Recently, I’ve been helping a friend migrate is web “store” from a collection of static html pages (2000+) to magento. The old store worked but wasn’t really functional. Everything was hardcoded and there was no shopping cart. After doing some research, I decided to give magento a try. This meant, we had to migrate the existing static html pages, both “product” pages and “expository” pages.
I started by writing a perl script to parse the pages and pull out the relevant product data. The original pages were done in one of the WYSIWYG editors, so there was a somewhat standard format. I used the perl IdentityParse package (HTML::Parser) to parse and, where necessary, preserve the original html files. I was able to pull out ~750 products, with their attributes (e.g. price, description, sku, etc) and in some places, the images associated with the product.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 | #!/usr/bin/perl -w use strict; no warnings "all"; package IdentityParse; use base "HTML::Parser"; my $plainContent; my $description; my $format=""; my $price=""; my $itemNum=""; my $length=""; my $author=""; my $allLines = ""; my $inMainTable = 0; my $inSecondaryTable=0; my $inHeader=0; my $inUL=0; my $navTrailText = ""; my %categoryHierarcy; sub trim($) { my $string = shift; $string =~ s/^\s+//; $string =~ s/\s+$//; return $string; } sub text { my ($self, $text) = @_; # just print out the original text $text =~ s/\s{2,}/ /g; $text =~ tr/"/""/; $plainContent.= $text; } sub start { my ($self, $tag, $attr, $attrseq, $origtext) = @_; if ($tag =~ m/^table$/i && $attr->{'width'} =~ m/^583$/i) { $inMainTable=1; } elsif ($tag =~ m/^table$/i){ $inSecondaryTable=1; $plainContent.=$origtext; } elsif ($tag =~ m/^tr$/i && $inMainTable) { if ($inSecondaryTable){ $plainContent.=$origtext; } } elsif ($tag =~ m/^td$/i && $inMainTable) { if ($inSecondaryTable){ $plainContent.=$origtext; } } elsif ($tag =~m/^h1$/i && $attr->{'class'} =~ m/^hdrPage$/i){ $inHeader = 1; $plainContent.= "<div class=\"page-head\"><h3>"; } elsif ($tag =~m/^p$/i && $attr->{'class'} =~ m/^hdrPage$/i){ $inHeader = 1; $plainContent.= "<div class=\"page-head\"><h3>"; } elsif ($tag=~m/^img$/i && $attr->{'src'} =~ m/spacer\.gif$/){ } elsif ($tag=~m/^img$/i){ my $imagePath = $attr->{'src'}; my @imagePathParts = split(/\//,$imagePath); my $partsLen = @imagePathParts; my $filename = $imagePathParts[$partsLen-1]; $plainContent.="<img src=\"/skin/frontend/4ulr/blue/images/$filename\" align=\"right\">"; } elsif ($tag=~/^ul$/i) { $inUL=1; $plainContent.="<ul class=\"disc\">"; } else{ $plainContent.=$origtext; } } sub end { my ($self, $tag, $attr, $attrseq, $origtext) = @_; if ($tag =~ m/^table$/i && $inMainTable) { if ($inSecondaryTable){ $inSecondaryTable=0; $plainContent.=$attr; } else { $inMainTable=0; } } elsif ($tag =~ m/^tr$/i && $inMainTable) { if($inSecondaryTable){ $plainContent.=$attr; } } elsif ($tag =~ m/^td$/i && $inMainTable) { if($inSecondaryTable){ $plainContent.=$attr; } } elsif($tag =~m/^h1$/i && $inHeader){ $inHeader=0; $plainContent.="</h3></div><div class=\"content\">"; } elsif($tag =~m/^p$/i && $inHeader){ $inHeader=0; $plainContent.="</h3></div><div class=\"content\">"; } elsif ($tag=~/^ul$/i && $inUL==1) { $plainContent.=$attr; } else{ $plainContent.=$attr; } } package main; my $p = new IdentityParse; my $categories={}; my @files = get_htmls("/home/juice/4ulr/parsing/products/counseling/"); open(OUTPUT, ">counselinglistHTML.csv"); print OUTPUT "filename\tbodyContent\n"; foreach my $file (@files){ print "$file\n"; $plainContent=""; $description=""; $allLines=""; $format=""; $price=""; $itemNum=""; $length=""; $author=""; open(MYINPUTFILE, "<$file"); # open for input my(@lines) = <MYINPUTFILE>; # read file into list my $title=""; my $content=""; my $contentStart=0; my @contentLines; chomp(@lines); foreach my $line (@lines){ chomp($line); $line=~ s/\r//g; $allLines .= $line; if ($line =~ m/<title>(.*)<\/title>/i){ $title = $1; $title =~ tr/"/""/; $title = trim($title); } if ($line =~ m/<!---------- tbl main content ---------->/i){ $contentStart = 1; } if ($contentStart){ push(@contentLines, $line); } if ($line =~ m/<!-------- \/ tbl main content ---------->/i){ $contentStart = 0; } } print "\n"; foreach my $contentLine (@contentLines){ $content.=$contentLine; } #parse to get content $plainContent=""; $p->parse($content); my $vanillaContent = $plainContent; $vanillaContent=~s/\s{2,}/ /g; $vanillaContent.="</div>"; #print $plainContent; print "title = $title\n"; # print "description = $plainDescription\n"; # print "bodyContent = $vanillaContent\n"; # print "format = $format\n"; # print "price = $price\n"; # print "itemNum = $itemNum\n"; # print "length = $length\n"; # print "author = $author\n"; $p->eof; $navTrailText=""; print OUTPUT "$file\t$vanillaContent\n"; close MYINPUTFILE; } sub trim($) { my $string = shift; $string =~ s/^\s+//; $string =~ s/\s+$//; return $string; } sub get_htmls { my $path = shift; opendir (DIR, $path) or die "Unable to open $path: $!"; my @files = map { $path . '/' . $_ } grep { !/^\.{1,2}$/ } readdir (DIR); # Rather than using a for() loop, we can just # return a directly filtered list. return grep { (/\.html*$/) && (! -l $_) } map { -d $_ ? get_htmls ($_) : $_ } @files; } |
I then started using Magento’s web service to load the data. Unfortunatley it was slow and I couldn’t get some of the custom attributes to load. I found some relevant posts in the magento forums, and switched over to php script using the magento classes to load the data.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 | #!/usr/bin/php <?php define('MAGENTO', realpath('/var/www/magento')); ini_set('memory_limit', '128M'); require_once MAGENTO . '/app/Mage.php'; Mage::app(); //$ourFileName = "listshort.csv" $ourFileName = "Catalog_short.csv"; $fh = fopen($ourFileName, 'r') or die("Can't open file"); while (!feof($fh)) { /* $theData = fgets($fh); $theData = ereg_replace('"',"",$theData); echo($theData); list($filename,$title,$imageName, $keywords, $description,$bodyContent,$format,$price,$itemNum,$length,$author, $catHier) = split("\t", $theData); preg_match('@/home/juice/4ulr/parsing/products(\/.*)\.htm[l]?@', $filename, $matches); $urlKey = $matches[1];*/ list($title,$description, $bodyContent, $format, $length,$author,$itemNum, $price,$rental,$keywords,$drop) = fgetcsv($fh); $price = ereg_replace("[^0-9.]","",$price); $imageSet=false; /* if (strlen($imageName)){ $imageName = "/var/www/magento/media/catalog/product" . $imageName; $imageSet = true; }*/ if (strlen($itemNum) > 0 && strlen($price) > 0){ // echo "$imageName\n"; $product = Mage::getModel('catalog/product'); $product->setTypeId('simple'); $product->setTaxClassId(0); //none $product->setWebsiteIds(array(1)); // store id $product->setAttributeSetId(4); // $product->setMediaFormat(6); // $product->setMetaCategory(array(3,4)); $product->setSku(ereg_replace("\n","",$itemNum)); $product->setName(ereg_replace("\n","",$title)); $product->setDescription($bodyContent); $product->setInDepth($bodyContent); $product->setPrice($price); $product->setShortDescription(ereg_replace("\n","",$description)); $product->setWeight(0); $product->setStatus(1); $product->setVisibilty(4); $product->setMetaDescription(ereg_replace("\n","",$description)); $product->setMetaTitle(ereg_replace("\n","",$title)); $product->setMetaKeywords($keywords); // $product->setUrlKey($urlKey); $visibility = array ( 'thumbnail', 'small_image', 'image' ); if ($imageSet){ try { $product->addImageToMediaGallery($imageName,$visibility,false, false); } catch (Exception $e) {echo "no image\n";} } try{ $product->save(); echo "$price, $itemNum added\n"; } catch (Exception $e){ echo "$price, $itemNum not added\n"; } $stockItem = Mage::getModel('cataloginventory/stock_item'); $stockItem->loadByProduct($product->getId()); //var_dump($stockItem); if (!$stockItem->getId()) { $stockItem->setProductId($product->getId())->setStockId(1); } $stockItem->setData('qty', 0); $stockItem->setData('is_in_stock', 1); $stockItem->save(); } else { echo "$price, $itemNum not added\n"; } } ?> |
I then went back and began parsing the “expository” pages in the site. Again using the magento classes I was able to create “CMS pages”. Now I just need to change all the links so that they work 8).
0 Responses
Stay in touch with the conversation, subscribe to the RSS feed for comments on this post.