Robots.txt & Duplicate Content
-
In reviewing my crawl results I have 5666 pages of duplicate content. I believe this is because many of the indexed pages are just different ways to get to the same content. There is one primary culprit. It's a series of URL's related to CatalogSearch - for example; http://www.careerbags.com/catalogsearch/result/index/?q=Mobile
I have 10074 of those links indexed according to my MOZ crawl. Of those 5349 are tagged as duplicate content. Another 4725 are not.
Here are some additional sample links:
http://www.careerbags.com/catalogsearch/result/index/?dir=desc&order=relevance&p=2&q=Amy
http://www.careerbags.com/catalogsearch/result/index/?color=28&q=bellemonde
http://www.careerbags.com/catalogsearch/result/index/?cat=9&color=241&dir=asc&order=relevance&q=baggalliniAll of these links are just different ways of searching through our product catalog. My question is should we disallow - catalogsearch via the robots file? Are these links doing more harm than good?
-
For product pages, I would canonical the page with the most descriptive URL.
For category pages, I agree with you, I would noindex them.
I think I just answered my own question!!
-
Oke, the question concerning rel="canonical" is which URL becomes the canonical version? Since there is no page on the website which would be appropiate (as far as i've seen) i recommended the meta robots tag.
I do agree that rel="canonical" is the preferred option, but in this situation i can't see a way to implement it properly. Which page would you highlight as the canonical?
-
I agree entirely that "Search result pages are too varied to be included in the index".
That said, my understanding is that if you canonical a page, it doesn't get indexed. So we wouldn't have to worry about the appearance / user-friendliness of the URL. But (again, in my opinion) we should still worry about link equity being passed, and that won't happen if you noindex.
This gets complicated fast. I like your solution b/c it's a lot cleaner and easier to implement. Still not convinced it's the "best" way to go though.
-
Where is the evidence that these work? I have never seen them work. Google totally ignores the URL parameters tools in GWTs.
-
I do agree that a rel="canonical" is good option for the problem that's at hand.
As jeremy has stated however the link we are referring to in the href section redirects to the home page. http://www.careerbags.com/catalogsearch/result/index/In my original answer i did not test this. I assumed there would be a list of all products here not filtered by search results. Since this is not the case and this page in fact does not exist it's hard to point at a url to be canonical.
Therefor i changed my answer to include the robots meta tag. This would indeed remove the search pages from the search index. I do think this is a positive thing though.
Look at the following url: http://www.careerbags.com/catalogsearch/result/?q=rolling+laptop+bags
Not really the type of URL i would click on in the search results. The following URL however is something i would want to click on: http://www.careerbags.com/laptop-bags/women-s/rolling-laptop-bags.html
Search result pages are too varied to be included in the index to my opinion.
Hope you agree with this, if not then i would like to hear your thoughts on this.
-
Simon, Wesley, Michael...
These customer facing search result pages are the ones often bookmarked and shared by site visitors. How worried does one need to be about losing link equity? I realize every site is going to be different and social shares don't have link equity - at least for now - but this could add up over time. The rel canonical will enable capture of link equity whereas the robots noindex will not.
Am I over thinking this?
-
In this case you could add the meta robots tag on the search result pages like this:
content="noindex, follow">
Search results can indeed spawn an infinite amount of different URL's. This can be avoided by making sure they are not included in the index but are followed.
-
Webmaster guidelines specifically request that you prevent crawling of search results pages using a robots.txt file. The relevant section reads: "Use robots.txt to prevent crawling of search results pages or other auto-generated pages that don't add much value for users coming from search engines."
-
There are 2 distinct possible issues here
1. Search results are creating duplicate content
2. Search results are creating lots of thin content
You want to give the user every possibility of finding your products, but you don't want those search results indexed because you should already have your source product page indexed and aiming to rank well. If not see last paragraph.
I slightly misread your post and took the URLs to be purely filtered. You should add disallow /catalogsearch to your robots.txt and if any are indexed you can remove the directory in Webmaster Tools > Google Index > Remove URLs > Reason: Remove Directory. This from Google - http://www.mattcutts.com/blog/search-results-in-search-results/
If your site has any other parameters not in that directory you can add them in Webmaster Tools > Crawl > URL Parameters > Let Googlebot Decide. Google will understand they are not the main URLs and treat them accordingly.
As a side issue with your search results it would be a good idea to analyse them in Analytics. You might find you have a trend, maybe something searched for or not the perfect match for the returned result, where you can create new more targeted content.
-
I'm not sure this is the right approach. The catalog search is based on the search box on the website. The query parameter can be anything the customer enters. Are you suggesting that the backend code be modified to always return the in every result?
And why that page because that URL just redirects to the home page because there is no query parameter provided for the search.
In terms o losing link equity, how much equity do they have it they are duplicate content?
-
Hi Jeremy.
Yours is a common problem. The best way to deal with it is, as Wesley mentions, by putting canonical tags on all the duplicate pages - the one you want indexed and to show up in search results AND all the others that you can arrive at via catalog search or any other means of navigation.
Michael's suggestion will prevent the duplicate pages from getting indexed by Google. Unfortunately you lose any link equity going that route, so I'd suggest starting with canonical tags first.
-
To back up the detail Wesley gave you, you can also add URL parameters in Google Webmaster Tools
-
You could add a canonical tag to link to the default page. This way Google will know that it should only index that.
The code for this would be:This should be placed in the section of your HTML code.
Some more resources on the subject:
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
-
Possible duplicate content issue
Hi, Here is a rather detailed overview of our problem, any feedback / suggestions is most welcome. We currently have 6 sites targeting the various markets (countries) we operate in all websites are on one wordpress install but are separate sites in a multisite network, content and structure is pretty much the same barring a few regional differences. The UK site has held a pretty strong position in search engines the past few years. Here is where we have the problem. Our strongest page (from an organic point of view) has dropped off the search results completely for Google.co.uk, we've picked this up through a drop in search visibility in SEMRush, and confirmed this by looking at our organic landing page traffic in Google Analytics and Search Analytics in Search Console. Here are a few of the assumptions we've made and things we've checked: Checked for any Crawl or technical issues, nothing serious found Bad backlinks, no new spammy backlinks Geotarggetting, this was fine for the UK site, however the US site a .com (not a cctld) was not set to the US (we suspect this to be the issue, but more below) On-site issues, nothing wrong here - the page was edited recently which coincided with the drop in traffic (more below), but these changes did not impact things such as title, h1, url or body content - we replaced some call to action blocks from a custom one to one that was built into the framework (Div) Manual or algorithmic penalties: Nothing reported by search console HTTPs change: We did transition over to http at the start of june. The sites are not too big (around 6K pages) and all redirects were put in place. Here is what we suspect has happened, the https change triggered google to re-crawl and reindex the whole site (we anticipated this), during this process, an edit was made to the key page, and through some technical fault the page title was changed to match the US version of the page, and because geotargetting was not turned on for the US site, Google filtered out the duplicate content page on the UK site, there by dropping it off the index. What further contributes to this theory is that a search of Google.co.uk returns the US version of the page. With country targeting on (ie only return pages from the UK) that UK version of the page is not returned. Also a site: query from google.co.uk DOES return the Uk version of that page, but with the old US title. All these factors leads me to believe that its a duplicate content filter issue due to incorrect geo-targetting - what does surprise me is that the co.uk site has much more search equity than the US site, so it was odd that it choose to filter out the UK version of the page. What we have done to counter this is as follows: Turned on Geo targeting for US site Ensured that the title of the UK page says UK and not US Edited both pages to trigger a last modified date and so the 2 pages share less similarities Recreated a site map and resubmitted to Google Re-crawled and requested a re-index of the whole site Fixed a few of the smaller issues If our theory is right and our actions do help, I believe its now a waiting game for Google to re-crawl and reindex. Unfortunately, Search Console is still only showing data from a few days ago, so its hard to tell if there has been any changes in the index. I am happy to wait it out, but you can appreciate that some of snr management are very nervous given the impact of loosing this page and are keen to get a second opinion on the matter. Does the Moz Community have any further ideas or insights on how we can speed up the indexing of the site? Kind regards, Jason
Intermediate & Advanced SEO | | Clickmetrics0 -
Robots.txt advice
Hey Guys, Have you ever seen coding like this in a robots.txt, I have never seen a noindex rule in a robots.txt file before - have you? user-agent: AhrefsBot User-agent: trovitBot
Intermediate & Advanced SEO | | eLab_London
User-agent: Nutch
User-agent: Baiduspider
Disallow: / User-agent: *
Disallow: /WebServices/
Disallow: /*?notfound=
Disallow: /?list=
Noindex: /?*list=
Noindex: /local/
Disallow: /local/
Noindex: /handle/
Disallow: /handle/
Noindex: /Handle/
Disallow: /Handle/
Noindex: /localsites/
Disallow: /localsites/
Noindex: /search/
Disallow: /search/
Noindex: /Search/
Disallow: /Search/
Disallow: ? I have never seen a noindex rule in a robots.txt file before - have you?
Any pointers?0 -
Duplicate Content through 'Gclid'
Hello, We've had the known problem of duplicate content through the gclid parameter caused by Google Adwords. As per Google's recommendation - we added the canonical tag to every page on our site so when the bot came to each page they would go 'Ah-ha, this is the original page'. We also added the paramter to the URL parameters in Google Wemaster Tools. However, now it seems as though a canonical is automatically been given to these newly created gclid pages; below https://www.google.com.au/search?espv=2&q=site%3Awww.mypetwarehouse.com.au+inurl%3Agclid&oq=site%3A&gs_l=serp.3.0.35i39l2j0i67l4j0i10j0i67j0j0i131.58677.61871.0.63823.11.8.3.0.0.0.208.930.0j3j2.5.0....0...1c.1.64.serp..8.3.419.nUJod6dYZmI Therefore these new pages are now being indexed, causing duplicate content. Does anyone have any idea about what to do in this situation? Thanks, Stephen.
Intermediate & Advanced SEO | | MyPetWarehouse0 -
Huge increase in server errors and robots.txt
Hi Moz community! Wondering if someone can help? One of my clients (online fashion retailer) has been receiving huge increase in server errors (500's and 503's) over the last 6 weeks and it has got to the point where people cannot access the site because of server errors. The client has recently changed hosting companies to deal with this, and they have just told us they removed the DNS records once the name servers were changed, and they have now fixed this and are waiting for the name servers to propagate again. These errors also correlate with a huge decrease in pages blocked by robots.txt file, which makes me think someone has perhaps changed this and not told anyone... Anyone have any ideas here? It would be greatly appreciated! 🙂 I've been chasing this up with the dev agency and the hosting company for weeks, to no avail. Massive thanks in advance 🙂
Intermediate & Advanced SEO | | labelPR0 -
Duplicate content issue - online retail site.
Hello Mozzers, just looked at a website and just about every product page (there are hundreds - yikes!) is duplicated like this at end of each url (see below). Surely this is a serious case of duplicate content? Any idea why a web developer would do this? Thanks in advance! Luke prod=company-081
Intermediate & Advanced SEO | | McTaggart
prod=company-081&cat=20 -
Penalised for duplicate content, time to fix?
Ok, I accept this one is my fault but wondering on time scales to fix... I have a website and I put an affiliate store on it, using merchant datafeeds in a bid to get revenue from the site. This was all good, however, I forgot to put noindex on the datafeed/duplicate content pages and over a period of a couple of weeks the traffic to the site died. I have since nofollowed or removed the products but some 3 months later my site still will not rank for the keywords it was ranking for previously. It will not even rank if I type in the sites' name (bright tights). I have searched for the name using bright tights, "bright tights" and brighttights but none of them return the site anywhere. I am guessing that I have been hit with a drop x place penalty by Google for the duplicate content. What is the easiest way around this? I have no warning about bad links or the such. Is it worth battling on trying to get the domain back or should I write off the domain, buy a new one and start again but minus the duplicate content? The goal of having the duplicate content store on the site was to be able to rank the category pages in the store which had unique content on so there were no problems with that which I could foresee. Like Amazon et al, the categories would have lists of products (amongst other content) and you would click through to the individual product description - the duplicate page. Thanks for reading
Intermediate & Advanced SEO | | Grumpy_Carl0 -
Mobile Site - Same Content, Same subdomain, Different URL - Duplicate Content?
I'm trying to determine the best way to handle my mobile commerce site. I have a desktop version and a mobile version using a 3rd party product called CS-Cart. Let's say I have a product page. The URLs are... mobile:
Intermediate & Advanced SEO | | grayloon
store.domain.com/index.php?dispatch=categories.catalog#products.view&product_id=857 desktop:
store.domain.com/two-toned-tee.html I've been trying to get information regarding how to handle mobile sites with different URLs in regards to duplicate content. However, most of these results have the assumption that the different URL means m.domain.com rather than the same subdomain with a different address. I am leaning towards using a canonical URL, if possible, on the mobile store pages. I see quite a few suggesting to not do this, but again, I believe it's because they assume we are just talking about m.domain.com vs www.domain.com. Any additional thoughts on this would be great!0 -
How to Resolve Duplication of HTTPS & HTPP URLs?
Right now, I am working on eCommerce website. [Lamps Lighting and More] I can find out both URLs in website as follow. HTTP Version: http://www.lampslightingandmore.com/ HTTPS Version: https://www.lampslightingandmore.com/ I have check one of my competitor who has implemented following canonical on both pages. Please, view source code for both URLs. http://www.wayfair.com ** https://www.wayfair.com** Then, I checked similar thing in SEOmoz website. 🙂 Why should I not check in SEOmoz because, They are providing best SEO information so may be using best practice to deal with HTTPS & HTTP. LOL I tried to load following URL so it redirect to home page. https://www.seomoz.org is redirecting to http://www.seomoz.org But, following URL is not redirecting any where as well as not set canonical over there. https://www.seomoz.org/users/settings I can find out following code on http://www.seomoz.org/robots.txt **User-agent: *** ** Disallow: /api/user?*** So, I am quite confuse to solve issue. Which one is best 301 redirect or canonical tag? If any live example to see so that's good for me and make me more confident.
Intermediate & Advanced SEO | | CommercePundit0