You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

41 lines
1.6 KiB

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

# -*- coding: utf-8 -*-
import os # 新增导入os模块用于文件检查
class DanmakuAnalyzer:
def __init__(self, danmu_path="./data/all_danmu.txt"):
self.danmu_list = []
# 新增:检查文件是否存在
if not os.path.exists(danmu_path):
print(f"错误:弹幕文件 {danmu_path} 不存在")
return
# 新增:异常处理
try:
with open(danmu_path, "r", encoding="utf-8") as f:
self.danmu_list = [line.strip() for line in f if line.strip()]
except Exception as e:
print(f"读取弹幕文件失败:{e}")
def analyze(self):
"""分析用户观点"""
if not self.danmu_list: # 新增:检查数据是否有效
print("无有效弹幕数据,无法进行分析")
return
categories = {
"应用领域": ["学习", "办公", "编程", "写作"],
"成本": ["免费", "付费", ""],
"担忧": ["失业", "隐私", "错误"]
}
counts = {k:0 for k in categories}
for danmu in self.danmu_list:
for cat, keywords in categories.items():
if any(kw in danmu for kw in keywords):
counts[cat] += 1
print("\n用户观点分析:")
total = len(self.danmu_list)
for cat, cnt in counts.items():
print(f"- {cat}{cnt}次提及(占比{cnt/total:.1%}")
if __name__ == "__main__":
analyzer = DanmakuAnalyzer()
analyzer.analyze()