What are you trying to achieve?
hello guys, i hope some solution for my issues
I have set up a Make.com scenario to automate the retrieval and processing of newsletters in order to extract the most relevant financial news.
The scenario works as follows:
1Retrieves the 10 latest emails from Outlook (ID: 35).
2. Converts the HTML content into plain text using HTML to Text (ID: 33).
3. Aggregates the cleaned emails using Text Aggregator (ID: 37).
4. Processes the aggregated content with Gemini AI (ID: 14) to extract the 4 most relevant news items related to finance, wealth management, and investment.
5. Stores the final results in the same Google Docs file (ID: 34).
Problem Encountered
- HTML Elements Not Fully Removed
- Despite using the HTML to Text module, some images and links remain in the text. This makes the final content cluttered and difficult to read.
- Is there a better way to fully remove all HTML elements while keeping the text clean?
- Overlapping Text in Google Docs
- All emails are stored in one Google Docs file, and once sent to Gemini, the AI-generated summary is also stored in the same document.
- This results in a mix of raw emails and AI-generated content, making the document overloaded with text and links.
- How can I structure the output to separate raw emails from the final Gemini summary more effectively?
What I need help with
- A better way to filter out all unnecessary HTML elements before processing the text.
- A method to organize the document structure so the email content and Gemini’s generated summaries do not mix in the same document.
- Any alternative approaches that have worked for similar automation workflows.
Screenshots
scenario:
Html to text :
Text agragator :
Thanks in advance for your help!