python解析Chrome浏览器历史浏览记录和收藏夹数据
时间：2022-07-09 09:36:52 | 栏目：Python代码 | 点击：次
前言
常使用chrome浏览器作为自己的默认浏览器，也喜欢使用浏览器来收藏自己的喜欢的有用的链接，自己也做了一个记录笔记的小脚本，想扩展收录chrome浏览器收藏夹的内容，，下面，，使用python提取chrome浏览器的历史记录，以及收藏夹。
(一)查询chrome数据缓存地址
1.打开 chrome浏览器,输入 chrome://version，进入浏览器版本信息页面 2.复制页面下图，划线地址
(二)提取收藏夹数据
1.文件路径
上面我的chrome浏览器的缓存路径是：
C:\Users\Administrator\AppData\Local\Google\Chrome\User Data\Default
浏览器的收藏夹的数据，记录在Bookmarks文件里面
Bookmark文件的内容格式是json
2.解析代码
解析代码为
import os
import json
#chrome data path
path = "C:/Users/Administrator/AppData/Local/Google/Chrome/User Data/Default"
#chrome browser bookmark
class BookMark:
def __init__(self,chromePath=path):
#chromepath
self.chromePath = chromePath
#parse bookmarks
with open(os.path.join(path,'Bookmarks'),encoding='utf-8') as f:
bookmarks = json.loads(f.read())
self.bookmarks = bookmarks
#folders
self.folders = self.get_folders()
def get_folders(self):
#folders
names = [
(i,self.bookmarks['roots'][i]['name'])
for i in self.bookmarks['roots']
]
return names
def get_folder_data(self,folder=0):
return self.bookmarks['roots'][self.folders[folder][0]]['children']
def set_chrome_path(self,chromePath):
self.chromePath = chromePath
def refresh(self):
'update chrome data from chrome path'
#parse bookmarks
with open(os.path.join(path,'Bookmarks'),encoding='utf-8') as f:
bookmarks = json.loads(f.read())
self.bookmarks = bookmarks
(三)查看浏览历史数据
1.文件路径
历史数据，存储在下面的History文件里面，内容格式是sqlite的数据库文件，可以直接使用sqlite3来解析，当然也可以使用DB Browser for SQLite来图形化界面显示History sqlite数据文件。
2.解析代码
import os
import sqlite3
#chrome data path
path = "C:/Users/Administrator/AppData/Local/Google/Chrome/User Data/Default"
#History
class History:
def __init__(self,chromePath=path):
self.chromePath = chromePath
def connect(self):
self.conn = sqlite3.connect(os.path.join(self.chromePath,"History"))
self.cousor = self.conn.cursor()
def close(self):
self.conn.close()
def get_history(self):
cursor = self.conn.execute("SELECT id,url,title,visit_count from urls")
rows = []
for _id,url,title,visit_count in cursor:
row = {}
row['id'] = _id
row['url'] = url
row['title'] = title
row['visit_count'] = visit_count
rows.append(row)
return rows
(四)完整代码&测试代码
import os
import sqlite3
#chrome data path
path = "C:/Users/Administrator/AppData/Local/Google/Chrome/User Data/Default"
#History
class History:
def __init__(self,chromePath=path):
self.chromePath = chromePath
def connect(self):
self.conn = sqlite3.connect(os.path.join(self.chromePath,"History"))
self.cousor = self.conn.cursor()
def close(self):
self.conn.close()
def get_history(self):
cursor = self.conn.execute("SELECT id,url,title,visit_count from urls")
rows = []
for _id,url,title,visit_count in cursor:
row = {}
row['id'] = _id
row['url'] = url
row['title'] = title
row['visit_count'] = visit_count
rows.append(row)
return rows