Obsidian-Knowledge-Base/X-Knowledge-Base/raw/Joplin/_resources/SexWord.py

import pymysql
from wordcloud import WordCloud
import matplotlib.pyplot as plt
import jieba
import os

# 数据库配置
db_config = {
    "host": "localhost",
    "port": 3306,
    "user": "kekezack",
    "password": "daofengyizhi@66",
    "database": "wnacg",
}

try:
    # 连接数据库
    conn = pymysql.connect(**db_config)
    cursor = conn.cursor()

    # 查询标题和标签数据
    query = "SELECT title, tag_list FROM cartoon;"
    cursor.execute(query)
    results = cursor.fetchall()

    # 提取并合并文本数据
    text_data = []
    for row in results:
        title = row[0]
        if title:
            text_data.append(title)
        tags = row[1]
        if tags:
            text_data.extend(tags.replace("[", "").replace("]", "").split(","))
    all_text = ",".join(text_data)

except pymysql.MySQLError as e:
    print(f"Error: {e}")
finally:
    cursor.close()
    conn.close()

# 分词和处理
stopwords = {"的", "是", "我", "在"}
word_list = []
for word in jieba.cut(all_text):
    if len(word) > 1 and word not in stopwords:
        word_list.append(word)

wordcloud_data = " ".join(word_list)

# 生成词云
wc = WordCloud(
    font_path="simhei.ttf", width=800, height=600, background_color="white"
).generate(wordcloud_data)

plt.figure(figsize=(12, 8))
plt.imshow(wc)
plt.axis("off")
# 保存词云图片
wc.to_file(os.path.join(os.getcwd(), "sexword.png"))
# 显示词云图片
# plt.show()