{ "cells": [ { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "# 可从video url中快速取出字幕文本信息" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "from langchain.document_loaders.bilibili import BiliBiliLoader" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "loader = BiliBiliLoader(\n", " [\"https://www.bilibili.com/video/BV1DP411m7TR/\"]\n", ")" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "ename": "RuntimeError", "evalue": "This event loop is already running", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mRuntimeError\u001b[0m Traceback (most recent call last)", "Cell \u001b[0;32mIn[8], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m loader\u001b[39m.\u001b[39;49mload()\n", "File \u001b[0;32m~/anaconda3/lib/python3.10/site-packages/langchain/document_loaders/bilibili.py:23\u001b[0m, in \u001b[0;36mBiliBiliLoader.load\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 21\u001b[0m results \u001b[39m=\u001b[39m []\n\u001b[1;32m 22\u001b[0m \u001b[39mfor\u001b[39;00m url \u001b[39min\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mvideo_urls:\n\u001b[0;32m---> 23\u001b[0m transcript, video_info \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_get_bilibili_subs_and_info(url)\n\u001b[1;32m 24\u001b[0m doc \u001b[39m=\u001b[39m Document(page_content\u001b[39m=\u001b[39mtranscript, metadata\u001b[39m=\u001b[39mvideo_info)\n\u001b[1;32m 25\u001b[0m results\u001b[39m.\u001b[39mappend(doc)\n", "File \u001b[0;32m~/anaconda3/lib/python3.10/site-packages/langchain/document_loaders/bilibili.py:51\u001b[0m, in \u001b[0;36mBiliBiliLoader._get_bilibili_subs_and_info\u001b[0;34m(self, url)\u001b[0m\n\u001b[1;32m 48\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[1;32m 49\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39m{\u001b[39;00murl\u001b[39m}\u001b[39;00m\u001b[39m is not bilibili url.\u001b[39m\u001b[39m\"\u001b[39m)\n\u001b[0;32m---> 51\u001b[0m video_info \u001b[39m=\u001b[39m sync(v\u001b[39m.\u001b[39;49mget_info())\n\u001b[1;32m 52\u001b[0m video_info\u001b[39m.\u001b[39mupdate({\u001b[39m\"\u001b[39m\u001b[39murl\u001b[39m\u001b[39m\"\u001b[39m: url})\n\u001b[1;32m 54\u001b[0m \u001b[39m# Get subtitle url\u001b[39;00m\n", "File \u001b[0;32m~/anaconda3/lib/python3.10/site-packages/bilibili_api/utils/sync.py:24\u001b[0m, in \u001b[0;36msync\u001b[0;34m(coroutine)\u001b[0m\n\u001b[1;32m 22\u001b[0m __ensure_event_loop()\n\u001b[1;32m 23\u001b[0m loop \u001b[39m=\u001b[39m asyncio\u001b[39m.\u001b[39mget_event_loop()\n\u001b[0;32m---> 24\u001b[0m \u001b[39mreturn\u001b[39;00m loop\u001b[39m.\u001b[39;49mrun_until_complete(coroutine)\n", "File \u001b[0;32m~/anaconda3/lib/python3.10/asyncio/base_events.py:625\u001b[0m, in \u001b[0;36mBaseEventLoop.run_until_complete\u001b[0;34m(self, future)\u001b[0m\n\u001b[1;32m 614\u001b[0m \u001b[39m\u001b[39m\u001b[39m\"\"\"Run until the Future is done.\u001b[39;00m\n\u001b[1;32m 615\u001b[0m \n\u001b[1;32m 616\u001b[0m \u001b[39mIf the argument is a coroutine, it is wrapped in a Task.\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 622\u001b[0m \u001b[39mReturn the Future's result, or raise its exception.\u001b[39;00m\n\u001b[1;32m 623\u001b[0m \u001b[39m\"\"\"\u001b[39;00m\n\u001b[1;32m 624\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_check_closed()\n\u001b[0;32m--> 625\u001b[0m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_check_running()\n\u001b[1;32m 627\u001b[0m new_task \u001b[39m=\u001b[39m \u001b[39mnot\u001b[39;00m futures\u001b[39m.\u001b[39misfuture(future)\n\u001b[1;32m 628\u001b[0m future \u001b[39m=\u001b[39m tasks\u001b[39m.\u001b[39mensure_future(future, loop\u001b[39m=\u001b[39m\u001b[39mself\u001b[39m)\n", "File \u001b[0;32m~/anaconda3/lib/python3.10/asyncio/base_events.py:584\u001b[0m, in \u001b[0;36mBaseEventLoop._check_running\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 582\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m_check_running\u001b[39m(\u001b[39mself\u001b[39m):\n\u001b[1;32m 583\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mis_running():\n\u001b[0;32m--> 584\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mRuntimeError\u001b[39;00m(\u001b[39m'\u001b[39m\u001b[39mThis event loop is already running\u001b[39m\u001b[39m'\u001b[39m)\n\u001b[1;32m 585\u001b[0m \u001b[39mif\u001b[39;00m events\u001b[39m.\u001b[39m_get_running_loop() \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[1;32m 586\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mRuntimeError\u001b[39;00m(\n\u001b[1;32m 587\u001b[0m \u001b[39m'\u001b[39m\u001b[39mCannot run the event loop while another loop is running\u001b[39m\u001b[39m'\u001b[39m)\n", "\u001b[0;31mRuntimeError\u001b[0m: This event loop is already running" ] } ], "source": [ "loader.load()" ] } ], "metadata": { "kernelspec": { "display_name": "base", "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": "3.10.10" }, "orig_nbformat": 4 }, "nbformat": 4, "nbformat_minor": 2 }