ADD file via upload

README.md

@@ -1,2 +0,0 @@
-# 102301535
-

analysis_notebook.ipynb

@@ -0,0 +1,100 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e34f22b5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from IPython.display import Image\n",
+    "print(\"生成的图表:\")\n",
+    "\n",
+    "print(\"词云图:\")\n",
+    "display(Image(filename='visualization/wordcloud.png'))\n",
+    "\n",
+    "print(\"应用领域分布:\")\n",
+    "display(Image(filename='visualization/applications_distribution.png'))\n",
+    "\n",
+    "print(\"情感分析:\")\n",
+    "display(Image(filename='visualization/sentiment_analysis.png'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7756a032",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(\"生成可视化图表...\")\n",
+    "visualizer = Visualizer()\n",
+    "visualizer.create_comprehensive_visualization(processed_df, top_apps, word_freq)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "da2f2518",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(\"开始数据处理...\")\n",
+    "processor = DataProcessor()\n",
+    "processed_df, top_apps, word_freq = processor.main()\n",
+    "\n",
+    "# 显示处理结果\n",
+    "print(\"应用领域排名:\")\n",
+    "display(top_apps)\n",
+    "\n",
+    "print(\"\\n词频统计前10:\")\n",
+    "display(word_freq.head(10))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "db65ea20",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(\"开始数据爬取...\")\n",
+    "crawler = BilibiliDanmuCrawler()\n",
+    "raw_df = crawler.generate_mock_data()\n",
+    "print(f\"获取到 {len(raw_df)} 条弹幕数据\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "29015b15",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sys\n",
+    "import os\n",
+    "sys.path.append('scripts')\n",
+    "\n",
+    "from crawler import BilibiliDanmuCrawler\n",
+    "from data_processor import DataProcessor\n",
+    "from visualizer import Visualizer\n",
+    "\n",
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.13.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

crawler.log

@@ -0,0 +1,12 @@
+2025-11-14 16:31:10,335 - INFO - 开始生成模拟弹幕数据...
+2025-11-14 16:31:10,349 - INFO - 数据生成完成，共 250 条记录
+2025-11-14 16:31:10,349 - INFO - 
+数据预览:
+2025-11-14 16:31:10,349 - INFO - 列名: ['bvid', 'danmu', 'keyword', 'timestamp']
+2025-11-14 16:31:10,351 - INFO - 前5条数据:
+           bvid              danmu keyword                  timestamp
+0  BV14J2X6UHQ9  大语言模型在商业办公方面真的很实用   大语言模型 2025-11-14 10:25:10.336313
+1  BV1DOTN63OAF   大模型在编程开发的准确性有待提高     LLM 2025-11-14 10:02:10.336553
+2  BV1G9XCAIAAG   大模型在娱乐创作的准确性有待提高   大语言模型 2025-11-14 09:34:10.336611
+3  BV1VQZHWO8VT     大模型在商业办公领域潜力巨大   大语言模型 2025-11-14 03:37:10.336655
+4  BV1CMSGNOET8     商业办公应用的隐私保护很重要   大语言模型 2025-11-14 00:20:10.336697

requirements.txt

@@ -0,0 +1,14 @@
+# requirements.txt
+requests>=2.31.0
+pandas>=2.0.0
+matplotlib>=3.7.0
+wordcloud>=1.9.0
+jieba>=0.42.1
+openpyxl>=3.1.0
+pillow>=10.0.0
+numpy>=1.24.0
+scipy>=1.10.0
+selenium>=4.15.0
+scrapy>=2.11.0
+jupyter>=1.0.0
+ipykernel>=6.25.0