Use b-semantic's API to extract and analyze web text. The API contains endpoints for text extraction, entity extraction, and similarity computing. B-semantic is REST based, employs HTTP POST methods, and accepts JSON data types. Use the text extraction service to extract the main text elements from a URL or HTML source code. The entity extraction web service identifies entities mapped to Wikipedia articles, and the similarity web service will compute the similarity of one source to another (with values between 1 and 0). See the API docs for full endpoint descriptions and code samples. B-semantic is available with limited usage for free.