
In Progress
Posted
Paid on delivery
We need somebody to: 1. extract target procurement line items from Spanish documents; Number of documents are 40 pdfs. 2. clean and normalize descriptions, quantities, units, brands, models, and technical attributes; 3. identify comparable supplier products using the approved source environment; 4. extract prices, currencies, package sizes, and source information; 5. convert prices into standardized unit prices; 6. flag uncertain matches and cases where no reliable match is available; 7. submit a reproducible data file and workflow documentation. Deliverables are: • [login to view URL]: one row per procurement item and candidate supplier match; • [login to view URL]: a machine-readable version of the same data; • [login to view URL], [login to view URL], or equivalent reproducible workflow, when automation is used; • [login to view URL]: tools, assumptions, source-use rules, match criteria, and reproduction steps. Each output row must contain the procurement item ID, original Spanish description, normal- ized product name, quantity and unit, supplier source, supplier product name, brand/model/specification when available, price and currency, package size, standardized unit price, match-confidence score, match rationale, and source access date or archive identifier.
Project ID: 40436630
15 proposals
Remote project
Active 5 days ago
Set your budget and timeframe
Get paid for your work
Outline your proposal
It's free to sign up and bid on jobs

Extracting structured procurement data from Spanish PDFs and matching it with supplier pricing requires more than simple scraping the important part is accurate normalization, unit conversion, and confidence-based product matching. I can build a reproducible Python workflow to process all 40 PDFs, extract procurement line items, normalize Spanish descriptions/units/brands/models, and generate standardized supplier price comparisons in both Excel and JSON formats. For similar data-processing work, I have worked with: - PDF extraction & cleaning pipelines - Automated Excel/JSON reporting - Product/data normalization workflows - Python-based scraping and matching systems using Pandas, OCR, and fuzzy matching Deliverables I will provide: - [login to view URL] with structured procurement and supplier match rows - [login to view URL] machine-readable dataset - reproducible Python script / notebook - README with workflow, assumptions, and matching logic I will also include: - confidence scoring for uncertain matches - standardized unit-price calculations - source/date tracking for auditability Are supplier sources already approved/listed, or should I search across public vendor catalogs? Are all PDFs text-based, or do some require OCR extraction? Since I am new to Freelancer.com, I am offering a competitive rate to build my profile reputation. I am happy to provide a quick sample extraction from 1 PDF before you award the project.
$20 USD in 2 days
0.0
0.0

With my extensive experience designing and building AI-driven systems, I am confident in my ability to automate the process of extracting and organizing the target procurement data from your 40 Spanish documents. I understand that your project does not simply require data extraction, but rather a systematic approach to data management and processing, which aligns perfectly with my skillset. The systems I design are not just prototypes; they are made for real-world application. Just like your project requires, my output comes in the form of clean and standardized data files (e.g., [login to view URL], [login to view URL]) accompanied by a reproducible workflow documentation (e.g., [login to view URL], [login to view URL]). My designs ensure that each row in the procurement data includes all the relevant information crucial for your analysis and decision making. So if you need someone who can automate your data flows seamlessly and is committed to delivering clean results - it would be a privilege for me to assist you with this project.
$10 USD in 1 day
0.0
0.0
15 freelancers are bidding on average $23 USD for this job

Hi, I’m interested in your Spanish Procurement Data Extraction and Supplier Price Matching project. I have experience with data extraction, web research, spreadsheet handling, and matching supplier pricing accurately from procurement documents. I can efficiently process Spanish-language procurement data, ensure clean structured outputs, and maintain high accuracy in supplier/product matching. I’m detail-oriented, reliable with deadlines, and ready to start immediately. Looking forward to discussing the project requirements further. Best regards, Fida
$30 USD in 1 day
5.3
5.3

I read your project requirements and would be thrilled to collaborate with you. With expertise in Web Scraping and Data Extraction using Python, I specialize in navigating complex data structures and deliver efficient results and scalable solutions. Let’s connect to discuss further
$30 USD in 2 days
4.2
4.2

Pully, Switzerland
Payment method verified
Member since Dec 9, 2025
$10-50 USD
$10-50 USD
$10-50 USD
$10-50 USD
$10-50 USD
₹600-1500 INR
$15-25 USD / hour
₹100-400 INR / hour
$2-8 USD / hour
₹600-1500 INR
$10-60 USD
$250-750 USD
₹600-1500 INR
₹100-400 INR / hour
₹1250-2500 INR / hour
₹750-1250 INR / hour
₹400-750 INR / hour
₹1500-12500 INR
€250-750 EUR
$10-30 USD
₹750-1250 INR / hour
₹600-1500 INR
₹100-400 INR / hour
₹1500-12500 INR
$15-25 USD / hour