# Captions and TV Archives {% embed url="" %} ## Notes: * Archive.org/TV * 2 million news shows online, searchable captions * The "Third Eye" -- reading and analyzing the "lower third" of the screen -- What are they reporting, what and how are they summarizing? * Uses tesseract-ocr and simhash to pull lines from multiple news channels * [www.twitter.com/tvThirdEye](http://www.twitter.com/tvThirdEye) -- watches CNN, tweets headlines. * CLIPS -- little JSON annotations to set start/end - points. Using JSONPatch. * Popcorn.js at IA: * Popcorn * Popcorn * Popcorn * 🍿 --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://textav.gitbook.io/textav-event/projects/captions-and-tv-archives.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.