Extract Bills of Lading into structured JSON and CSV.

Parses container IDs, notify parties, and HS codes from carrier paperwork. Review the extracted data, then download CSV, JSON, or Excel for downstream logistics work.

View supported formats ->
EXTRACTION_MONITOR v2.1.0
READY
Source_File.pdf
BILL OF LADING
MSC MEDITERRANEAN SHIPPING CO.
B/L Number
MSCU9872341-001
Shipper
ACME MANUFACTURING CO LTD
Container
MSCU 987234-1
Type 40HC Weight 28,459 KG
Consignee
GLOBAL IMPORTS INC
BOL_MSCU9872341.pdf 
// Extracted BOL Data
{
  "bl_number": "MSCU9872341-001",
  "container_id": "MSCU9872341" ✓ valid
  "container_valid": true,
  "type": "40HC",
  "weight_kg": 28459,
  "shipper": "ACME Manufacturing Co.",
  "consignee": "Global Imports Inc.",
  "port_load": "CNSHA",
  "port_discharge": "USLGB"
}
bl_number,container_id,type,weight_kg,shipper,consignee
MSCU9872341-001,MSCU9872341,40HC,28459,"ACME Manufacturing","Global Imports"
// Reviewed export package
{
  "formats": ["json", "csv", "xlsx"],
  "review_status": "checked",
  "low_confidence_fields": 0
}

READY FOR EXPORT
COMPATIBLE_CARRIERS
MAERSK MSC CMA CGM +40 more
LINE_ITEMS
01 Electronics 1,200 KG
02 Textiles 850 KG

Line Item Extraction

Autodetects running lists of goods, weights, and seal numbers.

VALIDATION
MSCU 123456-7 VALID
Check Digit: OK · ISO 6346

ISO 6346 Validation

We checksum every container ID against ISO standards to prevent errors.

EXPORTS
CSV JSON XLSX

Export package

Download reviewable files for the systems your team already uses.

PROCESSING_PIPELINE

How It Works

STAGE_01 // INGEST
UPLOAD_QUEUE 3 files
bol_maersk_001.pdf
scan_invoice_44.jpg
packing_list.jpg

Multi-Channel Capture

Upload PDF, PNG, JPEG, or WebP files through the workstation for review.

STAGE_02 // EXTRACT
ocr_engine.log
CHECK
> Detecting tables... OK
> Validating IDs... OK
> Mapping schema... OK
✓ Extraction complete

OCR + Logic Validation

Maps unstructured pixels to structured JSON schemas.

STAGE_03 // SYNC
QA
Review low-confidence fields
HUMAN CHECK
AVAILABLE
JSON
JSON + XLSX exports
AUTHENTICATED DOWNLOAD
AVAILABLE

Review & Exports

Review extracted fields, then download JSON and XLSX exports for downstream logistics work.

SCHEMA_CATALOG

Supported Document Types

Bill of Lading

REVIEWABLE
EXTRACTED_ENTITIES:
Shipper Consignee Container_ID Gross_Weight Port_Codes
Ocean BOL • House BOL • Sea Waybill
Review fields →

Commercial Invoice

REVIEWABLE
EXTRACTED_ENTITIES:
Line_Items Unit_Price Incoterms Currency Total_Value
FOB • CIF • EXW • DDP
Review fields →

Packing List

REVIEWABLE
EXTRACTED_ENTITIES:
Carton_No Dimensions Net_Weight HS_Code CBM
Full Container • LCL • Palletized
Request schema review →

Air Waybill

REVIEWABLE
EXTRACTED_ENTITIES:
MAWB_No HAWB_No Flight_Route Chargeable_Wt
IATA • e-AWB • Consolidated
Review fields →

Customs Declaration

REVIEWABLE
EXTRACTED_ENTITIES:
HS_Code Duty_Rate Country_Origin CIF_Value
CBP 7501 • ISF • Entry Summary
Request schema review →

Delivery Note / POD

REVIEWABLE
EXTRACTED_ENTITIES:
Signature Timestamp Status Receiver_Name
ePOD • Signed • GPS Verified
Request schema review →
BENCHMARK_MATRIX

Extraction Method Analysis

Operational tradeoffs across document processing approaches.

Metric Manual Entry Legacy OCR / Zonal PDF2TEXT Neural
Handwritten Notes
Manual
Fail
Review
Layout Variance
High Cost
Breaks
Layout Agnostic
Setup Time
0h
40h per template
Zero-shot
Processing Speed
5 min/doc
2 min/doc
Fast preview
Multi-language Support
Staff dependent
Limited
40+ languages
Error Rate
Human review
Rework
Review flags

Directional comparison for teams evaluating review effort, setup complexity, and export readiness.

ROI_SIMULATOR

Calculate Your Savings

Estimate cost reduction based on your document processing volume.

VOLUME_INPUTS
100 50,000
$
$15 $50
m
2m 15m
PROJECTED_SAVINGS
$
per month
Hours Saved
Annual Savings
Cost Comparison
Manual Entry $
PDF2TEXT $

Estimate compares manual handling with paid extraction-page pricing. Actual savings depend on document quality, review time, and workflow fit.

Test with your own data.

Upload a messy PDF, image, or scan. No integration setup required.

LIVE_DEMO_v2.0
> Uploading... OK
> OCR... OK
> Extracting Entities... â–‹

Drop PDF BOL here

or click to browse

Or try one of ours:
> Extraction complete. 12 fields parsed.
Container IDMSCU9872341 ✓
Type40HC
Weight28,459 KG
ShipperACME Manufacturing Co.
SSL
private workspace
Max 50MB
SYSTEM_FAQ

Operational Specifications

Technical details for security review and export planning.

Is data retained?

Yes. Originals and extracted results are retained in your authenticated private workspace so you can review and export them. They are not automatically deleted after 24 hours; contact support to request deletion.

View Security Policy →

On-premise available?

PDF2TEXT is currently a hosted service. Contact support before planning an on-premise or air-gapped deployment.

Contact Sales →

How do I export?

Review extracted bill-of-lading and air-waybill fields, then download authenticated JSON or XLSX exports from the workstation.

Try the workstation →

Handwriting support?

Handwriting and scan quality vary substantially. Test representative samples in the workstation and validate the output before automating a workflow.

Test a Sample →

Custom document types?

Use an extraction template for a fixed custom schema. Contact support to review a specialized format or workflow before committing development time.

Request Custom Model →

Availability requirements?

Public plans do not currently include a published SLA. Contact support if your procurement process needs availability or hosting details.

Discuss Requirements →