What could cause Google to not honor canonical URLs?
-
I have a strange situation on a website, when I do a Google query of site:example.com all the top indexed results appear to be queries that users can perform on the website. So any random term the user searches for on the website for some reason is causing the search result page to get indexed - like example.com/search/query/random-keywords
However, the search results page has a canonical tag on it that points to example.com/search, but that doesn't seem to be doing anything. Any thoughts or ideas why this could be happening?
-
Hi there,
First of all, its a mistake to think that when searching with _site: _operator, the first results are the most important nor the more relevant. Google has said a few times that we shouldn't rely that much on what that search in terms of what's being shown.
Blocking search results with robots.txt wont be of help, as it will not remove already indexed pages and cant prevent for new pages to be indexed (if there's an external link to a robots.txt blocked page, google can still index it) it'll only prevent Googlebot from discovering new ones FROM YOUR SITE.
Again, i'd try to dig deeper to understand where are the links to internal searches that google is finding. Googlebot will not do any search in your site.
The thing with GSC, might be related to quite a few reasons. I cant say much because I don't know any more specifics, but from what you are telling me it looks like you are getting impressions in searches that you don't relate to your site and that land on pages that google is noindexing. Yeah im repeating the obvious, hehe.
In my experience, Google can have these strange behaviours. You know, there are cases when a page is canonicalized, but it can still be shown in SERPS. Dont ask me why, but it happens. It takes a little time to google fully replace it with the correct one.
I'd wait a little longer to see how Google is handling them.I don't know if im helping you.
it kinda took me a few minutes to understand/process what you wrote and come up with an answer.Please, feel free ask again or comment on my reply if I misunderstood something.
Best luck,
Gaston -
Hi here's some more background info on this situation that makes it even stranger. I can perform some pretty specific searches on Google where these indexed search result pages show up. And I can look in Google Search Console under the performance section and see that those pages receive impressions and clicks. However, if I inspect the URL, Search Console says it is not included in Google's index, and the reason it gives under indexing is because it says it is honoring the canonical URL. So search console is saying it isn't indexed because of the canonical, but I can do searches and find that exact URL in the index. Any ideas what this could be from?
-
Hi Gaston,
Thanks for the response. I can confirm that the example, /search and /search?q=foo are pretty much identical. However that may not always be the case, only when a user searches for something that would return no results. So, a website that sells widgets, /search and /search?q=widgets would not be identical, and in that case it would make sense that Google would not honor the canonical link. What's really strange is if I search google for the site: operator of the domain, the top pages are not user queries for things that make sense. The top indexed pages are random, non-relevant user searches.
I do not have a way with this system to control noindex tags on these search result pages. The only thing I could do is take the nuclear option and just block it all with robots.txt using wildcards. But that means no search result pages would get indexed, relevant or not.
-
Hi there,
in my experience, when google doesn't honor Canonicals, is because pages arent similar.
In its definition, canonical are there for two or more pages that have the same content.If you are finding it problematic, i'd suggest to use noindex tags for that search pages.
I'd investigate If there are links pointing to those internal search pages, as its not common for google to discover search pages.Hope it helps,
Best luck.
Gaston
Got a burning SEO question?
Subscribe to Moz Pro to gain full access to Q&A, answer questions, and ask your own.
Browse Questions
Explore more categories
-
Moz Tools
Chat with the community about the Moz tools.
-
SEO Tactics
Discuss the SEO process with fellow marketers
-
Community
Discuss industry events, jobs, and news!
-
Digital Marketing
Chat about tactics outside of SEO
-
Research & Trends
Dive into research and trends in the search industry.
-
Support
Connect on product support and feature requests.
Related Questions
-
Google crawl drop
the crawl request of my company site: https://www.dhgate.com/ has dropped nearly over 95%, from daily 6463599 requests to 476493 requests at 12:00am on 9th, Oct (GMT+8). This dramatic dropping trend not only showed in our GSC crawl stats report but also our company's own log report. We have no idea what’s going on. We want to know whether there is an update of google about crawlling, or is this the issue of our own site? If something is wrong with our site, in what aspects would you recommend us to check, analyze and accordingly optimize?
Technical SEO | | DHgate_20140 -
Metadata configured, but Google only shows URL with sitelinks. Something wrong with my code?
Hi guys! I have a metadata problem with my home page. If I look for the brand's keyword, the SERPs don´t show the metadata I configured, instead it shows the URL with sitelinks. If I use the "site:" command, it doesn't appear at all. This happens only on the home page, not the rest, which are roughly 700 pages. Those appear fine. I already have a meta title and meta description configured, which include the mentioned KW. It used to appear correctly before. GSC shows it indexed. Most audit tools (configured to crawl JS) detect the metadata. Moz's On Page tool doesn't. Could it be because of the JS configuration? Or am I missing something else? Here´s the meta description code:What do you think? I'd appreciate your input. Thanks!
Technical SEO | | Reprise0 -
Google Search Console and User-declared canonical is actually Hreflang tag
Hey, We recently launched a US version of UK based ecommerce website on the us.example.com subdomain. Both websites are on Shopify so canonical tags are handled automatically and we have implemented Hreflang tags across both websites. Suddenly our rankings in the UK have dropped and after looking in search console for the UK site ive found that a lot of pages are now no longer indexed in Google because the User-declared canonical is the Hreflang tag for the US URL. Below is an example https://www.example.com/products/pac-man-arcade-cabinet - is the product page is the canonical tag rel="alternate" href="https://www.example.com/products/pac-man-arcade-cabinet" hreflang="en-gb" /> - UK hreflang tag rel="alternate" href="https://us.example.com/products/pac-man-arcade-cabinet" hreflang="en-us" /> - US Hreflang tag then in Google search console the user-defined canonical is https://us.example.com/products/pac-man-arcade-cabinet but it should be https://www.example.com/products/pac-man-arcade-cabinet The UK website has been assigned to target the United Kingdom in Search Console and the US website has been assigned to target the United States. We also do not have access to robots.txt file unfortunately. Any help or insight would be greatly appreciated.
Technical SEO | | PeterRubber0 -
Drupal, http/https, canonicals and Google Search Console
I’m fairly new in an in-house role and am currently rooting around our Drupal website to improve it as a whole. Right now on my radar is our use of http / https, canonicals, and our use of Google Search Console. Initial issues noticed: We serve http and https versions of all our pages Our canonical tags just refer back to the URL it sits on (apparently a default Drupal thing, which is not much use) We don’t actually have https properties added in Search Console/GA I’ve spoken with our IT agency who migrated our old site to the current site, who have recommended forcing all pages to https and setting canonicals to all https pages, which is fine in theory, but I don’t think it’s as simple as this, right? An old Moz post I found talked about running into issues with images/CSS/javascript referencing http – is there anything else to consider, especially from an SEO perspective? I’m assuming that the appropriate certificates are in place, as the secure version of the site works perfectly well. And on the last point – am I safe to assume we have just never tracked any traffic for the secure version of the site? 😞 Thanks John
Technical SEO | | joberts0 -
Questions about canonicals
Howdy Moz community, I had a question regarding canonicals. I help a business with their SEO, and they are a service company. They have one physical location, but they serve multiple cities in the state. My question is in regards to canonicals and unique content. I hear that a page with slightly differing content for each page won't matter as much, if most of the content is relevantly the same. This business wants to create service pages for at least 10 other cities they service. The site currently only have pages that are targeting one city location. I was wondering if it was beneficial to use a template to service each city and then put a canonical there to say that it is an identical page to the main city page? Example: our first city was san francisco, we want to create city pages for santa rosa, novato, san jose and etc. If the content for the 2nd, 3rd, 4th, city were the same content as the 1st city, but just had the slight change with the city name would that hurt? Would putting a canonical help this issue, if i alert that it is the same as the 1st page? The reason I want to do this, is because I have been getting concerns from my copywriter that after the 5th city, they can't seem to make the services pages that much different from the first 4 cities, in terms of wording of the content and its structure. I want to know is there a simpler way to target multiple cities for local SEO reasons like geo targeted terms without having to think of a completely new way to write out the same thing for each city service page, as this is very time consuming on my end. Main questions? Will making template service pages, changing the city name to target different geographic locations and putting a canonical tag for the new pages created, and referring back to the main city page going to be effective in terms of me wanting to rank for multiple cities. Will doing this tell google my content is thin or be considered a duplicate? Will this hurt my rankings? Thanks!
Technical SEO | | Ideas-Money-Art0 -
I have altered a url as it was too long. Do I need to do a 301 redirect for the old url?
Crawl diagnostics has shown a url that is too long on one of our sites. I have altered it to make it shorter. Do I now need to do a 301 redirect from the old url? I have altered a url previously and the old url now goes to the home page - can't understand why. Anyone know what is best practice here? Thanks
Technical SEO | | kingwheelie0 -
Friendly URLs
Hi, I have an important news site and I am trying to implement user friendly URLs. Now, when you click a news in the homepage, it goes to a redirect.php page and then goes to a friendly url. the question is, It is better to have the friendly URL in the first link or it is the same for the robot having this in the finally url? Thanks
Technical SEO | | informatica8100 -
How to keep a URL social equity during a URL structure/name change?
We are in the process of making significant URL name/structure change to one of our property and we want to keep the social equity (likes, share, +1, tweets) from the old to the new URL. We have been trying many different option without success. We are running our social "button" in an iframe. Thanks
Technical SEO | | OlivierChateau0