Copy the formatted transcript to paste into ChatGPT or Claude for analysis
Have you ever wondered where your brand was being cited when it comes to AI Search? Maybe you're not really sure what to make of all the data and you're not sure if you can trust all the different sources out there and wish you had a little bit more control over that data retrieval. Well, leveraging SE Rankings API, you can actually do some pretty awesome AI Search discovery and understand even where your competitors stack up against. In this video, that's exactly what we're going to cover. All right, so one of the most important things for SEOs and content marketers and businesses to understand today is how is their brand being cited within AI Search. Now, a lot of the big SEO tools are coming out with a number of ways to pull that information and some of it can be very, very expensive. But also, you know, you may want to have a little bit more flexibility in how you run these queries. And this is where leveraging APIs can be extremely helpful. So in this video, we're going to talk about how we can leverage SE Rankings API to pull some pretty amazing AI SEO research. So the first thing you need to do is make sure that you have an active SE Ranking account and an API key. If you don't, you can just click on this link and follow the guide and it will set up your API key with you. In this video, we're going to be looking at the Data API, not the Projects API. There's two different types of APIs. One will pull data from your specific projects. The other will pull from the database of what they have as far as like search rankings, things like that. You can also use the API within other integrations, maybe Looker Studio, you can use their MCP, which is pretty stinking cool. If you haven't gotten into that yet, you can use it in N8n or MADE to create your own workflows. But in this video, we're going to be talking specifically about creating our own Python applications within Google Colab, and how we can leverage those to pull the data that we need. Now, if you don't know anything about Colab, that's fine. Honestly, thanks to the growth of LLMs and the knowledge that these tools have to help build tools, as well as people that can share templates, I'll be sharing this template with you, you can do some pretty cool stuff without really knowing it fully. But I would recommend that you learn it because it can be extremely helpful. Alright, so what do we need to do? The first thing we need to do anytime we're running in Python is we need to make sure that we have all of the setup done correctly. A couple things that we need to do, we need to import requests, and we need to import pandas. This is going to allow us one to call the API key here, and then to to basically organize and work with our data. We also want to pull our our API key in from secrets, we have those under secrets here, that way we don't share our API keys, and we can still run the necessary calls. Now, once we have all of that set up, we've got the right headers, basically saying, hey, this is what we want you to be doing. Here's where you find our key, all that fun stuff, we can start to build our functions. Now, each one of these functions is going to do something specifically for us. So for instance, we're looking here at just two different engines right now, AI mode and AI overview, but you can also look at perplexity, you can look at chat GPT, you can look at Gemini, those are going to use a lot more API calls. So for this video, I just wanted to look at a couple basic ones, and ones that are honestly still extremely important, especially for SEOs. So what we're trying to do here is give it a list of brands and a list of engines, like we talked about AI overview, and AI mode here. And then we're saying this is where we want the information from, and what we're actually looking for. So we want brand sources, we want the engine, we want the volume that's going to come back for that specific AI overview query. And then we've also set a limit to 50. This way, we are not just overusing our API, but we're getting kind of the top 50 queries that these brands are being mentioned for. This is basically the function how it's doing that, and then it's going to return them all to the database. So we can run this cell here. I've already run it. So everything's kind of live right now. And if we want to just test it out really, really quick, I do have a little test thing here, which we can do. I'll just drop it in and test it. You can see that it's using this function up here. It's fetching all the different prompts for this brand name with an AI mode and AI overview. We're limiting it to 10 in this case, just to kind of give the idea of how this works. It's doing all of it in the background for you. You can kind of hit that button. And here after a few minutes, we've got the prompts, we've got the potential volume for the prompts, the type of search that we made, the brand that was found, and the engine we searched on, and the source. It also gives us the answer here. The reason why we're getting zero here is there's really no traffic for AI mode, but we can get traffic for AI overview because SE ranking attaches our keyword volume data to those specific prompts. All right. So with one, it's very helpful to understand where we rank, but it's also helpful to understand where our competitors rank and do we compete well against them. So again, we're going to need a new function. We've got both our brand as well as the competitors. We've got the engines that we talked about. We're looking in the US, we're limiting to 50. So we're setting our parameters. From there, we're asking it again to call the API and return this information and all the different information that we want. If we've got volume, making sure that they're grouped by the brands, things of that nature. Now, once we have this, we can put a little bit more data into a full prompt like this to run all of the information. So you can put our brand here, then we can put some competitors that we want to look at. These are all competitors within the carbon fiber manufacturing space. We want to look at these engines specifically. Again, you can swap these out with chat GPT, Gemini, perplexity, and then we're asking it to run those functions we called. So run all the prompts, do the brand summary, do the engine summary, and then I want you to compare the brands versus the competitors. So it's going to run all this analysis and it's going to give us this really cool chart here. It found for each of these brands, 100 prompts, 100 prompts, and 29 prompts in a total volume of 34,000, 6,000, 1,000. Then it also breaks down how many prompts did it find by engine or by group. So we have a lot of coverage here by Dragonplate, middle coverage by Elevated, and a lot of coverage again by Rockwest. Now, let's say you wanted to know the exact prompts that we were pulling for. Well, the cool part about this is it also will store that in this brand versus competitor data sheet right here. So you can pull up this sheet after you download it and you've got this rich sheet of information and you can see what are the prompts that your brand is showing up for and what are the prompts your competitors are showing up for. You can also analyze this to see, hey, where are some of the gaps? What are maybe some things that they're showing up for that we're not showing up for? And that's as easy as putting in some filters, right? So let's say we want to look at just AI overviews and then we want to sort this ascending, right? And we see, okay, Adhesive Carver, we show up. Aluminum Honeycomb Suppliers, they're showing up, but we're showing up for Aluminum Versus Supplier. So maybe this is a term we target. We got to look at volume, some of the other things there as well. But now we've got a list of the queries and prompts that we're showing up for, as well as a list of prompts and queries that our competitors are showing up for. And now we can begin to build out a strategy that will allow us to hopefully increase our visibility on these platforms. Honestly, this whole thing took me three minutes to run when I just ran it solely. That's where you put some of those limitations in there with making sure that you're not just going for an infinite number of queries and running out of your API keys. All of this is coming for honestly, not a lot of work and a lot cheaper than using a tool from like Ahrefs or SEMrush. And you get more control because you get to do what you want with the API calls here. I think this is a really cool tool. It's something that we're using just to help give us more information and build strategies that make sense in the world of GEO and AISEO and more. If you've got any more questions or you want to try it out, you can actually sign up for a 14-day free trial. We've got a link below. SE Ranking was really grateful in giving that to our viewers here. But if you have run into any questions or the Python here, this script is maybe not working for you, just let me know. But I'm going to show you one last thing. Now, this is very important. When I've shared Colabs before, people forget to do this. What you need to do is you need to go to File, and then you need to go Save a Copy in My Drive. That is the only way you're going to be able to run this in your own drive. So you would save it as a copy in your drive. I'm going to show you exactly what it does. It's creating that copy, and I'm going to open this in a new tab. The next thing you need to do to make sure that this works is you need to go over here where the keys are, and you need to create your key and create it exactly like I have it here, SE Ranking. Then put your API key right here where it says Value, and then turn this on so it has access to the notebook. If you don't do this, none of what I just showed you will work. So this is extremely, extremely important if you want to test this out on your own. Like I said, if you have any questions, let me know. And until next time, happy marketing. Transcribed by https://otter.ai
Python script + Google Colab template

Ahrefs