{ "cells": [ { "cell_type": "markdown", "id": "4bdaea79", "metadata": {}, "source": [ "# Subtitle\n", "\n", ">[The SubRip file format](https://en.wikipedia.org/wiki/SubRip#SubRip_file_format) is described on the `Matroska` multimedia container format website as \"perhaps the most basic of all subtitle formats.\" `SubRip (SubRip Text)` files are named with the extension `.srt`, and contain formatted lines of plain text in groups separated by a blank line. Subtitles are numbered sequentially, starting at 1. The timecode format used is hours:minutes:seconds,milliseconds with time units fixed to two zero-padded digits and fractions fixed to three zero-padded digits (00:00:00,000). The fractional separator used is the comma, since the program was written in France.\n", "\n", "How to load data from subtitle (`.srt`) files\n", "\n", "Please, download the [example .srt file from here](https://www.opensubtitles.org/en/subtitles/5575150/star-wars-the-clone-wars-crisis-at-the-heart-en)." ] }, { "cell_type": "code", "execution_count": null, "id": "c6eb0372-ad36-4747-8120-d1557fe632fd", "metadata": { "tags": [] }, "outputs": [], "source": [ "!pip install pysrt" ] }, { "cell_type": "code", "execution_count": 4, "id": "2cbb7f5c", "metadata": { "tags": [] }, "outputs": [], "source": [ "from langchain.document_loaders import SRTLoader" ] }, { "cell_type": "code", "execution_count": 5, "id": "865d8a14", "metadata": { "tags": [] }, "outputs": [], "source": [ "loader = SRTLoader(\"example_data/Star_Wars_The_Clone_Wars_S06E07_Crisis_at_the_Heart.srt\")" ] }, { "cell_type": "code", "execution_count": null, "id": "173a9234", "metadata": { "tags": [] }, "outputs": [], "source": [ "docs = loader.load()" ] }, { "cell_type": "code", "execution_count": 27, "id": "15e00030", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'Corruption discovered\\nat the core of the Banking Clan! Reunited, Rush Clovis\\nand Senator A'" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "docs[0].page_content[:100]" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.10.6" } }, "nbformat": 4, "nbformat_minor": 5 }