import sqlite3

# 獲取瀏覽器歷史記錄數(shù)據(jù)庫路徑
history_path = r"C:\Users\你的用戶名\AppData\Local\Google\Chrome\User Data\Default\History"

# 連接到歷史記錄數(shù)據(jù)庫
conn = sqlite3.connect(history_path)
cursor = conn.cursor()

# 查詢?cè)L問歷史
cursor.execute("SELECT url, title, visit_count FROM urls")
rows = cursor.fetchall()

# 打印歷史記錄
for row in rows:
    print(row)

# 關(guān)閉數(shù)據(jù)庫連接
conn.close()

import sqlite3
import os
from urllib.parse import urlparse
from collections import Counter


def get_top_10_domains():
    # 獲取用戶目錄
    user_profile = os.getenv('USERPROFILE')
    # 構(gòu)建歷史記錄數(shù)據(jù)庫的完整路徑
    history_path = os.path.join(user_profile, r'AppData\Local\Google\Chrome\User Data\Default\History')
    domain_counts = Counter()
    try:
        # 連接歷史記錄數(shù)據(jù)庫
        conn = sqlite3.connect(history_path)
        cursor = conn.cursor()
        # 執(zhí)行 SQL 查詢，從 urls 表中獲取 url 信息
        cursor.execute("SELECT url FROM urls")
        results = cursor.fetchall()
        for result in results:
            url = result[0]
            # 解析 url 獲取域名
            domain = urlparse(url).netloc
            if domain:
                domain_counts[domain] += 1
    except sqlite3.Error as e:
        print(f"SQLite error occurred: {e}")
    finally:
        # 關(guān)閉數(shù)據(jù)庫連接
        conn.close()
    # 獲取前 10 大訪問量最多的域名
    top_10_domains = domain_counts.most_common(10)
    for i, (domain, count) in enumerate(top_10_domains):
        print(f"{i + 1}.  {domain}, Count: {count}")


if __name__ == "__main__":
    get_top_10_domains()

import sqlite3
import os
import jieba
from snownlp import SnowNLP
import numpy as np


def analyze_sentiment():
    # 獲取用戶目錄
    user_profile = os.getenv('USERPROFILE')
    # 構(gòu)建歷史記錄數(shù)據(jù)庫的完整路徑
    history_path = os.path.join(user_profile, r'AppData\Local\Google\Chrome\User Data\Default\History')
    positive_count = 0
    negative_count = 0
    neutral_count = 0
    sentiment_scores = []
    try:
        # 連接歷史記錄數(shù)據(jù)庫
        conn = sqlite3.connect(history_path)
        cursor = conn.cursor()
        # 執(zhí)行 SQL 查詢，從 urls 表中獲取 title 信息
        cursor.execute("SELECT title FROM urls")
        results = cursor.fetchall()
        for result in results:
            title = result[0]
            if title:
                # 使用 jieba 分詞
                words = jieba.cut(title)
                title_text = " ".join(words)
                # 使用 SnowNLP 進(jìn)行情感分析
                s = SnowNLP(title_text)
                sentiment_score = s.sentiments
                sentiment_scores.append(sentiment_score)
                if sentiment_score > 0.6:
                    positive_count += 1
                elif sentiment_score < 0.4:
                    negative_count += 1
                else:
                    neutral_count += 1
    except sqlite3.Error as e:
        print(f"SQLite error occurred: {e}")
    finally:
        # 關(guān)閉數(shù)據(jù)庫連接
        conn.close()
    # 計(jì)算平均情感得分
    if sentiment_scores:
        average_score = np.mean(sentiment_scores)
    else:
        average_score = 0
    # 生成報(bào)告
    print("情感分析報(bào)告：")
    print(f"平均情感得分: {average_score}")
    print(f"積極情感的標(biāo)題數(shù)量: {positive_count}")
    print(f"消極情感的標(biāo)題數(shù)量: {negative_count}")
    print(f"中性情感的標(biāo)題數(shù)量: {neutral_count}")


if __name__ == "__main__":
    analyze_sentiment()

import sqlite3
import os
import jieba
from wordcloud import WordCloud
import matplotlib.pyplot as plt
import numpy as np
from PIL import Image


def get_titles():
    user_profile = os.getenv('USERPROFILE')
    history_path = os.path.join(user_profile, r'AppData\Local\Google\Chrome\User Data\Default\History')
    titles = []
    try:
        conn = sqlite3.connect(history_path)
        cursor = conn.cursor()
        cursor.execute("SELECT title FROM urls")
        results = cursor.fetchall()
        for result in results:
            title = result[0]
            if title:
                titles.append(title)
    except sqlite3.Error as e:
        print(f"SQLite error occurred: {e}")
    finally:
        conn.close()
    return titles


def load_stopwords():
    stopwords = {"了", "的", "么", "是", "在", "有", "和", "就", "都", "而", 
    "及", "與", "也", "很", "并", "之", "其", "此", "但", "一個(gè)", "一些"}
    return stopwords
    
def process_titles(titles):
    stopwords = load_stopwords()
    all_words = []
    for title in titles:
        words = jieba.cut(title)
        for word in words:
            if word not in stopwords:
                all_words.append(word)
    return all_words


def generate_wordcloud(words):
    # 設(shè)置詞云的形狀為 16:9 的長方形
    width = 1600
    height = 900
    mask = np.zeros((height, width), np.uint8)
    wordcloud = WordCloud(width=width, height=height, background_color='white', 
                          font_path="simhei.ttf",
                          stopwords=load_stopwords(), mask=mask).generate(' '.join(words))
    plt.figure(figsize=(16, 9))
    plt.imshow(wordcloud, interpolation='bilinear')
    plt.axis('off')
    plt.show()


if __name__ == "__main__":
    titles = get_titles()
    words = process_titles(titles)
    generate_wordcloud(words)