Welcome to the Q&A Forum

Hmm, interestingly, when I followed your link, I only saw the canonical version of the article. Is this what you're seeing now?

Also, in response to your earlier question, yes, you can disallow parameters with robots.txt. If these canonical issues continue, that may be the best next step.

Whoa, that shouldn't be working for them. Can you share some examples so I can look into this?

Hmm, that doesn't seem good. It's hard to say whether this is causing the decline in your rankings, but either way, you want to make sure that you're not splitting your link equity between your / and .shtml pages. Here's what I'd do:

1. If you can, 301 redirect / pages to .shtml pages. Obviously, it'd be easier if the canonical worked, but it sounds like it doesn't.
2. Use ScreamingFrog or DeepCrawl to look through internal pages on your site to see if you're ever linking to the / version of pages rather than the .shtml pages. When Google chooses a different version of a URL over the canonical one, it's often because that's how it sees internal links pointing to the page. Make sure that you only have links to the .shtml version of the page.
3. Use a tool like Moz or Ahrefs to find all internal links to your site. For any links that you built or have a partnership with the owners, make sure that they're linking to the .shtml version of the page. I could especially see your ad partners using / because it's a cleaner before parameters than .shtml.

After that, wait and see if Google fixes the problem.

Also worth noting: have you thought about changing your default to /? That's more common today, so you're probably getting a lot of external links with / instead of .shtml, and you'll never be able to fix that problem. If that's a possible solution, you may want to explore it.

Good luck!

Kristina

Agree with Oleg above; that's not a good solution if this lasts years, though.

Is there any chance you could serve the old site using the current URLs?

Google uses URLs as unique identifiers, which means that if you redirect to URLs that are only for the old site, it'll think you've created new pages. New pages mean a month or so of low rankings, before your page has a proven click through rate and gets some links.

If you use your current (and future) URLs to load the old site, though, Google won't see that as a site overhaul, it'll see it as content modifications on a pre-existing page.

Hope this helps! If 302s or using the same URL isn't an option, let us know so we can brainstorm more solutions with you.

Best,

Kristina

Not to toot my own horn, but I've written a whole blog post for this:

https://www.distilled.net/blog/seo/site-navigation-for-seo/

Give it a read and let me know if you have any questions!

Hey Srbello,

You should be fine, although if your domains are currently on different servers and are linking to each other, there's a chance that moving them to the same server will lower the value of those links.

This has been discussed more in depth here: https://moz.com/community/q/multiple-domains-on-1-ip-address

Now, as to your redirect question: do you want to merge all of these sites to one domain? Some of them? I'm not sure what your goal is, when you said you'd want to 301 redirect to the primary domain.

Best,

Kristina

Hey James,

There's a pretty thorough list of things you should look for here. Moz has also had a couple of good discussions on this here and here.

Highlights of what you might miss:

• Make sure to change all internal links, so they're not all 301 redirecting
• Make sure to change all self-referring canonicals, so they're not pointing to the HTTP version
• Make sure to update all XML sitemaps that Google has in GSC

I can tell you of stories where SEOs did everything right and they still saw a drop in traffic; I can also tell you that when we migrated our site to HTTPS, we didn't see a drop. You're taking a bit of a risk here, but as long as you do it properly, it's a 15% temporary drop in traffic, max. Then you should be fine.

Good luck!

Kristina

Typically, if you 301 redirect one URL to another URL with the exact same content, you're going to get little to no reduction in link juice. Google's more likely to reduce link equity passed if the new page seems different from the old one.

So: be pretty specific about how you set up those redirects!

Hey there,

Sorry for the silence!

Okay, a few things here:

1. Yeah, you're going to run into duplicate content issues, since you're using English on all sites.

• You only need www.website.com for the US. Don't create us.website.com.
• For the UK and EU domain, localize with different currency, standard shipping, and legal information. (What's your plan, since the UK and EU use different currencies, to have them on the same site section?)
• If you have any content that's universal, like a blog post, keep that part of the site on the www.website.com section and don't duplicate it on the UK / EU site (unless you translate it).

3. If at all possible, don't use subdomains for different countries. Subdomains split your domain value (which weakens your site) and also makes it clear that you're not a truly localized site, since you're using a .com instead of the right ccTLD for the country (not bad for SEO, but not great for click through rates). Better options are:

• Get the ccTLD for each country you're operating in. This is much more expensive, but better for localizing long term.
• Put each site section on a subdirectory, like www.website.com/uk/

5. Link between the different country versions of your site, so you can be sure Googlebot will find it.

Moz has got a good article on this I recommend:https://moz.com/learn/seo/international-seo

I hope this helps! Let me know if you have any questions,

Kristina

I would try to keep the same data, but organize it in a way that looks good on a screen the width of a mobile phone. HTML tables render the same way on a phone as they do on a desktop, they're just more likely to get smooshed.

I recommend playing around with your HTML using Google Chrome's Inspect option, and changing your device to a relatively small smartphone. Then build a table that looks good there.

If your table has too many columns, I'd recommend dividing the table into multiple tables, so you have the same data but in fewer columns for each table.

Good luck!

Kristina

Hi Becky,

I'm surprised to hear that there aren't a lot of long tail searches. Is the problem that you can't make more sub-category pages, or that you can't find long tail keywords to figure out which pages to build?

Either way, here's what I recommend:

1. Use Google AdWords Keyword Planner or a 3rd party tool like Storybase to gather keywords for "lockers". I used Storybase and found: mudroom lockers, mudroom lockers with bench, school lockers, storage lockers, metal lockers, lockers for home, vintage lockers, wood lockers, cell phone lockers, wooden lockers, entry lockers, all with over 880 searches/month.
2. Export these and filter for keywords that describe the products you sell.
3. Group keywords into categories and subcategories both by logic and by search volume; for example "mudroom lockers" fit within "lockers for home" but "mudroom lockers" get more searches.
4. If you can, create category pages for every subcategory that, once grouped with similar keywords, gets at least 100 searches/month
5. Add these categories to product pages. How you do this will have to do with which other keywords you're targeting and how much control you have over the page. But you'll want both category pages AND product pages to have the right keywords to rank for the type of lockers they are.
6. Check out your competition with a product like Clearscope. It'll show you the keywords that your competitors are using for those target keywords you've identified, so you can get even more long tail searches.

Hopefully that's the sort of guidance you were looking for - let us know if you have any follow up questions!

Kristina

As Brett and Gaston said, this is not ideal, but also not the worst thing. You'll probably have both non-WWW and WWW versions rank for awhile, then Google will start ignoring your canonicals.

As Gaston said, it's pretty simple to change canonicals - I would recommend doing that. Otherwise, you're showing Google that your canonicals don't match your actual site, and they may start ignoring them in the future. It's worth keeping your site structure clean!

Best,

Kristina

For any duplicate content you have between countries, use hreflang to differentiate regions. Google lays out how to do that here.

Hope this helps!

It's for different regions as well. Check out the link I shared. Google lists the reasons for hreflang. The second reason is:

"If your content has small regional variations with similar content, in a single language. For example, you might have English-language content targeted to the US, GB, and Ireland."

I would recommend setting up each country's subdirectory as separate properties in Google Search Console. Then, go to original Search Console, and click on Search Traffic > International Targeting, click the tab Country, and identify which country you're targeting users in.

That should give GSC enough information to not flag the content as duplicate.

Good luck!

Wow, yeah, this is weird! For what it's worth, your hreflang tags seem fine, so I'd be surprised if there are canonical issues. And Google has indexed your home page.

Here's what I'd dig into: does Google think visitors want to land on your /search/ page before your homepage? I work on a site that uses a search page as a paid and organic search landing page, and it has the best conversion rate of any page on our site. Is it possible that Google thinks your homepage offers a bad user experience, and your /search/ page offers a better one, so it's picking what it thinks is best?

To see if that could be the case, I'd look into:

• What's the bounce rate of the home  vs /search/ page?
• What's the time spent on page (if you can measure that properly) of each?
• How long do the pages take to load?
• How fresh is the content on the homepage vs search? (I assume the account page is the most boring.)

If this is the case, you may want to consider letting visitors search, then requiring a registration.

Good luck! And let us know what you find out!

Kristina

What I've usually seen with canonicals is that Google either removes the noncanonical page from its index, or it ignores your canonical and treats them as two separate pages. I haven't seen an example where a canonical lets you get the best of both worlds.

I agree with Nozzle - you can tweak your existing content to target both phrases! Google understands synonyms, so if anything, you're just creating a more all around relevant page.

Good luck!

Kristina