Moz Q&A is closed.
After more than 13 years, and tens of thousands of questions, Moz Q&A closed on 12th December 2024. Whilst we’re not completely removing the content - many posts will still be possible to view - we have locked both new posts and new replies. More details here.
Best approach to launch a new site with new urls - same domain
-
We have a high volume e-commerce website with over 15K items, an average of 150K visits per day and 12.6 pages per visit. We are launching a new website this spring which is currently on a beta sub domain and we are looking for the best strategy that preserves our current search rankings while throttling traffic (possibly 25% per week) to measure results.
The new site will be soft launched as we plan to slowly migrate traffic to it via a load balancer. This way we can monitor performance of the new site while still having the old site as a backup. Only when we are fully comfortable with the new site will we submit the 301 redirects and migrate everyone over to the new site. We will have a month or so of running both sites.
Except for the homepage the URL structure for the new site is different than the old site.
What is our best strategy so we don’t lose ranking on the old site and start earning ranking on the new site, while avoiding duplicate content and cloaking issues?
Here is what we got back from a Google post which may highlight our concerns better:
Thank You,
sincerely,
Stephan Woo Cude
SEO Specialist
-
Hi there,
I was just reading this old thread to get some info, but I'd love it if you could share you actual results from the launch. What did you do and how much did traffic change? How long before you were back to normal?
I usually find that with a new website and all new URLs, I end up seeing maybe a month or sodip in traffic that can be up to 10%. But that seems to be less and less as time goes on. The search engines are usually on top of it though, they recrawl and recatalog quite quickly.
Would love to hear from you.
Thanks!
Leslie
-
Just to chime in on this, albeit maybe a little late now... I had the same thought as I was reading through this with using rel=canonical to point the old pages to the new for now, so the search engines don't have any duplicate content issues until a 301 redirect can take over when the new site is fully launched.
However, depending on your rollout schedule, this would mean that the SERPs would soon be indexing only the new pages. You'd need to ensure that the traffic diverter you are using would handle this. Otherwise you could put the rel=canonical on the new pages for now, which would avoid the duplicate content until you are fully launched. Then you'd remove it and 301 redirect the old pages to the new.
Just something you maybe want to think about! Hopefully your traffic diverter can handle this though.
-
Thank you very much for the insight!
-
Ah ok. I understand now. I wasn't picking up on what you were saying before.
If with the soft launch you are already putting the "new" version of the site on their intended final URLs then yes, you can let the engines start crawling those URLs. For each new URL you let the search engines crawl make sure to 301 its corresponding old URL (the old site) to the new version to minimize any duplicate content issues.
If for whatever reason you can't quite 301 the old URLs yet (like if you still need instant access to reroute traffic back to them) you could try using rel=canonical on the old pages and point them to their new counter part only if the main content on each of the pages is almost exactly the same. You don't want Google to think you're manipulating them with rel=canonical.
-
Sorry this is so confusing and thank you so much for your responses... there would be no subdomain when we do the soft launch... it would be http://www.sierratradingpost.com/Mens-Clothing.html (old site) vs http://www.sierratradingpost.com/mens-clothing~d~15/ (new site)...
-
As I'd said, there really isn't a reason to let them get a head start. The URL's will be changing when you transition the new site out of the subdomain (ie beta.sierratradingpost.com/mens vs sierratradingpost.com/mens - those are considered 2 completely different URLs) and the engines will have to recrawl all of the new pages at that point anyway.
-
We do plan to do that... it is just since we plan a soft launch we will essentially have 2 sites out there. We are wondering when to remove the noindex from the new site. We will have 2 sites for about a month... should we let the bots crawl the new site (new urls, same domain) only we we take down the old site and have the 301's or let Google crawl earlier to get the new site a head start on indexing.
-
And when you drop the sub domain you definitely want to 301 all of the old site structure's URLs to their corresponding new page's URLs. That way nothing gets lost in the transition.
-
We would drop the subdomain - so we would have 2 "Men's Clothing" department pages - different URLs, slightly different content...
-
Yeah, just refer to our conversation above as I think it will pertain better to your situation.
-
The only issue is that you have to keep in mind that Google/Bing defines pages on the internet through their URL's, not the content. The content only describes the pages.
So if you let the engines pre crawl the pages before dropping the subdomain - simply for the reason of letting them have a "sneak peek" - you won't really be doing yourself much of a favor, as the engines will just be recrawling the content on the non subdomain URL as if it were brand new anyway.
The reason to do it the pre crawl way would be if you're already building back links to the new beta pages. Then it could make sense to let the engines index those pages and 301 them to their new non subdomain versions later. In my opinion the benefit from this route would outweigh any potential duplicate content issues.
-
But the URL structer is different... does that matter?
-
What YesBaby is talking about is somehting like Google's Website Optimizer. When someone goes to sierratradingpost.com/mens-stuff, for example, it will give 50% of the people the old version of the site for that page, and the other 50% the new version. It will eliminate any duplicate content issues as the 2 page variations will still be attached to the same exact URL.
Definitely a viable option if it fits with your game plan of how you want to do things.
-
SInce all of the URLs except for the homepage - what do you think about letting the new site get crawled maybe 2 weeks before it is 100% launched? We would have some duplicate content issues but I am hoping this would give us a head start with the new site.... then when we go 100% we add the 301's and new sitemap. It is my understanding we will be dropping the sub domain for the soft launch.
Thank you so much!
-
First of all - I love the new design. It looks great!
The absolutel best way to go about it in my opinion would be to simply have the new site ready, and then launch it fully under the base domain (no subdomain) while 301 redirecting important old pages on the site to their related new versions. That way the search engine will have the easiest time of discovering the new site and indexing it, while making sure you don't lose anything in the transition via proper 301'ing.
I can't say it would provide you with a massive benefit to set up a way for the search engines to start crawling the new site for now, as you're just going to be moving all of those URL's off of the subdomain in the near future anyway - where they will then need to be recrawled on the parent domain as if they were brand new.
If the traffic diverter you have set up automatically 301's requests for old site pages to their new beta URL version then you might as well let those new versions be indexed for the time being. Just make sure that when you transfer the beta site to the parent domain that you 301 the old beta URL's to their new permanent home.
-
So with the service - the new site is not crawled until we launch it?
-
The new site is beta.sierratradingpost.com where we will be dropping the beta. On the old one has catalog departments... ie Men's Classics, which, at this time, are not being carried over to the new site. I guess we are wonding when we should allow the robots to crawl the new site?
-
Hey Stephan,
I'm assuming you want to measure how the traffic is converting on the new site, hence the strategy to send small portions of traffic to new pages?
If so, the easiest way might to just straight up A/B split test the new pages with a service like Adobe/Omniture Test&Target. This doesn't cause any cloaking/dupe isseues. When you are happy with the results you can realese the site with all the 301's in place.
-
Let me make sure I have this straight... you're not going to be directing the new site format to a subdomain permanently, right? You were only using the sub domain for beta purposes?
The way I see it, when I go to Sierra Trading Post's site now I can make out what looks like 2 different types of architecture structures. You have one link on the page pointing to Men's clothing which executes at a single defined .htm file. Then you can see that you have the "Men's Classics" (still general men's clothing?) which points to a directory which I'm guessing is your new site. Correct me if I'm wrong on this, or if I'm right but have the old vs. new reversed.
If that is the case your best bet to try and minimalize any ranking impact would be to 301 redirect pages from the old catalog architecture to the new. That way you could remove the old site files completely and let the server take care of the direction.
If you need to leave the old site up for throttling purposes like you said - you could use canoniclazation tags to refer the old pages to the new ones. That along with employing 301 tags would help train the search engines into understanding what you're doing.
I'm sorry if I didn't answer your question as you needed. I'm still not sure if I understood your issue as intended. =P
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
-
Shopify Site with Multiple Domains?
Hey there! My client has a website on Shopify. I don't even know how to open this can of worms, but let me try. The site URL is: https://mobilityequipmentforless.com/ However, there is another (older?) URL that gets updated as the main site gets updated and shows the exact same content. It's a straight duplicate, but is it's own URL and doesn't redirect to the main site. https://www.powerchairrecyclers.com/ And this isn't the SITE.Shopify back-end site name that was used for set up initially. I just have no idea what's going on here. Not sure if it's a serious error that needs to be fixed, or if it's something weird with how Shopify work. Any insight would be immensely helpful. Thanks! Mike
Intermediate & Advanced SEO | | naturalsociety0 -
All URLs in the site is 302 redirected to itself
Hi everyone, I have a problem with a website wherein all URLs (homepage, inner pages) are 302 redirected. This is based on Screaming Frog crawl. But the weird thing is that they are 302 redirected to themselves which doesn't make any sense. Example:
Intermediate & Advanced SEO | | alex_goldman
https://www.example.com.au/ is 302 redirected to https://www.example.com.au/ https://www.example.com.au/shop is 302 redirected to https://www.example.com.au/shop https://www.example.com.au/shop/dresses is 302 redirected to https://www.example.com.au/shop/dresses Have you encountered this issue? What did you do to fix it? Would be very glad to hear your responses. Cheers!0 -
Redirecting to a new domain... a second time
Hi all, I help run a website for a history-themed podcast and we just moved it to its second domain in 7 years. We've had very good SEO up until last week, and I'm wondering if I screwed up the way I redirected the domains. It's like this: Originally the site was hosted at "first.com", and it acquired inbound links. However, we then started to host the site on blogger, so we... Redirected the site to "second.blogspot.com". (Thus, 1 --> 2) It stayed here for about 7 years and got lots of traffic. Two weeks ago we moved it off of blogger and into Wordpress, so we 301 redirected everything to... third.com. (Thus, 1 --> 2 --> 3) The redirects worked, and when we Google individual posts, we are now seeing them in Google's index at the new URL. My question: What about the 1--> 2 redirect? There are still lots of links pointing to "first.com". Last week I went into my GoDaddy settings and changed the first redirect, so that first.com now points to third.com. (Thus 1 --> 3, and 2-->3) I was correct in doing that, right? The drop in Google traffic I've seen this past week makes me think that maybe I screwed something up. Should we have kept 1 --> 2 --> 3? (Again, now we have 1-->3 and 2-->3) Thanks for any insights on this! Tom
Intermediate & Advanced SEO | | TomNYC1 -
Where is the best place to put a sitemap for a site with local content?
I have a simple site that has cities as subdirectories (so URL is root/cityname). All of my content is localized for the city. My "root" page simply links to other cities. I very specifically want to rank for "topic" pages for each city and I'm trying to figure out where to put the sitemap so Google crawls everything most efficiently. I'm debating the following options, which one is better? Put the sitemap on the footer of "root" and link to all popular pages across cities. The advantage here is obviously that the links are one less click away from root. Put the sitemap on the footer of "city root" (e.g. root/cityname) and include all topics for that city. This is how Yelp does it. The advantage here is that the content is "localized" but the disadvantage is it's further away from the root. Put the sitemap on the footer of "city root" and include all topics across all cities. That way wherever Google comes into the site they'll be close to all topics I want to rank for. Thoughts? Thanks!
Intermediate & Advanced SEO | | jcgoodrich0 -
What is the best URL structure for categories?
A client's site currently uses the URL structure: www.website.com/�tegory%/%postname% Which I think is optimised fairly well, as the categories are keywords being targeted. However, as they are using a category hierarchy, often times the URL looks like this: www.website.com/parent-category/child-category/some-post-titles-are-quite-long-as-they-are-long-tail-terms Best practise often dictates (such as point 3 in this Moz article) that shorter URLs are better for several reasons. So I'm left with a few options: Remove the category from the URL Flatten the category hierarchy Shorten post titles two a word or two - which would hurt my long tail search term traffic. Leave it as it is What do we think is the best route to take? Thanks in advance!
Intermediate & Advanced SEO | | underscorelive0 -
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 -
Include Cross Domain Canonical URL's in Sitemap - Yes or No?
I have several sites that have cross domain canonical tags setup on similar pages. I am unsure if these pages that are canonicalized to a different domain should be included in the sitemap. My first thought is no, because I should only include pages in the sitemap that I want indexed. On the other hand, if I include ALL pages on my site in the sitemap, once Google gets to a page that has a cross domain canonical tag, I'm assuming it will just note that and determine if the canonicalized page is the better version. I have yet to see any errors in GWT about this. I have seen errors where I included a 301 redirect in my sitemap file. I suspect its ok, but to me, it seems that Google would rather not find these URL's in a sitemap, have to crawl them time and time again to determine if they are the best page, even though I'm indicating that this page has a similar page that I'd rather have indexed.
Intermediate & Advanced SEO | | WEB-IRS0 -
URL Structure for Directory Site
We have a directory that we're building and we're not sure if we should try to make each page an extension of the root domain or utilize sub-directories as users narrow down their selection. What is the best practice here for maximizing your SERP authority? Choice #1 - Hyphenated Architecture (no sub-folders): State Page /state/ City Page /city-state/ Business Page /business-city-state/
Intermediate & Advanced SEO | | knowyourbank
4) Location Page /locationname-city-state/ or.... Choice #2 - Using sub-folders on drill down: State Page /state/ City Page /state/city Business Page /state/city/business/
4) Location Page /locationname-city-state/ Again, just to clarify, I need help in determining what the best methodology is for achieving the greatest SEO benefits. Just by looking it would seem that choice #1 would work better because the URL's are very clear and SEF. But, at the same time it may be less intuitive for search. I'm not sure. What do you think?0