Pull Item, Price, and Seller Type from Leboncoin and Marktplaats Screenshots, Without Retyping a French or Dutch Price
Manually copying a listing's title, price, and location from a French or Dutch classifieds listing takes about 3 minutes per ad. This pulls all five fields in under 10 seconds, across both markets.
5-10s per screenshot · European € format normalized · Up to 99% accuracy
Five Listing Fields You Can Pull from Any Leboncoin or Marktplaats Screenshot
Leboncoin renders listings as a grid of cards with a bold "Prix" tag and a "Vendu" overlay on sold items. Marktplaats renders compact cards with Dutch labels and a condition badge such as "Zo goed als nieuw". With Custom Column Extraction, the AI reads each field by its role in the card, so the boldest text is the item name and the amount next to the "€" is the price, whether you start from a Leboncoin screenshot or a Marktplaats screenshot.
The largest bold text on the listing, whether it is a card title on Leboncoin or a headline block on Marktplaats.
French format "1 500 €" or Dutch "€ 1.250,00", both normalized to clean numbers. "Bieden" (offer) qualifiers are captured alongside.
City and postcode on Leboncoin; city and distance from a Dutch postcode on Marktplaats.
The listing body text, captured as it appears on either platform.
"Particulier" vs "Professionnel" (private vs pro) on Leboncoin; "Privé" vs "Zakelijk" on Marktplaats.
Type these as column names in English, French, or Dutch. The AI reads each field by context across both platforms.
Two Countries, Two Languages, Two Price Formats: Why Screenshots Beat Scrapers for FR and NL Classifieds
Leboncoin places listings in a card grid with "Prix" tags, "Vendu" overlays on sold items, and a category sidebar. Marktplaats shows compact cards with Dutch labels and "Bieden" (bidding) instead of a fixed price on many items. URL-based scrapers either trip DataDome bot protection on Leboncoin or depend on Marktplaats's undocumented internal API, and both break when the site updates. A screenshot captures exactly what the buyer saw, regardless of what the backend allows. Here is why that matters.
Why Leboncoin and Marktplaats Break Traditional Extraction
Leboncoin's grid buries the listing in visual noise. Category navigation, "Prix" tags, "Vendu" overlays, and sponsored boxes all produce visible text. Traditional OCR cannot tell the listing card's title from the category label next to it.
Marktplaats often shows "Bieden" instead of a number. Many listings carry no fixed price, only "Bieden" (make an offer) or "Bieden vanaf € 250" (bidding starts at € 250). Pure numeric extraction either fails or grabs the wrong value.
French and Dutch € formats differ. Leboncoin writes "1 500 €" with a space as the thousand separator. Marktplaats writes "€ 1.250,00" with a period as the thousand separator and a comma before the cents. One set of column names has to read both conventions.
How One Set of Column Names Reads Both Platforms
Name the fields and the AI finds each value by context, not position. Type Item Name, Price, Location, Description, Seller Type. The visual model reads the boldest card text as the item name, the number next to "€" as the price, and ignores adjacent category navigation and sponsored labels.
"Bieden" pricing is kept with its context. When Marktplaats shows "Bieden vanaf € 250", the AI puts 250.00 in the Price column and "Bieden" in a qualifier field, so you keep both the amount and the fact that it is negotiable.
Both € formats normalize automatically. "1 500 €" from a Leboncoin screenshot and "€ 1.250,00" from a Marktplaats screenshot both land as 1500.00 in the Price column, with the raw text preserved in a parallel column so you can verify the conversion.
From Mixed FR and NL Screenshots to One Consolidated Listing Sheet
Whether you are tracking items listed on both platforms, comparing prices across markets, or archiving your transactions, here is how the extraction workflow handles screenshots from two countries in a single pass.
Upload Screenshots from Both Platforms
Drop in captures from your camera roll or desktop: Leboncoin listing cards with "Prix" badges and "Vendu" overlays, alongside Marktplaats cards with "Bieden" pricing and "Privé" labels. PNG, JPG, or WebP from any device. Mix them in the same batch with no sorting by platform needed.
Define One Set of Column Names
Type the fields you want, in English, French, or Dutch: Item Name, Price, Location, Description, Seller Type (or Titre, Prix, Localisation, Description, Vendeur; or Titel, Prijs, Locatie, Beschrijving, Verkoperstype). The AI reads each screenshot and fills the matching fields, so a Leboncoin card takes its Price from the "Prix" tag and a Marktplaats card reads the same field from its own label.
Export a Combined FR/NL Spreadsheet
Processing takes 5-10 seconds per screenshot, about 18x faster than opening each image and typing the fields by hand. The output is one XLSX or CSV file with all five columns. Prices are already normalized from both French and Dutch formats. Filter by Seller Type to separate professional listings from private sellers across both platforms.
When Leboncoin and Marktplaats Screenshot Extraction Works Best, and When to Be Cautious
When It Works Best
Full-resolution native screenshots of listing cards or detail pages. High-contrast, machine-rendered text from either platform reaches up to 99% accuracy for fields like Item Name and Price.
Mixed Leboncoin and Marktplaats screenshots in one batch. One column definition works across both platforms, and the AI adapts to each layout independently.
Clean captures where the listing card or text block is the main focus. When the listing fills most of the frame, the AI separates its fields from nearby navigation and sponsored content.
When to Be Cautious
Screenshots forwarded through messaging apps. WhatsApp and Messenger compress images, reducing accuracy for smaller text like seller type badges. Use native screenshots for best results.
Multiple listing cards in one screenshot. The AI reads the most visually prominent listing. For clean per-item extraction, capture each listing individually.
Leboncoin screenshots with a heavy "Vendu" overlay. The "Vendu" badge is semi-transparent, so the underlying Item Name and Price are still readable, but accuracy may decrease for fields near the overlay edge.
A listing screenshot is not a receipt. It records the asking price shown when you saved it, not the price finally agreed, and it cannot confirm that a sale took place. If you need proof of the terms you settled on, keep the message thread or the final agreement alongside the screenshot.
Frequently Asked Questions
Can I extract the Item Name and Price from a Leboncoin screenshot that already shows a "Vendu" overlay?
Yes. The AI reads the listing data underneath the "Vendu" badge. The overlay is semi-transparent and does not fully obscure the Item Name or Price, and the Description column captures the listing body text from the area below the overlay. For Marktplaats, "Verkocht" badges follow the same semi-transparent pattern.
How does the tool handle Marktplaats listings that show "Bieden" instead of a fixed Price?
When a listing shows "Bieden" (make an offer), the AI records the offer type in a separate Price Qualifier column. If the listing shows "Bieden vanaf € 250" (bidding starts at € 250), the 250.00 goes into the Price column too. The same qualifier field captures "Nader overeen te komen" (price to be agreed) and "Gratis" (free pickup), so a fixed price and an open bid never blur into the same cell.
Can I process Leboncoin and Marktplaats screenshots together in one batch?
Yes. Define one set of column names, Item Name, Price, Location, Description, Seller Type, and upload screenshots from both platforms into the same batch. The AI reads each screenshot independently, so a Leboncoin card with a "Prix" tag and a Marktplaats card with a "Prijs" or "Bieden" label both fill the same columns. Every screenshot becomes a row in one spreadsheet, and you can add a Platform column to tag each row "Leboncoin" or "Marktplaats".
What columns work best for tracking listings across both platforms?
Start with the five standard fields: Item Name, Price, Location, Description, Seller Type. Add Platform to separate Leboncoin rows from Marktplaats rows, and Price Qualifier to keep "Bieden", "Gratis", or "Nader overeen te komen" beside the numeric price. If you want one sortable number, add a Computed Column such as Numeric Price that pulls both country formats into a single column.
Can I use French or Dutch column names instead of English?
Yes. Column names can be in any language. Type Titre, Prix, Localisation, Description, Vendeur for Leboncoin screenshots, or Titel, Prijs, Locatie, Beschrijving, Verkoperstype for Marktplaats. The AI matches the field names by meaning, not by exact wording, so the output spreadsheet uses your chosen column names as headers.
Return to the secondhand marketplace overview, which covers Facebook Marketplace, Vinted, Carousell, Leboncoin, Marktplaats, and more.
Deep dives: Batch processing marketplace screenshots into a single spreadsheet · General guide to extracting data from screenshots