Text Entity Extractor - Emails, Phones, URLs, Dates, Money

Extract structured entities from free text: email addresses, URLs, phone numbers (incl. Japanese formats and full-width digits), dates (ISO, slash, Japanese 年月日) and IP addresses. Deterministic regex extraction with per-kind counts — fast, cheap, no LLM.

Named Entity Recognition (NER) & Sentiment Analysis API

lofomachines/named-entity-recognition-api

🔥 Only 0.002$ 🔥 Named Entity Recognition (NER), entity extraction and sentiment analysis API for bulk text, CSV and Excel files. Analyze reviews, social media posts, customer feedback, surveys, support tickets, transcripts and much more, give your Agent bulk excel rows classification ability.

Website Contact Scraper — Bulk Emails, Phones & Socials | $1/1k

pro100chok/extract-emails

Bulk contact scraper for up to 100 domains in parallel — emails, phones, and 7 social platforms in one run. Decodes obfuscated emails ([at], HTML entities). $1 per 1000 results.

Extract structured intelligence from document text for AI, RAG and automation workflows. Detect document type, dates, money, emails, phone numbers, URLs, headings, named-entity candidates, statistics and possible PII. Returns machine-readable JSON.

Contact Scraper: Validated Emails + Phones, Pay Per Site

mrlarryjohnson/contact-details-scraper-pro

Crawl business websites for emails, phones, and socials — then VALIDATE every email (DNS/MX, disposable, role, placeholder filtering) so you get deliverable contacts, not regex soup. Failed fetches never billed.

Named Entity Extractor & Name Validator

dominic-quaiser/named-entity-extractor

Extract named entities from text using a NER API. Supports multilingual, English, and German text extraction with confidence scores for each detected name.

Extract ranked multi-word keyword phrases (RAKE-scored) + top words from up to 200 texts per run. For tagging, SEO briefs, ticket clustering, labeling scraped content. $0.0005 per text, no start fee, junk entries never charged. No paid keyword-extraction rival with defined pricing measured.

Screen up to 1,000 texts per run against a tiered profanity wordlist with obfuscation heuristics (leet, spacing, partial masks) — severity, exact positions, masked cleanedText, Scunthorpe-guarded boundaries. A filter, NOT an AI moderation system. $0.0004 per text, junk entries never charged.

Detect the language of up to 200 texts per run: ISO 639-3 code, English name, confidence and ranked alternatives (franc trigram model, in-process, texts never leave the run). $0.0005 per text — half the measured incumbent ($0.001); too-short snippets never charged. For routing and dataset splitting.

The Money TMX Quote URLs Scraper is a tool for extracting news article links from TMX Money based on search queries. It offers automated data extraction, customizable parameters, and structured JSON output....