Powerful, Adaptable Technology For Real-Time Data From Websites
Fetch technology utilizes advanced machine learning and pattern recognition, enabling it to extract and normalize web data in any language accurately, scalably, and cost-effectively. Fetch technology transforms web pages into databases, using precision machine learning technology to intelligently extract and transform only the data you need.
| PROFILE | Using advanced machine learning technologies, Fetch Live Access profiles web sites, “understanding” how they work, and enabling targeted extraction. Based on direction from users, Fetch builds “web agents” to extract the desired data. |
| EXTRACT | Fetch web agents enable online sources to be queried as if they were databases, targeting specific data sources within websites (e.g. prices, names), regardless of where the data is located within the site. Only the specific data you require is extracted from up to thousands of pages. |
| NORMALIZE | Extracted data from different websites comes in different formats; Fetch technology can take data in these different formats and “normalize” them into a singular format that each client determines. This makes the data immediately usable. |
| DELIVER | Fetch data can be delivered in multiple ways. Fetch offers a hosted Live Access service delivering data in convenient XML, or for customers that want installed software, Fetch can provide Live Access software, allowing data to be deposited directly into databases. |
Fetch technology adapts to changing web conditions providing high reliability. The technology was originally developed for the Defense Advanced Research Projects Agency (DARPA), the National Science Foundation (NSF), the U.S. Air Force, and other U.S. Government agencies.
Fetch technology provides:
- Access to a wide variety of web data regardless of website structure, including sites with forms, cookies, malformed HTML, JavaScript, AJAX, etc.
- Compatibility with foreign language sites
- Monitoring of data integrity
- Ability to scale to extraction of hundreds, thousands, or millions of records per day
Fetch Labs, an internal R&D group, continues to invest in advanced information extraction and integration technologies.
