my $document = `wget -q -O /tmp/doc "http://flickr.com/photos/schipplock/" && cat /tmp/doc && rm /tmp/doc`;
my @lines = split(/\n/, $document);
my @page_numbers = 0;
my $max_page = 0;
 
for (my $run=0;$run<(@lines);$run++) {
	my @page_split = split(/\/page/, $lines[$run]) if (index($lines[$run], "/page")!=-1);
	my @number_split = split(/\//, $page_split[1]) if (index($lines[$run], "/page")!=-1);
	push @page_numbers, $number_split[0] if (index($lines[$run], "/page")!=-1);
}
 
for (my $run=0;$run<(@page_numbers);$run++) {
	if ($page_numbers[$run] > $max_page) {
		$max_page = $page_numbers[$run];
	}
}
 
print "max pages: $max_page\n";
 
for (my $run=1;$run<=$max_page;$run++) {
	print "Page $run: ";
	my $page = `wget -q -O /tmp/doc "http://www.flickr.com/photos/schipplock/page$run/" && cat /tmp/doc && rm /tmp/doc`;
	my @lines = split(/\n/, $page);
	for (my $irun=0;$irun<(@lines);$irun++) {
		if (index($lines[$irun], "class=\"photo_container pc_m\"")!=-1) {
			my @f_split = split(/\/photos\/schipplock\//, $lines[$irun]);
			my @s_split = split(/\/"/, $f_split[1]);
			my $photo_id = $s_split[0];
			my $photo_page = `wget -q -O /tmp/doc "http://www.flickr.com/photos/schipplock/$photo_id/sizes/o/" && cat /tmp/doc && rm /tmp/doc`;
			my @p_split = split(/\n/, $photo_page);
			for (my $iirun=0;$iirun<(@p_split);$iirun++) {
				if (index($p_split[$iirun], "Download this version")!=-1) {
					my @url_split = split(/href="/, $p_split[$iirun+1]);
					my @value_split = split(/">/, $url_split[1]);
					my $url = $value_split[0];
					my @filename_split = split(/\//, $value_split[0]);
					my $filename = $filename_split[(@filename_split)-1];
					print "url: $url\n";
					print "filename: $filename\n";
					qx|wget -q -O /mnt/photos/flickr/$filename "$url"|;
					print "*";
				}
			}
		}
	}
	print "\n";
}