Freelancer profile translated to English.
Back to original languageAbout Simon
🕷️ Web scraping starting from €150 per site -> difficult sites, blocks, captcha solving.
I help you transform any website into aclean, structured, and usable data stream (also works from iOS and Android apps✨).
With 10 years of experience and over 500 companies assisted, I design robust and maintainable production scraping systems.
I implement automatic solutions that:
✔️ Collect dataat regular intervals
✔️ Manage errors and blocks automatically
✔️ Detectstructural changes
✔️ Maintainlong-term stability
✔️ Produceclean, normalized, and usable data
✔️ Usable via API
Whether for lead generation, competitor monitoring, market tracking, or feeding AI agents, I build solutions tailored to your objectives.
🔎 Project examples:
- Google Maps (lead generation)
- Google Search
- LinkedIn & Sales Navigator
- Indeed (job postings)
- Real Estate (SeLoger, PAP, Idealista, Leboncoin)
- Social Networks (Instagram, YouTube, Twitter…)
🛡️ Protected Environments Expertise:
- DataDome
- Cloudflare
- PerimeterX / HUMAN
- reCAPTCHA, hCaptcha, Geetest
- Complex Captchas & Behavioral Detection, Fingerprinting
⚙️ Production Methodology:
- Scalable Architecture
- Intelligent IP Rotation
- Browser Fingerprint Management
- Monitoring & Alerting
- Auto-corrections in case of errors
- Data Cleaning, Normalization, and Structuring
- CSV / API / Database Export
💡 Objective: to provide you with reliable data directly usable by your teams (or your LLM models ✨)
🎓 Master's Degree in Artificial Intelligence – École des Ponts
English
Fluent
French
Native or bilingual
Spanish
Conversational
Remote only
Primarily works remotely
Experience
- LBF
On Malt
B2B Database of Bars and Restaurants in Paris + 92/93/94/95 with verified emails + phone numbersRESTAURANTS AND FOOD SERVICEOctober 2025 - November 2025 (1 month)Paris, France🚀 Scraping & Qualification – Restaurants (Paris + Île-de-France)Implemented an AI pipeline to build a highly qualified database of bars & restaurants (Google Maps + Uber Eats).Achievements:- Identified official websites (excluded marketplaces)
- Extracted professional emails + mobile numbers (06/07)
- Intelligent email scoring (prioritized usable contacts)
- MX/DNS/SMTP verification to reduce bounces
- Merged & deduplicated multi-source data
Result:- Clean, structured database ready for CRM
- Optimized deliverability rate
- More effective outreach campaigns
Deliverable: Structured CSV/XLSX + source traceability. - Geoplanete France SASShopify Product Catalog Automation (scraping + AI + Matrixify integration)E-COMMERCESeptember 2025 - November 2025 (2 months)Paris, France🧩 Shopify Catalog Automation – Geoplanete (Website → Shopify)Implemented a complete pipeline to automate the integration of the product catalog into Shopify.Achievements:
- Developed a robust scraper (products, variants, accessories, images, technical PDFs)
- Advanced data normalization and cleaning (attributes, prices, weights, SEO, metadata)
- Automated description and FAQ enrichment using GPT-5 (prompt engineering + validation)
- Generated the catalog via Matrixify (stock, custom fields, brands, product relationships)
- Imported as Drafts into Shopify for validation (50+ products tested)
- Set up a replicable process for future suppliers
Result:An automated pipeline allowing the import of hundreds of clean and enriched products in minutes, eliminating manual data entry and making the addition of new catalogs scalable. - Expertual invest SLData Engineer & Python Developer — scraping and structuring of tax documents, RAG pipelineSOFTWARE PUBLISHINGJuly 2025 - August 2025 (1 month)Paris, France- Collection & parsing of Spanish tax documents (PDF/HTML) with a robust pipeline (retries, logs).- Metadata cleaning/normalization (period, issuer, document type).- Indexing: Postgres database + optimized schema, storage of files and content.- Automatic summarization & classification via OpenAI (business labels + synopsis per document).- Airtable synchronization for consultation and tracking (~60,000 docs).- Quality & industrialization: tests, monitoring, alerting, recovery scripts.- Phase 2 preparation: design of an RAG chatbot (semantic search, history, permissions).Main stack: Python, FastAPI, Playwright/Requests, BeautifulSoup, PostgreSQL (+pgvector), OpenAI API, Airtable API, Docker, CI/CD.
Reviews
Recommendations
Be the first to recommend Simon
Help this freelancer shine by sharing your experience working together.
These freelancer profiles also match your criteria
Agatha Frydrych
Backend Java Software Engineer
4.7
(3)
2
Baptiste Duhen
Fullstack developer
4.6
(4)
5
Amed Hamou
Senior Lead Developer
4
(2)
7
Audrey Champion
Web developer
4.3
(3)
4
Education
- Master of Financial EngineeringUniversité Paris Dauphine2016Modèles probabilistes, produits dérivés.
- Machine Learning (Artificial Intelligence)Ecole Nationale des Ponts et Chaussées2017Neural Networks, SVM, k-means, spectral clustering