Google Not Indexing XML Sitemap Images
-
Hi Mozzers,
We are having an issue with our XML sitemap images not being indexed.
The site has over 39,000 pages and 17,500 images submitted in GWT. If you take a look at the attached screenshot, 'GWT Images - Not Indexed', you can see that the majority of the pages are being indexed - but none of the images are.
The first thing you should know about the images is that they are hosted on a content delivery network (CDN), rather than on the site itself. However, Google advice suggests hosting on a CDN is fine - see second screenshot, 'Google CDN Advice'. That advice says to either (i) ensure the hosting site is verified in GWT or (ii) submit in robots.txt. As we can't verify the hosting site in GWT, we had opted to submit via robots.txt.
There are 3 sitemap indexes: 1) http://www.greenplantswap.co.uk/sitemap_index.xml, 2) http://www.greenplantswap.co.uk/sitemap/plant_genera/listings.xml and 3) http://www.greenplantswap.co.uk/sitemap/plant_genera/plants.xml.
Each sitemap index is split up into often hundreds or thousands of smaller XML sitemaps. This is necessary due to the size of the site and how we have decided to pull URLs in. Essentially, if we did it another way, it may have involved some of the sitemaps being massive and thus taking upwards of a minute to load.
To give you an idea of what is being submitted to Google in one of the sitemaps, please see view-source:http://www.greenplantswap.co.uk/sitemap/plant_genera/4/listings.xml?page=1.
Originally, the images were SSL, so we decided to reverted to non-SSL URLs as that was an easy change. But over a week later, that seems to have had no impact. The image URLs are ugly... but should this prevent them from being indexed?
The strange thing is that a very small number of images have been indexed - see http://goo.gl/P8GMn. I don't know if this is an anomaly or whether it suggests no issue with how the images have been set up - thus, there may be another issue.
Sorry for the long message but I would be extremely grateful for any insight into this. I have tried to offer as much information as I can, however please do let me know if this is not enough.
Thank you for taking the time to read and help.
Regards,
Mark
-
Hi Mark,
I'm just following the thread as I have a similar problem. Would you mind sharing your results from the tests?
Thanks,
Bogdan -
Thanks Everett - that's exactly what I intend to do.
We will be testing two new sitemaps with 100 x URLs each. 1. With just the file extension removed and 2. With the entire cropping part of the URL removed, as suggested by Matt.
Will be interested to see whether just one or both of the sitemaps are successful. Will of course post the outcome here, for anyone who might have this problem in future.
-
It isn't always that simple. Maybe commas don't present a problem on their own. Maybe double file extensions don't present a problem on their own. Maybe a CDN doesn't present a problem on its own. Maybe very long, complicated URLs don't present a problem on their own.
You have all of these. Together, in any combination, they could make indexation of your images a problem for Google.
Just test it out on a few. Get rid of the file extension. If that doesn't work, get rid of the comma. That is all you can do. Start with whatever is easiest for the developer to implement, and test it out on a few before rolling it out across all of your images.
-
Cheers for that mate - especially the useful Excel formula.
I am going to try a few things in isolation so that we can accurately say which element/s caused the issue.
Thanks again, mate.
-
Ignore the developer - what worked for one doesn't mean it'll work for you
The easiest way to test this is to manually create a sitemap with 100 or so 'clean' image URLs. Just pull the messy ones into excel and use the formula below to create a clean version (Use A1 for messy, B1 for formula).
Good luck mate.
=CONCATENATE("image:imageimage:lochttp://res.cloudinary.com/greenplantswap/image/upload/",RIGHT(A1,LEN(A1)-(FIND("",(SUBSTITUTE(A1,"/","",(IF(LEN(TRIM(A1))=0,0,LEN(TRIM(A1))-LEN(SUBSTITUTE(A1,"/",""))))))))),"</image:loc></image:image>")
-
Thanks for the responses guys, much appreciated.
In terms of the commas, that was something that I put to the developer, however he was able to come back with examples where this has clearly not been an issue - e.g. apartable.com have commas in their URLs and use the same CDN (Coudinary).
However, I agree with you that double file extension could be the issue. I may have to wait until next week to find out as the developer is working on another project, but will post the outcome here once I know.
Thank you again for the help!
-
Hello Edlondon,
I think you're probably answering your own question here. Google typically doesn't have any problem indexing images served from a CDN. However, I've seen Google have problems with commas in the URL at times. Typically it happens when other elements in the URL are also troublesome, such as your double file extension.
Are you able to rename the files to get rid of the superfluous .jpg extension? If so, I'd recommend trying it out on a few dozen images. We could come up with a lot of hypothesis, but that would be the one I'd test first.
-
Hmmm I step off here, never used cloudinary.com or even heard of them. I personally use NetDNA, with pull zones (which means that they load the image/css/js from your origin and store a version on their servers) while handling cropping/resizing from my own end (via PHP and then loading that image, example: http://cdn.fulltraffic.net/blog/thumb/58x58/youtube-video-xQmQeKU25zg.jpg try changing the 58x58 to another size and my server will handle the crop/resize while NetDNA will serve it and store for future loads).
-
Found one of the sites with the same Cloudinary URLs with commas - apartable.com
See Google image results: https://www.google.co.uk/search?q=site:apartable.com&tbm=isch
Their images appear to be well indexed. One thing I have noticed, however, is that we often have .jpg twice in the image URL. E.g.:
- http://res.cloudinary.com/greenplantswap/image/upload/c_crop,g_north,h_0.9,w_1.0/c_fill,d_no_image_icon-720x720**.jpg**,g_center,h_900,q_80,w_900/v1352574983/oyfos82vwvmxdx91hxaw**.jpg**
- http://res.cloudinary.com/greenplantswap/image/upload/c_crop,g_north,h_0.9,w_1.0/c_fill,d_no_image_icon-720x720**.jpg**,g_center,h_900,q_80,w_900/v1352574989/s09cv3krfn7gbyvw3r2y**.jpg**
- http://res.cloudinary.com/greenplantswap/image/upload/c_crop,g_north,h_0.9,w_1.0/c_fill,d_no_image_icon-720x720**.jpg**,g_center,h_407,q_80,w_407/v1352575010/rl7cl4xi0timza1sgzxj**.jpg**
Wonder if that is confusing Google? If so, none of this is consistent, as they do have a few images indexed with exactly the same kind of URL as those listed above.
-
Thought I had them on email but must be within our fairly cumbersome Skype thread... let me have a dig through when I get chance and I'll post them up here.
-
Hmmmm, okay... Could you post the examples they gave, and an example page where the images are located on the site?
-
Hi Matt,
Thought I should let you know that (i) the X-Robots-Tag was not set, so that's not the issue and (ii) the URLs, although ugly, are not the issue either. We had a couple of examples of websites with the same thing (I'm told the commas facilitate on-the-fly sizing and cropping) and their images were indexed fine.
So, back to the drawing board for me! Thank you very much for the suggestions, really do appreciate it.
Mark
-
Hmm interesting - we hadn't thought of the X-Robots-Tag http header. I'm going to fire that over to the developer now.
As for the URLs, they are awful! But I am told that this is not a problem - but perhaps this is worth re-chasing up as other solutions have, so far, been unfruitful.
Thanks for taking the time to help, Matt - I'll let you know if that fixes it! Unfortunately it could be another week before I know, as the developer is currently working on another project so any changes may be early-mid next week.
Thanks again...
-
This is a bit of a long shot but if the files have been uploaded using their API it may have been that the 'X-Robots-Tag' http header is set to no-index...
Also, those URLs don't look great with the commas in them. Have you tried doing a small subset that just has the image id (e.g. http://res.cloudinary.com/greenplantswap/image/upload/nprvu0z6ri227cgnpmqc.jpg)?
Matt
-
Hi Federico,
Thanks very much for taking the time to respond.
To answer your question, we are using http://cloudinary.com/. So, taking one of the examples from the XML sitemap I posted above, an example of an image URL is http://res.cloudinary.com/greenplantswap/image/upload/c_crop,g_north,h_0.9,w_1.0/c_fill,d_no_image_icon-720x720.jpg,g_center,h_900,q_80,w_900/v1352575097/nprvu0z6ri227cgnpmqc.jpg (what a lovely URL!).
I had a look at http://res.cloudinary.com/robots.txt and it seems that they are not blocking anything - the disallow instruction is commented out. I assume that is indeed the robots.txt I should be looking at?
Assuming it is, this does not appear to get to the bottom of why the images are not being indexed.
Any further assistance would be greatly appreciated - we have 17k unique images that could be driving traffic and this is a key way that people find our kind of website.
Thanks,
Mark
-
Within that robot.txt file on the CDN (which one are you using?) have you set to allow Google to index them?
Most CDNs I know allows you to block engines via the robots.txt to avoid bandwidth consumption.
In the case you are using NetDNA (MaxCDN) or the like, make sure your robots file isn't disallowing robots to crawl.
We are using a CDN too to deliver images and static files and all of them are being indexed, we tested disallowing crawlers but it caused a lot of warnings, so instead we no allow all of them to read and index content (is a small price to pay to have your content indexed).
Hope that helps!
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
-
What to do if lots of backend pages have been indexed by Google erroneously?
Hi Guys Our developer forgot to add a no index no follow tag on the pages he created in the back-end. So we have now ended up with lots of back end pages being indexed in google. So my question is, since many of those are now indexed in Google, so is it enough to just place a no index no follow on those or should we do a 301 redirect on all those to the most appropriate page? If a no index no follow is enough, that would create lots of 404 errors so could those affect the site negatively? Cheers Martin
Intermediate & Advanced SEO | | martin19700 -
Can you index a Google doc?
We have updated and added completely new content to our state pages. Our old state content is sitting in a our Google drive. Can I make these public to get them indexed and provide a link back to our state pages? In theory it sounds like a great link building strategy... TIA!
Intermediate & Advanced SEO | | LindsayE1 -
Google doesn't index image slideshow
Hi, My articles are indexed and images (full size) via a meta in the body also. But, the images in the slideshow are not indexed, have you any idea? A problem with the JS Example : http://www.parismatch.com/People/Television/Sport-a-la-tele-les-femmes-a-l-abordage-962989 Thank you in advance Julien
Intermediate & Advanced SEO | | Julien.Ferras0 -
SITEMAP - Does <changefreq>and <image:title>have any apreciable effect?</image:title></changefreq>
Hi everyone. It was hard to find some actual evidence that some of the atributes to be declared in a sitemap have some real impact.
Intermediate & Advanced SEO | | Gaston Riera
Particularly, im interested in these two: <changefreq></changefreq> and**image:title</image:title>** I've used them in a few cases just to check their effect and couldnt see any.
Do you have any experience with these? Or any other atribute that might be helpful, in order to create a more accurate and effective sitemap? Also, this could be a great topic to create a new Moz Blog post, the one about sitemap is 8years old.0 -
Sitemaps: HTML and/or XML?
Can someone explain sitemaps, and if you need html and/or xml? I have a site with a few html sitemaps, one for products, one for categories. I have another site with just one xml sitemap for my entire site (which has massive pages, 600k+). Should I be dividing the site with massive pages into html sitemaps like my other site?
Intermediate & Advanced SEO | | WebServiceConsulting.com0 -
Best way to permanently remove URLs from the Google index?
We have several subdomains we use for testing applications. Even if we block with robots.txt, these subdomains still appear to get indexed (though they show as blocked by robots.txt. I've claimed these subdomains and requested permanent removal, but it appears that after a certain time period (6 months)? Google will re-index (and mark them as blocked by robots.txt). What is the best way to permanently remove these from the index? We can't use login to block because our clients want to be able to view these applications without needing to login. What is the next best solution?
Intermediate & Advanced SEO | | nicole.healthline0 -
Killing 404 errors on our site in Google's index
Having moved a site across to Magento, obviously re-directs were a large part of that, ensuring all the old products and categories linked up correctly with the new site structure. However, we came up against an issue where we needed to add, delete, then re-add products. This, coupled with a misunderstanding of the csv upload processing, meant that although the old urls redirected, some of the new Magento urls changed and then didn't redirect: For Example: mysite/product would get deleted re-added and become: mysite/product-1324 We now know what we did wrong to ensure it doesn't continue to happen if we weret o delete and re-add a product, but Google contains all these old URLs in its index which has caused people to search for products on Google, click through, then land on the 404 page - far from ideal. We kind of assumed, with continual updating of sitemaps and time, that Google would realise and update the URL accordingly. But this hasn't happened - we are still getting plenty of 404 errors on certain product searches (These aren't appearing in SEOmoz, there are no links to the old URL on the site, only Google, as the index contains the old URL). Aside from going through and finding the products affected (no easy task), and setting up redirects for each one, is there any way we can tell Google 'These URLs are no longer a thing, forget them and move on, let's make a fresh start and Happy New Year'?
Intermediate & Advanced SEO | | seanmccauley0 -
IP address being indexed by Google in addition to canonical domain.
Our site's IP address is being indexed in addition to the canonical www.example.com domain. As soon as it was flagged a 301 was implemented in the .htaccess file to redirect the IP address to the canonical. Does this usually occur? Is it detrimental to SEO? In my time in SEO I've never heard of this being an issue, or being part of a list of things to be checked. It sounds more like a server that wasn't configured correctly when hosting was set up? It didn't seem to be affecting the site at all, but is it more common and I've just never heard of it? 😛 Should it be something I'm usually looking for in future? Responses are greatly appreciated!
Intermediate & Advanced SEO | | mikeimrie0