LEAD GENERATION

Harvest Guest Sites from Podcast Show Notes into Airtable

Crawls a list of podcast episode pages, extracts each guest's name, company, and personal website from the show notes.

CategoryLead Generation
Enginesim
Difficultybeginner
Triggerschedule
Steps5
Setup~5 min

How it runs

The automated pipeline, trigger to output.

  • TriggerWeekly schedule fires with episode URL list
  • ActionScrape each show-notes page to markdownFirecrawl
  • ActionExtract guest name, company, and websiteOpenAI
  • LogicDrop rows with no site or duplicate domain
  • OutputWrite unique guests as prospect rowsAirtableAirtable

What it does

Given a list of podcast episode URLs, this workflow scrapes each show-notes page, pulls out the guest's name, company, and outbound website link, and writes one row per guest into an Airtable prospecting base. It dedupes against sites you've already captured so the base stays clean.

When to use it

Run this when you've identified a few relevant podcasts in your niche and want to turn their back catalog of episodes into a structured list of guest websites worth pitching for a backlink or guest post.

How it works

  1. 1A scheduled run fires weekly (or on demand) with the configured list of episode URLs.
  2. 2Firecrawl scrapes each episode page and returns clean markdown of the show notes.
  3. 3An OpenAI extraction step parses the markdown into structured fields: guest name, company, role, and primary website URL.
  4. 4A logic step filters out rows with no website and drops any domain already present in the base.
  5. 5Airtable receives each surviving guest as a new prospect row, tagged with the source podcast and episode.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect FirecrawlCrawl, scrape, structured extract.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect AirtableBases, tables, views, automations.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.