Text Entity Extractor

Pull structured entities out of messy, unstructured text with the Text Entity Extractor. Point it at an article, email, chat log, transcript or scraped page and get back every email, phone number, URL, date, time, money amount, percentage, IP address, hashtag, @mention, ZIP code and emoji — one clean row per entity, exported as JSON, CSV or Excel.

Ideal for lead extraction, data mining, log parsing, content moderation, redaction prep and dataset enrichment, it turns free text into a tidy, filterable table with zero setup.

What it does

• 📧 Many entity types — emails, URLs, phone numbers, dates, times, money, percentages, IPv4 addresses, hashtags, @mentions, US ZIP codes, card-number candidates and emojis.
• 🎛️ Pick what you want — extract everything, or select just the types you need (e.g. only emails and phones).
• 🧹 Smart matching — phone detection avoids false positives from dates, IPs and ZIP codes.
• 🧾 De-duplication — keep only the first occurrence of each identical entity, or keep them all.
• 📚 Batch texts — scan many documents in one run, each labelled by document.
• 📍 Positions included — every entity comes with its character offset in the source text.
• 📤 Export anywhere — JSON, CSV or Excel, or straight into a CRM, spreadsheet or workflow.

Example output

{ "documentIndex": 0, "type": "email", "value": "jane.doe@example.com", "start": 8 }
{ "documentIndex": 0, "type": "phone", "value": "+1 (650) 555-1234", "start": 32 }
{ "documentIndex": 0, "type": "money", "value": "$1,250.50", "start": 96 }

How to use it

1. Paste your text (or add several texts in the list).
2. Optionally choose which entity types to extract — leave empty for all.
3. Toggle Remove duplicates if you want unique values only.
4. Run, and download the entities as JSON, CSV or Excel.

Input fields

Output fields

documentIndex, type, value, start, collectedAt.

Popular use cases

• Lead extraction — pull emails and phone numbers out of scraped pages or documents.
• Data mining — turn free-text notes, reviews or tickets into structured fields.
• Log & security parsing — extract IPs, URLs and timestamps from logs.
• Content moderation & redaction — locate personal data (emails, phones, cards) to review or mask.
• Social analysis — collect hashtags and @mentions across posts.
• Dataset enrichment — add structured entity columns to an existing text dataset.

FAQ

Do I need an account or key? No. Paste your text, pick the types, and run.

How accurate is the extraction? It uses well-tuned pattern matching with guards to reduce false positives (for example, dates and IP addresses aren't mistaken for phone numbers). As with any pattern-based extractor, unusual formats may vary.

Can I extract only certain types? Yes — select just the entity types you need (e.g. only emails and phones) and the rest are ignored.

Does it work on many documents at once? Yes — add a list of texts and each is scanned separately, with a document index on every result.

Can I export to Excel or Google Sheets? Yes — results download as JSON, CSV or Excel and integrate with Sheets, CRMs and automation tools.

Turn unstructured text into a clean table of emails, phones, URLs, dates, money and more — filterable, deduplicated and export-ready.

You pay only for what the run returns. Set a maximum cost per run and it stops cleanly at that limit.