Would you rate-control Googlebot? How much crawling is too much crawling?
-
One of our sites is very large - over 500M pages. Google has indexed 1/8th of the site - and they tend to crawl between 800k and 1M pages per day.
A few times a year, Google will significantly increase their crawl rate - overnight hitting 2M pages per day or more. This creates big problems for us, because at 1M pages per day Google is consuming 70% of our API capacity, and the API overall is at 90% capacity. At 2M pages per day, 20% of our page requests are 500 errors.
I've lobbied for an investment / overhaul of the API configuration to allow for more Google bandwidth without compromising user experience. My tech team counters that it's a wasted investment - as Google will crawl to our capacity whatever that capacity is.
Questions to Enterprise SEOs:
*Is there any validity to the tech team's claim? I thought Google's crawl rate was based on a combination of PageRank and the frequency of page updates. This indicates there is some upper limit - which we perhaps haven't reached - but which would stabilize once reached.
*We've asked Google to rate-limit our crawl rate in the past. Is that harmful? I've always looked at a robust crawl rate as a good problem to have.
- Is 1.5M Googlebot API calls a day desirable, or something any reasonable Enterprise SEO would seek to throttle back?
*What about setting a longer refresh rate in the sitemaps? Would that reduce the daily crawl demand? We could set increase it to a month, but at 500M pages Google could still have a ball at the 2M pages/day rate.
Thanks
-
I agree with Matt that there can probably be a reduction of pages, but that aside, how much of an issue this is comes down to what pages aren't being indexed. It's hard to advise without the site, are you able to share the domain? If the site has been around for a long time, that seems a low level of indexation. Is this a site where the age of the content matters? For example Craigslist?
Craig
-
Thanks for your response. I get where you're going with that. (Ecomm store gone bad.) It's not actually an Ecomm FWIW. And I do restrict parameters - the list is about a page and a half long. It's a legitimately large site.
You're correct - I don't want Google to crawl the full 500M. But I do want them to crawl 100M. At the current crawl rate we limit them to, it's going to take Google more than 3 months to get to each page a single time. I'd actually like to let them crawl 3M pages a day. Is that an insane amount of Googlebot bandwidth? Does anyone else have a similar situation?
-
Gosh, that's a HUGE site. Are you having Google crawl parameter pages with that? If so, that's a bigger issue.
I can't imagine the crawl issues with 500M pages. A site:amazon.com search only returns 200M. Ebay.com returns 800M so your site is somewhere in between these two? (I understand both probably have a lot more - but not returning as indexed.)
You always WANT a full site crawl - but your techs do have a point. Unless there's an absolutely necessary reason to have 500M indexed pages, I'd also seek to cut that to what you want indexed. That sounds like a nightmare ecommerce store gone bad.
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
-
How do I know if I am correctly solving an uppercase url issue that may be affecting Googlebot?
We have a large e-commerce site (10k+ SKUs). https://www.flagandbanner.com. As I have begun analyzing how to improve it I have discovered that we have thousands of urls that have uppercase characters. For instance: https://www.flagandbanner.com/Products/patriotic-paper-lanterns-string-lights.asp. This is inconsistently applied throughout the site. I directed our website vendor to fix the issue and they placed 301 redirects via a rule to the web.config file. Any url that contains an uppercase character now displays as a lowercase. However, as I use screaming frog to monitor our site, I see all these 301 redirects--thousands of them. The XML sitemap still shows the the uppercase versions. We have had indexing issues as well. So I'm wondering what is the most effective way to make sure that I'm not placing an extra burden on Googlebot when they index our site? Should I have just not cared about the uppercase issue and let it alone?
Intermediate & Advanced SEO | | webrocket0 -
Move domain to new domain, for how much time should I keep forwarding?
I'm not sure but my website looks like is not getting it's juice as supposed to be. As we already know, google preferred https sites and this is what happened to mine, it was been crawling as https but when the time came to move my domain to new domain, I used 301 or domain forwarding service, unfortunately they didn't have a way to forward from https to new https, they only had regular http to https, when users clicked to my old domain from google search my site was returned to "site does not exist", I used hreflang at least that google would detect my new domain been forwarding and yes it worked but now I'm wondering, for how much time should I keep the forwarding the old domain to the new one, my site looks like is not going up, I have changed all the external links, any help would be appreciated. Thanks!
Intermediate & Advanced SEO | | Fulanito1 -
Best way to link to 1000 city landing pages from index page in a way that google follows/crawls these links (without building country pages)?
Currently we have direct links to the top 100 country and city landing pages on our index page of the root domain.
Intermediate & Advanced SEO | | lcourse
I would like to add in the index page for each country a link "more cities" which then loads dynamically (without reloading the page and without redirecting to another page) a list with links to all cities in this country.
I do not want to dillute "link juice" to my top 100 country and city landing pages on the index page.
I would still like google to be able to crawl and follow these links to cities that I load dynamically later. In this particular case typical site hiearchy of country pages with links to all cities is not an option. Any recommendations on how best to implement?0 -
Google Webmaster tools -Fixing over 20,000+ crawl errors
Hi, I'm trying to gather all the 404 crawl errors on my website after a recent hacking that I've been trying to rectify and clean up. Webmaster tools states that I have over 20 000+ crawl errors. I can only download a sample of 1000 errors. Is there any way to get the full list instead of correcting 1000 errors, marking them as fixed and waiting for the next batch of 1000 errors to be listed in Webmaster tools? The current method is quite timely and I want to take care of all errors in one shot instead of over a course of a month.
Intermediate & Advanced SEO | | FPK0 -
Download all GSC crawl errors: Possible today?
Hey guys: I tried to download all the crawl data from Google Search Console using the API and solutions like this one: https://github.com/eyecatchup/php-webmaster-tools-downloads but seems that is not longer working (or I made something wrong, I just receive a blank page when running the PHP file after some load time)... I needed to download more than 1.000 URLs long time ago, so I didn't tried to use this method since then. Is there any other solution using the API to grab all the crawl errors, or today this is not possible anymore? Thanks!
Intermediate & Advanced SEO | | antonioaraya1 -
Click Through Rate on Password Protected Pages
Hi Moz community, I have a website that has a large database with 800+ important pages, and want Google to know when people visit and stay on these pages. However, these pages are only accessible to people once they create an account with a password, and sign in. I know that since these pages are password protected, Google doesn't index them, but when our visitors stay for a while on our site browsing through our database, does this data get included in our CTR and Bounce Rate by Google? This is really important for Google to know about our database (that people are staying on our site for a while) for SEO purposes, so I wanted to know that if the CTR gets measured even though these pages aren't crawled. Thanks for the help!!
Intermediate & Advanced SEO | | danstern0 -
Block Googlebot from submit button
Hi, I have a website where many searches are made by the googlebot on our internal engine. We can make noindex on result page, but we want to stop the bot to call the ajax search button - GET form (because it pass a request to an external API with associate fees). So, we want to stop crawling the form button, without noindex the search page itself. The "nofollow" tag don't seems to apply on button's submit. Any suggestion?
Intermediate & Advanced SEO | | Olivier_Lambert0 -
Would spiders successfully crawl a page with two distinct sets of content?
Hello all and thank you in advance for the help. I have a coffee company that sell both retail and wholesale products. These are typically the same product, just at different prices. We are planning on having a pop up for users to help them self identify upon their first visit asking if they are retail or wholesale clients. So if someone clicks retail, the cookie will show them retail pricing throughout the site and vice versa for those that identify themselves as wholesale. I can talk to our programmer to find out how he actually plans on doing this from a technical standpoint if it would be of assistance. My question is, how will a spider crawl this site? I am assuming (probably incorrectly) that whatever the "default" selection is (for example, right now now people see retail pricing and then opt into wholesale) will be the information/pricing that they index. So long story short, how would a spider crawl a page that has two sets of distinct pricing information displayed based on user self identification? Thanks again!
Intermediate & Advanced SEO | | ClayPotCreative0