The challenge
Sponsorscout faced the challenge of automating web crawling to find newsletters, podcasts, events, and other sponsored content from a diverse range of organizations. Turning thousands of newsletters, watching tons of videos, and keeping track ofcountless events would consume unimaginable man-hours and prove unsustainable. They sought an automated mechanism that could deliver exact results in minimal time, with reduced costs and efforts.
Process
- We initiated the content aggregation process using the Feedly API. This versatile API enabled the automatic extraction of a multitude of newsletters, podcasts, events, and digital content from various sources.
- With the content in hand, we introduced Google Vision API, a robust image analysis tool. It meticulously detected and interpreted elements within images and videos, enhancing our ability to identify sponsor mentions within visual content.
- Google OCR was employed to convert textual information from images and scanned documents into machine-readable text. This tool facilitated text-based analysis and the extraction of valuable information from visual content.
- Google Entity Recognition further enriched the extracted data. It intelligently recognized and categorized entities like names, dates, and locations within the text, enhancing the overall accuracy and structure of the information.
- To fortify the database, we integrated the Crunchbase API. This versatile API provided access to comprehensive information about companies, funding rounds, leadership teams, and more. It empowered us to incorporate accurate and up-to-date company data into the database.
- The n8n Workflow Automation platform allowed us to seamlessly connect and coordinate the various applications, services, and APIs involved in the workflow.
- The extracted and organized data found its home in Airtable, ensuring easy accessibility, storage, and collaboration on the amassed information.
Outcome
With the n8n and make.com automation, our client achieved a continuous and ever-growing list of sponsors from across the web. The data was stored in Airtable, making it universally applicable and allowing easy access and analysis
Conclusion
Using n8n combined with other powerful tools such as Feedly and Google OCR proved to be a game-changer for gosponsorscout.com. Complex and labor-intensive tasks were
effortlessly automated, providing a comprehensive and accurate database of sponsors. The capabilities of n8n and make.com are vast, empowering us to create tailored automations for
countless use cases, meeting the diverse needs of our clients. If you are looking forward to automating tasks involving an organized and structured approach to data, we can help you with our immense expertise with these tools.