Siemens Document PDF Parser — Specs JSON

Crawloop Siemens Automation Suite — Structured data extraction for Siemens SiePortal (Industry Mall), SIOS, and TED product datasheets. Built for procurement teams, system integrators, and BOM engineering workflows.

Discovery	Enrichment	SIOS documents	PDF parsing
Catalog Crawler	SiePortal Scraper	Document Downloader	Document PDF Parser ◄── you are here
	Lifecycle Tracker

Disclaimer: This is an unofficial integration developed independently of Siemens AG. It is not affiliated with, sponsored by, or endorsed by Siemens AG or any of its subsidiaries.

Siemens, SiePortal, SIMATIC, and related names are trademarks of Siemens AG. Product data is read from publicly accessible Siemens web sources only; no proprietary databases are redistributed.

This Actor is provided for informational and research purposes only (e.g. procurement research, BOM audits, internal engineering workflows). You are solely responsible for ensuring your use complies with applicable laws, Siemens website terms of use, and your organization's policies.

No warranty is given as to accuracy, completeness, or continued availability of third-party data. Use at your own risk.

Siemens SIOS PDF parser — parse Siemens documents into structured JSON: specifications, tables, limits, and diagrams. Chain after Document Downloader (Key-Value Store keys) or provide file references. Use from Python, Node.js, or MCP.

When to use this Actor

Use the Siemens Document PDF Parser when you have SIOS PDFs in Key-Value Store (from Document Downloader) and need structured JSON from PDF content.

For web PDP specifications without PDF parsing, use Siemens SiePortal Scraper. For TED catalog datasheets, use Siemens Datasheet PDF Crawler.

Key Features

• PDF → JSON — Specs, tables, limits, diagrams
• KV Store input — Chain after Document Downloader
• Parse status — PARSED / PARTIAL / FAILED visibility
• Browser-free parsing — No SiePortal session required for parse-only mode

Input Parameters

Parameter	Description	Default
keyValueStoreId	Store ID from Document Downloader run.	—
items	List of partNumber + keyValueStoreKey / fileName.	—
extractDiagrams	Extract diagram metadata.	false
maxConcurrency	Parallel parse workers.	—

Input Example

{
  "keyValueStoreId": "YOUR_DOCUMENT_DOWNLOADER_STORE_ID",
  "items": [{
    "partNumber": "6ES7193-6BP00-0DA0",
    "keyValueStoreKey": "6ES7193-6BP00-0DA0_manual.pdf",
    "fileName": "6ES7193-6BP00-0DA0_manual.pdf"
  }],
  "extractDiagrams": false,
  "maxConcurrency": 3
}

Output Format

{
  "partNumber": "6ES7193-6BP00-0DA0",
  "fileName": "6ES7193-6BP00-0DA0_manual.pdf",
  "status": "PARSED",
  "pageCount": 48,
  "tableCount": 12,
  "specificationCount": 85,
  "diagramCount": 0,
  "parsedAt": "2026-08-03T12:00:00Z"
}

Use cases

Use case	What you get
Document digitization	Specs/tables as JSON
Compliance extraction	Structured limits from certificates/manuals
BOM / PLM enrichment	Parsed attributes from SIOS PDFs
AI / MCP workflows	Run via Apify API, clients, or MCP

Integration examples

Node.js

import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: process.env.APIFY_TOKEN });
const run = await client.actor('crawloop/siemens-sieportal-product-datasheet-pdf-crawler').call({{ keyValueStoreId: 'YOUR_STORE_ID', items: [{{ partNumber: '6ES7193-6BP00-0DA0', keyValueStoreKey: '6ES7193-6BP00-0DA0_manual.pdf', fileName: '6ES7193-6BP00-0DA0_manual.pdf' }}], extractDiagrams: false, maxConcurrency: 3 }});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items.slice(0, 5));

Python

from apify_client import ApifyClient

client = ApifyClient(token)
run = client.actor("crawloop/siemens-sieportal-product-datasheet-pdf-crawler").call(
    run_input={{"keyValueStoreId": "YOUR_STORE_ID", "items": [{"partNumber": "6ES7193-6BP00-0DA0", "keyValueStoreKey": "6ES7193-6BP00-0DA0_manual.pdf", "fileName": "6ES7193-6BP00-0DA0_manual.pdf"}], "extractDiagrams": False, "maxConcurrency": 3}}
)
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item.get("partNumber"), item.get("specificationCount"), item.get("status"))

cURL

curl "https://api.apify.com/v2/acts/crawloop~siemens-sieportal-product-datasheet-pdf-crawler/runs?token=$APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"keyValueStoreId":"YOUR_STORE_ID","items":[{"partNumber":"6ES7193-6BP00-0DA0","keyValueStoreKey":"6ES7193-6BP00-0DA0_manual.pdf","fileName":"6ES7193-6BP00-0DA0_manual.pdf"}],"extractDiagrams":false,"maxConcurrency":3}'

MCP and AI assistants

Use this Actor from AI tools via Apify MCP. Connect your Apify account, then call crawloop/siemens-sieportal-product-datasheet-pdf-crawler.

Example prompts:

• "Parse Siemens SIOS PDFs from this Key-Value Store and return specificationCount and status"
• "Run Siemens Document PDF Parser after Document Downloader for these MPNs"
• "Chain Document Downloader then Document PDF Parser for 6ES7193-6BP00-0DA0"

Suite next step

Start downloads with Siemens Document Downloader. For TED datasheets, use Siemens Datasheet Downloader then Siemens Datasheet PDF Crawler.

Related Actors — Siemens Automation

Focus	Actor
Discover Siemens MPNs	Siemens Catalog Crawler
Bulk lifecycle / successors	Siemens Lifecycle Tracker
Full SiePortal PDP specs	Siemens SiePortal Scraper
Download SIOS PDFs	Siemens Document Downloader
Parse SIOS PDFs to JSON	Siemens Document PDF Parser ◄── you are here
TED datasheet download	Siemens Datasheet Downloader
TED datasheet parse	Siemens Datasheet PDF Crawler