Most people subscribe to more newsletters than they read. Industry digests, research publications, competitor updates — they arrive as PDFs in Gmail, get marked as read, and pile up. The ones that do get read take 20-30 minutes each to properly extract anything useful from.
Built a workflow that watches Gmail for PDF newsletters, reads each one automatically, and posts a structured digest to Slack — topics covered, key stories summarized, stats pulled out, trends identified — without opening a single PDF.
What it does
PDF newsletter arrives in Gmail → checks for PDF attachment → extracts the PDF → analyzes content → formats digest → logs to newsletter library → posts to Slack
Checks Gmail every hour. Takes about 12-15 seconds to process each newsletter.
Smart attachment detection
The workflow includes an IF node that checks whether the email actually has a PDF attachment before doing anything. Non-PDF emails or emails without attachments are filtered out automatically — only genuine PDF newsletters proceed.
The Code node finds the first PDF in the email’s binary attachments regardless of how the attachment is named, so it works even when the filename isn’t predictable.
What gets extracted
Uses PDF Vector’s Ask operation with a structured prompt that returns five sections:
-
Document info — what is it, who published it
-
Main topics — 3-5 primary subjects covered
-
Key stories — 2-3 most important stories or sections, 1-2 sentences each
-
Stats and data — specific numbers and data points mentioned
-
Trends — emerging themes the document highlights
What lands in Slack
📰 Newsletter PDF Digest
From: McKinsey & Company
Subject: McKinsey Technology Trends Report Q1 2025
File: mckinsey-tech-trends-q1-2025.pdf
---
📋 Topics Covered:
AI adoption in enterprise, semiconductor supply chain,
cybersecurity spending, cloud infrastructure consolidation,
workforce automation impact
---
📖 Key Stories:
Enterprise AI deployment accelerated significantly — 67% of
Fortune 500 companies now run at least one production AI system,
up from 41% in 2023. The report identifies integration complexity
as the primary bottleneck, not talent or budget.
Semiconductor supply chain diversification is reshaping vendor
relationships — companies that built dual-sourcing strategies in
2022-2023 report 40% fewer disruption incidents.
---
📊 Stats & Data:
• 67% of Fortune 500 have production AI systems
• AI project failure rate: 42% before production
• Average cloud spend per enterprise: $14.2M annually
• Cybersecurity budgets up 23% YoY
---
📈 Trends:
Shift from AI experimentation to AI operations maturity.
Supply chain regionalization accelerating. Security spending
outpacing IT budget growth for third consecutive year.
What lands in Google Sheets
Each row: Newsletter, Subject, Sender, Received Date, Topics, Key Stories, Stats & Data, Trends, Full Analysis, Processed Date
Your entire newsletter archive in one searchable sheet. Filter by Newsletter to see all issues from one publication. Search Topics column for specific subjects across all newsletters.
Setup
You’ll need:
-
Gmail (where PDF newsletters arrive)
-
Google Sheets (free)
-
n8n instance (self-hosted — uses PDF Vector community node)
-
PDF Vector account (free tier: 100 credits/month)
-
Slack (for digest sharing)
About 15 minutes to configure.
Download
Workflow JSON:
Full workflow collection:
Setup Guide
Step 1: Get your PDF Vector API key
Sign up at pdfvector.com — free plan works for testing. Go to API Keys and generate a key.
Step 2: Create your Google Sheet
Headers in Row 1:
Newsletter | Subject | Sender | Received Date | Topics | Key Stories | Stats & Data | Trends | Full Analysis | Processed Date
Step 3: Import the workflow
Download JSON from GitHub → n8n → Import from File.
Step 4: Configure the nodes
Gmail Trigger:
-
Connect Gmail account (OAuth2)
-
Polls every hour by default — change to
everyMinutefor real-time processing -
Add a Gmail filter in the search query to target specific senders if needed:
-
from:([email protected]) has:attachment -
has:attachment filename:pdffor all PDF emails
Has PDF Attachment?:
- No config needed — automatically filters emails without PDF attachments
Extract PDF Attachment:
- No config needed — finds first PDF attachment regardless of filename
PDF Vector - Analyze Content:
-
Add new credential (Bearer Token)
-
Paste your API key
-
Uses Ask operation with structured 5-section prompt
Format Analysis:
- No config needed — parses the 5 sections automatically
Log Newsletter:
-
Connect Google Sheets
-
Paste your Sheet ID
Share Digest:
-
Connect Slack
-
Select your content or digest channel
Step 5: Test it
Send yourself an email with a PDF newsletter attached. Check Slack and your Sheet within the next polling cycle.
Accuracy
Tested on industry newsletters, research digests, and PDF reports from consulting firms and media companies.
-
Topics and trends: ~92% — Ask operation reliably identifies main themes
-
Key story summaries: ~90% — quality depends on how structured the newsletter is
-
Stats and data extraction: ~87% — reliable for clearly stated numbers; misses data embedded in charts
-
Document identification: ~95% — publisher name and document type extract reliably
Works best on text-heavy PDF newsletters. Newsletters that are primarily images or infographics will have lower accuracy.
Cost
Each newsletter uses 3-4 PDF Vector credits. Free tier of 100 credits handles roughly 25-30 newsletters per month — enough for a heavy newsletter subscriber.
Customizing it
Filter to specific senders:
In the Gmail Trigger search query, add from:(specificdomain.com) to only process newsletters from sources you care about.
Route by topic to different channels:
Add a Switch node after Format Analysis that checks the topics field for keywords — AI newsletters go to #ai-updates, finance newsletters go to #market-intel, etc.
Weekly digest rollup:
Build a companion workflow that reads your Sheets library every Friday and posts a summary of all newsletters processed that week — one Slack message with all the week’s key stories and stats in one place.
Keyword alerts:
Add an IF node that checks whether the topics or trends contain specific keywords (e.g., “your company name”, “competitor name”) and routes those to a separate urgent channel.
Limitations
-
Requires self-hosted n8n (PDF Vector is a community node)
-
Polls Gmail hourly by default — not real-time unless changed to every minute
-
Only processes the first PDF attachment per email — multiple attachments need extra handling
-
Image-heavy or infographic newsletters extract poorly
-
Section parsing depends on the AI returning consistent section headers — occasionally needs manual review
Questions? Drop a comment.