Initial commit: skills library
- 70 skills with code and documentation - Add .gitignore (ignore __pycache__, output/, temp/, venv/) - Clean up test intermediates and caches
This commit is contained in:
hmo
@@ -0,0 +1,321 @@
|
||||
"""
|
||||
视频内容分析框架
|
||||
用于分析心理学/恋爱技巧类视频内容
|
||||
"""
|
||||
|
||||
import json
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
class VideoContentAnalyzer:
|
||||
def __init__(self, video_title):
|
||||
self.video_title = video_title
|
||||
self.analysis = {
|
||||
"title": video_title,
|
||||
"category": self._determine_category(),
|
||||
"key_concepts": [],
|
||||
"core_principles": [],
|
||||
"practical_techniques": [],
|
||||
"psychological_insights": [],
|
||||
"controversial_points": [],
|
||||
"ethical_considerations": [],
|
||||
"key_quotes": [],
|
||||
"summary": "",
|
||||
}
|
||||
|
||||
def _determine_category(self):
|
||||
"""根据标题确定视频类别"""
|
||||
title_lower = self.video_title.lower()
|
||||
|
||||
categories = {
|
||||
"relationship_psychology": ["爱", "恋爱", "女人", "男人", "感情", "关系"],
|
||||
"self_improvement": ["方法", "技巧", "提升", "改变"],
|
||||
"controversial": ["脏", "强行", "套路", "操控"],
|
||||
"educational": ["心理学", "心理", "科学", "研究"],
|
||||
}
|
||||
|
||||
detected = []
|
||||
for cat, keywords in categories.items():
|
||||
for kw in keywords:
|
||||
if kw in title_lower:
|
||||
detected.append(cat)
|
||||
break
|
||||
|
||||
return detected if detected else ["unknown"]
|
||||
|
||||
def analyze_transcript(self, transcript_text):
|
||||
"""分析转录文本"""
|
||||
print(f"分析视频: {self.video_title}")
|
||||
print(f"类别: {', '.join(self.analysis['category'])}")
|
||||
print(f"转录长度: {len(transcript_text)} 字符")
|
||||
|
||||
# 提取关键概念
|
||||
self._extract_key_concepts(transcript_text)
|
||||
|
||||
# 提取核心原则
|
||||
self._extract_core_principles(transcript_text)
|
||||
|
||||
# 提取实用技巧
|
||||
self._extract_practical_techniques(transcript_text)
|
||||
|
||||
# 提取心理学洞察
|
||||
self._extract_psychological_insights(transcript_text)
|
||||
|
||||
# 识别争议点
|
||||
self._identify_controversial_points(transcript_text)
|
||||
|
||||
# 伦理考量
|
||||
self._analyze_ethical_considerations(transcript_text)
|
||||
|
||||
# 提取关键引述
|
||||
self._extract_key_quotes(transcript_text)
|
||||
|
||||
# 生成总结
|
||||
self._generate_summary(transcript_text)
|
||||
|
||||
return self.analysis
|
||||
|
||||
def _extract_key_concepts(self, text):
|
||||
"""提取关键概念"""
|
||||
# 这里可以添加更复杂的NLP处理
|
||||
concepts = []
|
||||
|
||||
# 简单关键词提取（实际应用中应该用更复杂的方法）
|
||||
concept_keywords = [
|
||||
"吸引力",
|
||||
"价值",
|
||||
"框架",
|
||||
"需求感",
|
||||
"投资",
|
||||
"服从性",
|
||||
"筛选",
|
||||
"推拉",
|
||||
"冷读",
|
||||
"心锚",
|
||||
]
|
||||
|
||||
for concept in concept_keywords:
|
||||
if concept in text:
|
||||
concepts.append(concept)
|
||||
|
||||
self.analysis["key_concepts"] = concepts
|
||||
|
||||
def _extract_core_principles(self, text):
|
||||
"""提取核心原则"""
|
||||
# 寻找原则性陈述
|
||||
principle_indicators = [
|
||||
"原则是",
|
||||
"核心是",
|
||||
"关键在于",
|
||||
"最重要的是",
|
||||
"本质是",
|
||||
"根本在于",
|
||||
]
|
||||
principles = []
|
||||
|
||||
lines = text.split("。")
|
||||
for line in lines:
|
||||
for indicator in principle_indicators:
|
||||
if indicator in line:
|
||||
principles.append(line.strip())
|
||||
break
|
||||
|
||||
self.analysis["core_principles"] = principles[:5] # 取前5个
|
||||
|
||||
def _extract_practical_techniques(self, text):
|
||||
"""提取实用技巧"""
|
||||
technique_indicators = ["方法", "技巧", "步骤", "操作", "做法", "策略", "战术"]
|
||||
techniques = []
|
||||
|
||||
lines = text.split("。")
|
||||
for line in lines:
|
||||
for indicator in technique_indicators:
|
||||
if indicator in line and len(line) < 100: # 避免太长的句子
|
||||
techniques.append(line.strip())
|
||||
break
|
||||
|
||||
self.analysis["practical_techniques"] = techniques[:10] # 取前10个
|
||||
|
||||
def _extract_psychological_insights(self, text):
|
||||
"""提取心理学洞察"""
|
||||
insight_indicators = [
|
||||
"心理学",
|
||||
"心理",
|
||||
"潜意识",
|
||||
"认知",
|
||||
"情绪",
|
||||
"动机",
|
||||
"需求",
|
||||
"人性",
|
||||
]
|
||||
insights = []
|
||||
|
||||
lines = text.split("。")
|
||||
for line in lines:
|
||||
for indicator in insight_indicators:
|
||||
if indicator in line:
|
||||
insights.append(line.strip())
|
||||
break
|
||||
|
||||
self.analysis["psychological_insights"] = insights[:8]
|
||||
|
||||
def _identify_controversial_points(self, text):
|
||||
"""识别争议点"""
|
||||
controversial_indicators = [
|
||||
"脏",
|
||||
"强行",
|
||||
"操控",
|
||||
"套路",
|
||||
"欺骗",
|
||||
"利用",
|
||||
"不道德",
|
||||
"争议",
|
||||
]
|
||||
points = []
|
||||
|
||||
lines = text.split("。")
|
||||
for line in lines:
|
||||
for indicator in controversial_indicators:
|
||||
if indicator in line:
|
||||
points.append(line.strip())
|
||||
break
|
||||
|
||||
self.analysis["controversial_points"] = points
|
||||
|
||||
def _analyze_ethical_considerations(self, text):
|
||||
"""分析伦理考量"""
|
||||
ethical_indicators = [
|
||||
"尊重",
|
||||
"真诚",
|
||||
"诚实",
|
||||
"道德",
|
||||
"伦理",
|
||||
"责任",
|
||||
"伤害",
|
||||
"欺骗",
|
||||
]
|
||||
considerations = []
|
||||
|
||||
lines = text.split("。")
|
||||
for line in lines:
|
||||
for indicator in ethical_indicators:
|
||||
if indicator in line:
|
||||
considerations.append(line.strip())
|
||||
break
|
||||
|
||||
self.analysis["ethical_considerations"] = considerations
|
||||
|
||||
def _extract_key_quotes(self, text):
|
||||
"""提取关键引述"""
|
||||
# 寻找可能的重要陈述
|
||||
lines = text.split("。")
|
||||
quotes = []
|
||||
|
||||
for line in lines:
|
||||
line = line.strip()
|
||||
if len(line) > 20 and len(line) < 150: # 适中的长度
|
||||
# 检查是否包含重要关键词
|
||||
important_words = [
|
||||
"爱",
|
||||
"感情",
|
||||
"关系",
|
||||
"心理",
|
||||
"方法",
|
||||
"技巧",
|
||||
"价值",
|
||||
"吸引",
|
||||
]
|
||||
if any(word in line for word in important_words):
|
||||
quotes.append(line)
|
||||
|
||||
self.analysis["key_quotes"] = quotes[:5]
|
||||
|
||||
def _generate_summary(self, text):
|
||||
"""生成总结"""
|
||||
# 简单的总结生成（实际应用中应该用LLM）
|
||||
summary = f"视频《{self.video_title}》主要探讨了"
|
||||
|
||||
if self.analysis["key_concepts"]:
|
||||
summary += f"关于{', '.join(self.analysis['key_concepts'][:3])}等概念"
|
||||
|
||||
if self.analysis["practical_techniques"]:
|
||||
summary += f"，提出了{len(self.analysis['practical_techniques'])}个实用技巧"
|
||||
|
||||
if self.analysis["controversial_points"]:
|
||||
summary += f"，其中包含一些具有争议性的观点"
|
||||
|
||||
if self.analysis["ethical_considerations"]:
|
||||
summary += f"，同时也涉及伦理考量"
|
||||
|
||||
summary += "。"
|
||||
|
||||
self.analysis["summary"] = summary
|
||||
|
||||
def save_analysis(self, output_path):
|
||||
"""保存分析结果"""
|
||||
with open(output_path, "w", encoding="utf-8") as f:
|
||||
json.dump(self.analysis, f, ensure_ascii=False, indent=2)
|
||||
|
||||
print(f"分析结果已保存到: {output_path}")
|
||||
|
||||
def print_analysis(self):
|
||||
"""打印分析结果"""
|
||||
print("\n" + "=" * 60)
|
||||
print("视频内容分析报告")
|
||||
print("=" * 60)
|
||||
|
||||
print(f"\n📺 视频标题: {self.analysis['title']}")
|
||||
print(f"📂 类别: {', '.join(self.analysis['category'])}")
|
||||
print(f"📝 总结: {self.analysis['summary']}")
|
||||
|
||||
print(f"\n🔑 关键概念 ({len(self.analysis['key_concepts'])}个):")
|
||||
for concept in self.analysis["key_concepts"]:
|
||||
print(f" • {concept}")
|
||||
|
||||
print(f"\n🎯 核心原则 ({len(self.analysis['core_principles'])}个):")
|
||||
for i, principle in enumerate(self.analysis["core_principles"], 1):
|
||||
print(f" {i}. {principle}")
|
||||
|
||||
print(f"\n🛠️ 实用技巧 ({len(self.analysis['practical_techniques'])}个):")
|
||||
for i, technique in enumerate(self.analysis["practical_techniques"][:5], 1):
|
||||
print(f" {i}. {technique}")
|
||||
if len(self.analysis["practical_techniques"]) > 5:
|
||||
print(f" ... 还有{len(self.analysis['practical_techniques']) - 5}个技巧")
|
||||
|
||||
print(f"\n🧠 心理学洞察 ({len(self.analysis['psychological_insights'])}个):")
|
||||
for i, insight in enumerate(self.analysis["psychological_insights"][:3], 1):
|
||||
print(f" {i}. {insight}")
|
||||
|
||||
if self.analysis["controversial_points"]:
|
||||
print(f"\n⚠️ 争议点 ({len(self.analysis['controversial_points'])}个):")
|
||||
for i, point in enumerate(self.analysis["controversial_points"], 1):
|
||||
print(f" {i}. {point}")
|
||||
|
||||
if self.analysis["ethical_considerations"]:
|
||||
print(f"\n⚖️ 伦理考量 ({len(self.analysis['ethical_considerations'])}个):")
|
||||
for i, consideration in enumerate(
|
||||
self.analysis["ethical_considerations"], 1
|
||||
):
|
||||
print(f" {i}. {consideration}")
|
||||
|
||||
if self.analysis["key_quotes"]:
|
||||
print(f"\n💬 关键引述 ({len(self.analysis['key_quotes'])}个):")
|
||||
for i, quote in enumerate(self.analysis["key_quotes"], 1):
|
||||
print(f' {i}. "{quote}"')
|
||||
|
||||
|
||||
# 使用示例
|
||||
if __name__ == "__main__":
|
||||
video_title = "一个很'脏'的方法，让你喜欢的女人强行爱上你！"
|
||||
|
||||
analyzer = VideoContentAnalyzer(video_title)
|
||||
|
||||
# 这里应该读取转录文本
|
||||
# transcript = "转录文本内容..."
|
||||
# analysis = analyzer.analyze_transcript(transcript)
|
||||
|
||||
# 保存分析结果
|
||||
# analyzer.save_analysis("video_analysis.json")
|
||||
# analyzer.print_analysis()
|
||||
|
||||
print("分析框架已创建，等待转录文本...")
|
||||
@@ -0,0 +1,155 @@
|
||||
"""
|
||||
快速转录方案：如果本地Whisper太慢，尝试其他方法
|
||||
"""
|
||||
|
||||
import os
|
||||
import subprocess
|
||||
from pathlib import Path
|
||||
import json
|
||||
|
||||
|
||||
def extract_audio_from_video(video_path):
|
||||
"""从视频提取音频"""
|
||||
audio_path = video_path.with_suffix(".wav")
|
||||
|
||||
print(f"提取音频: {video_path.name} → {audio_path.name}")
|
||||
|
||||
cmd = [
|
||||
"ffmpeg",
|
||||
"-y",
|
||||
"-i",
|
||||
str(video_path),
|
||||
"-vn",
|
||||
"-acodec",
|
||||
"pcm_s16le",
|
||||
"-ar",
|
||||
"16000",
|
||||
"-ac",
|
||||
"1",
|
||||
str(audio_path),
|
||||
]
|
||||
|
||||
result = subprocess.run(cmd, capture_output=True, text=True)
|
||||
if result.returncode != 0:
|
||||
print(f"音频提取失败: {result.stderr}")
|
||||
return None
|
||||
|
||||
print(f"✅ 音频提取完成: {audio_path.stat().st_size / 1024 / 1024:.2f} MB")
|
||||
return audio_path
|
||||
|
||||
|
||||
def check_whisper_availability():
|
||||
"""检查Whisper是否可用"""
|
||||
try:
|
||||
import whisper
|
||||
|
||||
print("✅ Whisper已安装")
|
||||
return True
|
||||
except ImportError:
|
||||
print("❌ Whisper未安装")
|
||||
return False
|
||||
|
||||
|
||||
def transcribe_with_whisper(audio_path):
|
||||
"""使用Whisper转录"""
|
||||
try:
|
||||
import whisper
|
||||
|
||||
print("加载Whisper模型...")
|
||||
# 使用最小的模型加快速度
|
||||
model = whisper.load_model("tiny")
|
||||
|
||||
print("开始转录...")
|
||||
result = model.transcribe(str(audio_path), language="zh")
|
||||
|
||||
return result
|
||||
except Exception as e:
|
||||
print(f"Whisper转录失败: {e}")
|
||||
return None
|
||||
|
||||
|
||||
def save_transcription(result, video_path):
|
||||
"""保存转录结果"""
|
||||
if not result:
|
||||
return False
|
||||
|
||||
# 保存文本
|
||||
txt_path = video_path.with_suffix(".txt")
|
||||
with open(txt_path, "w", encoding="utf-8") as f:
|
||||
f.write(result["text"])
|
||||
|
||||
print(f"✅ 转录文本保存到: {txt_path.name}")
|
||||
print(f"文本长度: {len(result['text'])} 字符")
|
||||
|
||||
# 保存完整结果（JSON）
|
||||
json_path = video_path.with_suffix(".json")
|
||||
with open(json_path, "w", encoding="utf-8") as f:
|
||||
json.dump(result, f, ensure_ascii=False, indent=2)
|
||||
|
||||
print(f"✅ 完整结果保存到: {json_path.name}")
|
||||
|
||||
# 预览
|
||||
print("\n=== 转录预览（前500字符）===")
|
||||
preview = result["text"][:500]
|
||||
print(preview + "..." if len(result["text"]) > 500 else preview)
|
||||
|
||||
return True
|
||||
|
||||
|
||||
def main():
|
||||
print("=== 视频转录程序 ===")
|
||||
|
||||
# 查找视频文件
|
||||
video_dir = Path(r"D:\F\NewI\opencode\daily-workspace\temp")
|
||||
video_files = list(video_dir.glob("*.mp4"))
|
||||
|
||||
if not video_files:
|
||||
print("❌ 未找到mp4文件")
|
||||
return
|
||||
|
||||
video_path = video_files[0]
|
||||
print(f"处理视频: {video_path.name}")
|
||||
print(f"文件大小: {video_path.stat().st_size / 1024 / 1024:.2f} MB")
|
||||
|
||||
# 检查是否已有转录文件
|
||||
txt_path = video_path.with_suffix(".txt")
|
||||
if txt_path.exists():
|
||||
print(f"✅ 已有转录文件: {txt_path.name}")
|
||||
with open(txt_path, "r", encoding="utf-8") as f:
|
||||
text = f.read()
|
||||
print(f"文本长度: {len(text)} 字符")
|
||||
print("\n=== 现有转录预览 ===")
|
||||
print(text[:500] + "..." if len(text) > 500 else text)
|
||||
return
|
||||
|
||||
# 提取音频
|
||||
audio_path = extract_audio_from_video(video_path)
|
||||
if not audio_path:
|
||||
print("❌ 无法提取音频")
|
||||
return
|
||||
|
||||
# 检查Whisper
|
||||
if not check_whisper_availability():
|
||||
print("请安装Whisper: pip install openai-whisper")
|
||||
return
|
||||
|
||||
# 转录
|
||||
result = transcribe_with_whisper(audio_path)
|
||||
if not result:
|
||||
print("❌ 转录失败")
|
||||
return
|
||||
|
||||
# 保存结果
|
||||
if save_transcription(result, video_path):
|
||||
print("\n✅ 转录完成！")
|
||||
|
||||
# 清理临时音频文件
|
||||
if audio_path.exists():
|
||||
audio_path.unlink()
|
||||
print("临时音频文件已删除")
|
||||
else:
|
||||
print("❌ 保存转录结果失败")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -0,0 +1,43 @@
|
||||
import whisper
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
# 视频文件路径
|
||||
video_dir = Path(r"D:\F\NewI\opencode\daily-workspace\temp")
|
||||
video_files = list(video_dir.glob("*.mp4"))
|
||||
|
||||
if not video_files:
|
||||
print("未找到mp4文件")
|
||||
exit(1)
|
||||
|
||||
video_file = video_files[0]
|
||||
print(f"找到视频文件: {video_file.name}")
|
||||
print(f"文件大小: {video_file.stat().st_size / 1024 / 1024:.2f} MB")
|
||||
|
||||
# 使用Whisper转录
|
||||
print("\n加载Whisper模型...")
|
||||
model = whisper.load_model("base") # 使用base模型，速度较快
|
||||
|
||||
print("开始转录...")
|
||||
result = model.transcribe(str(video_file), language="zh")
|
||||
|
||||
# 保存结果
|
||||
output_file = video_file.with_suffix(".txt")
|
||||
with open(output_file, "w", encoding="utf-8") as f:
|
||||
f.write(result["text"])
|
||||
|
||||
print(f"\n✅ 转录完成！保存到: {output_file.name}")
|
||||
print(f"转录文本长度: {len(result['text'])} 字符")
|
||||
|
||||
# 显示前500字符预览
|
||||
print("\n=== 转录预览（前500字符）===")
|
||||
print(result["text"][:500] + "...")
|
||||
|
||||
# 如果有分段信息，也保存
|
||||
if "segments" in result:
|
||||
json_file = video_file.with_suffix(".json")
|
||||
import json
|
||||
|
||||
with open(json_file, "w", encoding="utf-8") as f:
|
||||
json.dump(result, f, ensure_ascii=False, indent=2)
|
||||
print(f"详细分段信息保存到: {json_file.name}")
|
||||
@@ -0,0 +1,108 @@
|
||||
import os
|
||||
import subprocess
|
||||
import json
|
||||
import re
|
||||
from pathlib import Path
|
||||
|
||||
# 视频文件路径
|
||||
video_path = Path(
|
||||
r'D:\F\NewI\opencode\daily-workspace\temp\一个很"脏"的方法，让你喜欢的女人强行爱上你！.mp4'
|
||||
)
|
||||
|
||||
print(f"处理视频: {video_path.name}")
|
||||
print(f"文件大小: {video_path.stat().st_size / 1024 / 1024:.2f} MB")
|
||||
|
||||
# 1. 提取音频
|
||||
audio_path = video_path.with_suffix(".wav")
|
||||
print(f"\n1. 提取音频到: {audio_path.name}")
|
||||
|
||||
ffmpeg_cmd = [
|
||||
"ffmpeg",
|
||||
"-y",
|
||||
"-i",
|
||||
str(video_path),
|
||||
"-vn",
|
||||
"-acodec",
|
||||
"pcm_s16le",
|
||||
"-ar",
|
||||
"16000",
|
||||
"-ac",
|
||||
"1",
|
||||
str(audio_path),
|
||||
]
|
||||
|
||||
print(f"运行命令: {' '.join(ffmpeg_cmd[:4])}...")
|
||||
result = subprocess.run(ffmpeg_cmd, capture_output=True, text=True)
|
||||
|
||||
if result.returncode != 0:
|
||||
print(f"提取音频失败: {result.stderr}")
|
||||
exit(1)
|
||||
|
||||
print("✅ 音频提取完成")
|
||||
|
||||
# 2. 检查是否安装了funasr
|
||||
print("\n2. 检查FunASR安装...")
|
||||
try:
|
||||
import funasr
|
||||
|
||||
print("✅ FunASR已安装")
|
||||
except ImportError:
|
||||
print("❌ FunASR未安装，正在安装...")
|
||||
subprocess.run(["pip", "install", "funasr", "modelscope"], capture_output=True)
|
||||
print("✅ FunASR安装完成")
|
||||
|
||||
# 3. 转录音频
|
||||
print("\n3. 开始转录...")
|
||||
try:
|
||||
from funasr import AutoModel
|
||||
|
||||
# 加载模型
|
||||
print("加载Paraformer模型...")
|
||||
model = AutoModel(
|
||||
model="paraformer-zh",
|
||||
vad_model="fsmn-vad",
|
||||
punc_model="ct-punc",
|
||||
disable_update=True,
|
||||
)
|
||||
|
||||
# 转录
|
||||
print("转录中...")
|
||||
result = model.generate(
|
||||
input=str(audio_path), batch_size_s=300, timestamp_granularity="sentence"
|
||||
)
|
||||
|
||||
# 保存结果
|
||||
output_path = video_path.with_suffix(".json")
|
||||
with open(output_path, "w", encoding="utf-8") as f:
|
||||
json.dump(result, f, ensure_ascii=False, indent=2)
|
||||
|
||||
print(f"✅ 转录完成，保存到: {output_path.name}")
|
||||
|
||||
# 显示摘要
|
||||
print("\n转录摘要:")
|
||||
if isinstance(result, list) and len(result) > 0:
|
||||
full_text = ""
|
||||
for item in result:
|
||||
if "text" in item:
|
||||
full_text += item["text"]
|
||||
|
||||
print(f"总字符数: {len(full_text)}")
|
||||
print(f"句子数: {len(result)}")
|
||||
print("\n前3句:")
|
||||
for i, item in enumerate(result[:3]):
|
||||
if "text" in item:
|
||||
print(f" {i + 1}. {item['text'][:100]}...")
|
||||
|
||||
except Exception as e:
|
||||
print(f"❌ 转录失败: {e}")
|
||||
import traceback
|
||||
|
||||
traceback.print_exc()
|
||||
|
||||
# 4. 清理临时文件
|
||||
print("\n4. 清理临时文件...")
|
||||
if audio_path.exists():
|
||||
audio_path.unlink()
|
||||
print("✅ 临时音频文件已删除")
|
||||
|
||||
print("\n✅ 处理完成！")
|
||||
Reference in New Issue
Block a user