8 مستودعات
Tools that identify and transform unstructured document content into standardized, machine-readable formats.
Explore 8 awesome GitHub repositories matching data & databases · Structured Data Extractors. Refine with filters or upvote what's useful.
Firecrawl is a headless browser automation tool and web crawling engine designed to extract structured data from the web. It functions as an API that transforms raw website content and documents into clean markdown and JSON formats to serve as context for large language models. The project distinguishes itself by using natural language prompts to translate human instructions into targeted data extraction tasks and browser actions. It can execute interactive page navigation, such as clicking and scrolling, and perform automated web research to retrieve structured data without manual interventi
Transforms unstructured web pages and documents into standardized, machine-readable formats using natural language prompts.
MinerU is a document parsing pipeline designed to transform unstructured files into machine-readable, structured data. It utilizes deep learning models to perform layout analysis, identifying document regions and extracting complex content such as mathematical expressions. By combining these neural network inferences with geometric heuristics, the system reconstructs the reading order and structural hierarchy of documents to ensure accurate data representation. The project distinguishes itself through a multi-stage processing workflow that integrates layout detection, optical character recogn
Transforms unstructured document content into standardized, machine-readable formats for automated information retrieval.
Docling is a modular framework designed for document parsing, layout analysis, and structured data extraction. It transforms unstructured files and web content into a unified, hierarchical data model that preserves the spatial and semantic relationships between text, tables, images, and layout elements. By normalizing diverse input formats into a consistent internal representation, the library enables uniform processing across various document types. The project distinguishes itself through a schema-driven approach that maps document regions to strongly-typed objects, ensuring data accuracy t
Identifies and transforms complex document layouts into standardized, machine-readable information.
Guardrails is a Python SDK that wraps calls to large language models with configurable validation pipelines, corrective actions, and structured output generation. It provides a unified API layer that connects to over 100 language models, applying consistent validation, streaming, and error-handling across providers. The framework validates and corrects model responses against safety and quality rules, detecting and mitigating risks in both inputs and outputs using pre-built and custom validators. The project distinguishes itself through a validator-pipeline architecture that sequentially appl
Generates validated JSON or schema-based structured data from free-form model responses using function calling.
X-ray هو متصفح ويب بدون واجهة رسومية (headless) ومزاحف محتوى HTML مصمم لاستخراج البيانات المهيكلة من المواقع. يعمل كمزاحف بيانات يعتمد على التدفق ومستخرج بيانات مهيكلة، باستخدام محددات لاسترداد النصوص والسمات من HTML ككائنات أو مصفوفات متداخلة. يتضمن المشروع وحدة تحكم في معدل الطلبات لإدارة حركة مرور الشبكة من خلال حدود التزامن، والمخنق، والمهلات. يتعامل مع كشط المواقع الديناميكية عن طريق عرض JavaScript عبر متصفح بدون واجهة رسومية ويقوم بأتمتة زحف المواقع باستخدام تتبع الروابط بالعرض أولاً وإدارة الترقيم. يوفر النظام خط أنابيب بيانات يطبق تحويلات قيم وظيفية على السلاسل الخام ويكتب النتائج إلى تدفق قابل للقراءة لمنع تجاوز سعة الذاكرة أثناء مهام كشط الويب واسعة النطاق.
Provides a selector-based parser to retrieve text and attributes from HTML as structured nested objects or arrays.
هذا المشروع هو إطار عمل لكشط الويب (web scraping) مبني على Node.js مصمم لأتمتة استخراج البيانات من خلال سير عمل برمجي للطلبات، والتحليل، وتفاعل المستندات. يعمل كزاحف ويب بدون رأس (headless)، ومدير طلبات HTTP، ومحلل ومستخرج DOM. يتميز إطار العمل بدمج محرك تنفيذ JavaScript للتفاعل مع المحتوى الديناميكي ونظام اختيار هجين يستخدم كلاً من محددات CSS وXPath. يتضمن برمجيات وسيطة (middleware) متخصصة لتدوير الوكيل (proxy rotation) وإدارة جلسة ملفات تعريف الارتباط للحفاظ على الحالات المصادق عليها وإدارة حركة المرور المؤتمتة. تغطي قدراته الأوسع زحف الروابط المتكرر، ومعالجة الترقيم، وأتمتة نماذج الويب. توفر الأداة أيضاً ميزات إدارة حركة المرور مثل تحديد معدل الطلبات من خلال تأخيرات زمنية وتكوين رؤوس HTTP مخصصة.
Implements CSS and XPath selectors to extract structured data from HTML and XML documents.
Jodd is a suite of lightweight Java extensions and standard library utilities designed for application configuration, database mapping, dependency injection, and HTML parsing. It provides a consolidated set of core tools to facilitate Java development with a zero-dependency core to ensure compatibility and a small footprint across environments. The project features a pragmatic dependency injection container for managing object lifecycles and a database mapper that uses SQL templates to map result sets directly to Java objects. It includes a specialized configuration manager supporting profile
Provides an HTML parser that allows element extraction using CSS3 selector patterns.
Epicenter is a local-first knowledge management system and data orchestrator designed to structure information generated by large language models into validated schemas. It functions as a storage architecture that persists application data in human-readable files and databases to ensure user ownership and portability. The system distinguishes itself by projecting language model outputs into structured, schema-validated tables and utilizing conflict-free replicated data types to synchronize application state across multiple devices without a central server. This allows for offline access and c
Projects language model outputs into structured, schema-validated tables for advanced knowledge management.