SplitInBatches Automate streamlines the extraction and processing of EU legislative procedures, filtering for sustainability-related topics. It collects data from web pages, evaluates relevance using AI, and organizes findings into Google Sheets while creating actionable tasks in Google Tasks. This workflow enhances efficiency, ensuring that critical sustainability issues are prioritized and easily accessible.
- Legislative Analysts: Professionals who analyze EU legislation and need to track sustainability-related documents efficiently.
- Environmental Advocates: Individuals or organizations focused on sustainability who require timely updates on relevant legislative procedures.
- Project Managers: Those managing sustainability projects who want to stay informed about new legislation affecting their work.
- Data Analysts: Analysts who need to extract and process data from legislative documents for reporting or research.
- Automation Enthusiasts: Users looking to automate data collection and task management processes using n8n.
- Inefficiency in Data Collection: Automates the extraction of legislative documents, reducing manual effort and time.
- Relevance Filtering: Uses AI to filter out non-sustainability-related documents, ensuring users only receive pertinent information.
- Task Management: Integrates with Google Tasks to create actionable items based on relevant legislation, helping users stay organized and proactive.
- Data Recording: Automatically records sustainability-related procedures in Google Sheets for easy access and tracking.
1. Manual Trigger: The workflow starts when a user clicks 'Test workflow' to initiate the process.
2. Extract Yesterday Records: An HTTP request collects legislative documents from the EU Parliament's website for the previous day.
3. Extract HTML Blocks: The HTML response is parsed to extract relevant sections containing legislative information.
4. Parse Blocks: Each block is analyzed to extract specific details such as Reference Number, Committee, Rapporteur, Title/Description, PDF Link, and Date.
5. Edit Links: The PDF links are formatted for accessibility.
6. Loop Over Items: Each legislative document is processed individually to determine its relevance to sustainability.
7. Classification Agent: An AI model assesses each document, returning a 'yes' or 'no' answer regarding its sustainability relevance.
8. Collect Answer: The AI's response is recorded for further processing.
9. Merge: The results are combined for documents that are related to sustainability.
10. If Condition: A conditional check filters out non-relevant documents, allowing only those related to sustainability to proceed.
11. Record Sustainability Procedures: Relevant documents are recorded in Google Sheets for future reference.
12. Create Google Tasks: For each relevant document, a task is created in Google Tasks, scheduled for the following day at 09:00 AM.
- Modify the HTTP Request URL: Change the URL in the 'Extract Yesterday Records' node to target different data sources or adjust the date range.
- Adjust CSS Selectors: Update the CSS selectors in the 'Parse Blocks' node to extract additional or different data fields from the HTML response.
- Change AI Model Parameters: In the 'Classification Agent' node, users can select different AI models or modify the prompt to refine the relevance assessment based on their specific needs.
- Customize Google Sheets Mapping: In the 'Record Sustainability Procedures' node, adapt the mapping of fields to match the structure of the target Google Sheet.
- Task Scheduling: Change the timing of Google Tasks in the 'Google Tasks' node to suit personal or team schedules.