Website Main Content Extraction Using Template-Based Approach and Naïve-Bayes Classification

Every web page will have the main content. The main content is a section, segment or block that contains text or multimedia on a single web page. Important information about local governance generally lies within the main content, thus the need for web content extractor to extract that information. To solve these problems, this research combines two approaches that already existed, template-based approach and machine learning approach using Naïve-Bayes Classifier. Generally, previous research that has been conducted is using one type of approach; it is either using a template-based approach or using a machine learning approach. The result shows that with combining two types of approaches, the model could identify 95% all nodes that contain the main content.