怎么使用python提取chrome浏览器的历史记录及收藏夹

# 怎么使用Python提取Chrome浏览器的历史记录及收藏夹

## 引言

在日常使用浏览器时，我们会积累大量的历史记录和收藏夹数据。这些数据不仅反映了我们的浏览习惯，还可能包含重要的工作或学习资料。本文将详细介绍如何使用Python提取Chrome浏览器的历史记录和收藏夹数据，并对其进行处理和分析。

## 准备工作

### 1. 安装必要的Python库

我们需要安装以下几个Python库：

```bash
pip install sqlite3
pip install pandas
pip install pywin32  # Windows系统需要
pip install pyobjc  # macOS系统需要

import sqlite3
import pandas as pd

# Chrome历史记录文件路径
history_path = "C:\\Users\\<用户名>\\AppData\\Local\\Google\\Chrome\\User Data\\Default\\History"

# 复制文件以避免锁定问题
import shutil
import os

temp_path = "temp_history"
shutil.copy2(history_path, temp_path)

# 连接数据库
conn = sqlite3.connect(temp_path)
cursor = conn.cursor()

# 执行查询
cursor.execute("SELECT title, url, last_visit_time FROM urls ORDER BY last_visit_time DESC")

# 获取结果
history = cursor.fetchall()

# 转换为DataFrame
history_df = pd.DataFrame(history, columns=["标题", "URL", "最后访问时间"])

# 关闭连接
conn.close()
os.remove(temp_path)  # 删除临时文件

def chrome_time_to_datetime(chrometime):
    return pd.to_datetime(chrometime/1e6 - 11644473600, unit='s')

history_df["访问时间"] = history_df["最后访问时间"].apply(chrome_time_to_datetime)
history_df.drop("最后访问时间", axis=1, inplace=True)

history_df.to_csv("chrome_history.csv", index=False, encoding='utf-8-sig')

import json

bookmarks_path = "C:\\Users\\<用户名>\\AppData\\Local\\Google\\Chrome\\User Data\\Default\\Bookmarks"

with open(bookmarks_path, "r", encoding="utf-8") as f:
    bookmarks_data = json.load(f)

def extract_bookmarks(bookmark_item, folder_path=""):
    bookmarks = []
    
    if "children" in bookmark_item:
        # 这是一个文件夹
        new_folder = f"{folder_path}/{bookmark_item['name']}"
        for child in bookmark_item["children"]:
            bookmarks.extend(extract_bookmarks(child, new_folder))
    elif "url" in bookmark_item:
        # 这是一个书签
        bookmarks.append({
            "标题": bookmark_item["name"],
            "URL": bookmark_item["url"],
            "文件夹路径": folder_path,
            "添加日期": pd.to_datetime(bookmark_item.get("date_added", 0)/1e6 - 11644473600, 
            unit='s') if "date_added" in bookmark_item else None
        })
    
    return bookmarks

# 提取所有书签
all_bookmarks = []
for root in ["bookmark_bar", "other", "synced"]:
    if root in bookmarks_data["roots"]:
        all_bookmarks.extend(extract_bookmarks(bookmarks_data["roots"][root]))

bookmarks_df = pd.DataFrame(all_bookmarks)
bookmarks_df.to_csv("chrome_bookmarks.csv", index=False, encoding='utf-8-sig')

# 按小时分析浏览习惯
history_df["小时"] = history_df["访问时间"].dt.hour
hourly_activity = history_df["小时"].value_counts().sort_index()

# 绘制图表
import matplotlib.pyplot as plt

hourly_activity.plot(kind="bar")
plt.title("按小时分布的浏览活动")
plt.xlabel("小时")
plt.ylabel("访问次数")
plt.savefig("hourly_activity.png")

# 提取域名
import urllib.parse

def extract_domain(url):
    try:
        return urllib.parse.urlparse(url).netloc
    except:
        return None

history_df["域名"] = history_df["URL"].apply(extract_domain)
top_domains = history_df["域名"].value_counts().head(20)

top_domains.plot(kind="barh")
plt.title("访问最频繁的网站")
plt.savefig("top_domains.png")

# 找出重复收藏的URL
duplicate_urls = bookmarks_df[bookmarks_df.duplicated("URL", keep=False)]
duplicate_urls.to_csv("duplicate_bookmarks.csv", index=False)

import platform

def get_chrome_data_path():
    system = platform.system()
    username = os.getlogin()
    
    if system == "Windows":
        return f"C:\\Users\\{username}\\AppData\\Local\\Google\\Chrome\\User Data\\Default"
    elif system == "Darwin":  # macOS
        return f"/Users/{username}/Library/Application Support/Google/Chrome/Default"
    elif system == "Linux":
        return f"/home/{username}/.config/google-chrome/Default"
    else:
        raise Exception("Unsupported operating system")

def get_chrome_history():
    data_path = get_chrome_data_path()
    history_path = os.path.join(data_path, "History")
    
    try:
        # 直接尝试连接
        return sqlite3.connect(history_path)
    except sqlite3.OperationalError:
        # 如果失败，尝试复制文件
        temp_path = "temp_history"
        shutil.copy2(history_path, temp_path)
        return sqlite3.connect(temp_path)

# chrome_data_extractor.py

import sqlite3
import pandas as pd
import json
import os
import shutil
import urllib.parse
import platform
from datetime import datetime

class ChromeDataExtractor:
    def __init__(self):
        self.data_path = self._get_chrome_data_path()
    
    def _get_chrome_data_path(self):
        system = platform.system()
        username = os.getlogin()
        
        if system == "Windows":
            return f"C:\\Users\\{username}\\AppData\\Local\\Google\\Chrome\\User Data\\Default"
        elif system == "Darwin":  # macOS
            return f"/Users/{username}/Library/Application Support/Google/Chrome/Default"
        elif system == "Linux":
            return f"/home/{username}/.config/google-chrome/Default"
        else:
            raise Exception("Unsupported operating system")
    
    def _chrome_time_to_datetime(self, chrometime):
        if pd.isna(chrometime) or chrometime == 0:
            return None
        return datetime(1601, 1, 1) + pd.Timedelta(microseconds=chrometime)
    
    def get_history(self, save_to_csv=True):
        history_path = os.path.join(self.data_path, "History")
        temp_path = "temp_history"
        
        try:
            shutil.copy2(history_path, temp_path)
            conn = sqlite3.connect(temp_path)
            cursor = conn.cursor()
            
            cursor.execute("""
                SELECT urls.title, urls.url, urls.visit_count, 
                       urls.last_visit_time, visits.visit_time, visits.from_visit
                FROM urls
                LEFT JOIN visits ON urls.id = visits.url
                ORDER BY visits.visit_time DESC
            """)
            
            history = cursor.fetchall()
            history_df = pd.DataFrame(history, columns=[
                "标题", "URL", "访问次数", "最后访问时间", "访问时间", "来源访问"
            ])
            
            # 转换时间格式
            history_df["访问时间"] = history_df["访问时间"].apply(self._chrome_time_to_datetime)
            history_df["最后访问时间"] = history_df["最后访问时间"].apply(self._chrome_time_to_datetime)
            
            # 提取域名
            history_df["域名"] = history_df["URL"].apply(
                lambda x: urllib.parse.urlparse(x).netloc if pd.notna(x) else None
            )
            
            if save_to_csv:
                history_df.to_csv("chrome_history.csv", index=False, encoding='utf-8-sig')
            
            return history_df
        
        finally:
            conn.close()
            if os.path.exists(temp_path):
                os.remove(temp_path)
    
    def get_bookmarks(self, save_to_csv=True):
        bookmarks_path = os.path.join(self.data_path, "Bookmarks")
        
        with open(bookmarks_path, "r", encoding="utf-8") as f:
            bookmarks_data = json.load(f)
        
        def extract_bookmarks(bookmark_item, folder_path=""):
            bookmarks = []
            
            if "children" in bookmark_item:
                new_folder = f"{folder_path}/{bookmark_item['name']}" if folder_path else bookmark_item['name']
                for child in bookmark_item["children"]:
                    bookmarks.extend(extract_bookmarks(child, new_folder))
            elif "url" in bookmark_item:
                bookmarks.append({
                    "标题": bookmark_item["name"],
                    "URL": bookmark_item["url"],
                    "文件夹路径": folder_path,
                    "添加日期": self._chrome_time_to_datetime(bookmark_item.get("date_added"))
                })
            
            return bookmarks
        
        all_bookmarks = []
        for root in ["bookmark_bar", "other", "synced"]:
            if root in bookmarks_data["roots"]:
                all_bookmarks.extend(extract_bookmarks(bookmarks_data["roots"][root]))
        
        bookmarks_df = pd.DataFrame(all_bookmarks)
        
        if save_to_csv:
            bookmarks_df.to_csv("chrome_bookmarks.csv", index=False, encoding='utf-8-sig')
        
        return bookmarks_df

if __name__ == "__main__":
    extractor = ChromeDataExtractor()
    
    print("正在提取Chrome历史记录...")
    history_df = extractor.get_history()
    print(f"提取到 {len(history_df)} 条历史记录")
    
    print("\n正在提取Chrome收藏夹...")
    bookmarks_df = extractor.get_bookmarks()
    print(f"提取到 {len(bookmarks_df)} 个收藏项")
    
    print("\n操作完成！")