Initial commit

app/browser.py

@@ -0,0 +1,18 @@
+from datetime import datetime
+from typing import List, Tuple
+from browser_history import get_history, get_bookmarks
+from urllib.parse import urlparse
+
+class BrowserHistoryCollector:
+    @staticmethod
+    def get_domain(url: str) -> str:
+        return urlparse(url).netloc
+
+    def fetch_history(self) -> List[Tuple[datetime, str, str]]:
+        outputs = get_history()
+        # Returns list of tuples containing (datetime, url, title)
+        return [(entry[0], entry[1], entry[2]) for entry in outputs.histories]
+
+    def fetch_bookmarks(self) -> List[Tuple[datetime, str, str, str]]:
+        outputs = get_bookmarks()
+        return outputs.bookmarks

app/database.py

@@ -0,0 +1,38 @@
+from sqlalchemy import create_engine, Column, Integer, String, DateTime
+from sqlalchemy.ext.declarative import declarative_base
+from sqlalchemy.orm import sessionmaker
+
+SQLALCHEMY_DATABASE_URL = "sqlite:///./browser_history.db"
+
+engine = create_engine(SQLALCHEMY_DATABASE_URL)
+SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
+
+Base = declarative_base()
+
+class HistoryEntry(Base):
+    __tablename__ = "history_entries"
+
+    id = Column(Integer, primary_key=True, index=True)
+    url = Column(String, index=True)
+    title = Column(String, nullable=True)
+    visit_time = Column(DateTime, index=True)
+    domain = Column(String, index=True)
+
+class Bookmark(Base):
+    __tablename__ = "bookmarks"
+
+    id = Column(Integer, primary_key=True, index=True)
+    url = Column(String, index=True)
+    title = Column(String, nullable=True)
+    added_time = Column(DateTime, index=True)
+    folder = Column(String, index=True)
+    domain = Column(String, index=True)
+
+Base.metadata.create_all(bind=engine)
+
+def get_db():
+    db = SessionLocal()
+    try:
+        yield db
+    finally:
+        db.close()

app/main.py

@@ -0,0 +1,62 @@
+from fastapi import FastAPI, Depends, Query
+from sqlalchemy.orm import Session
+from datetime import datetime
+from typing import List
+import asyncio
+
+from .database import get_db, HistoryEntry, Bookmark
+from .scheduler import HistoryScheduler
+
+app = FastAPI()
+scheduler = HistoryScheduler()
+
+@app.on_event("startup")
+async def startup_event():
+    # Initial bookmark fetch
+    await scheduler.update_bookmarks()
+    # Start the background task
+    asyncio.create_task(scheduler.update_history())
+
+@app.get("/history/search")
+async def search_history(
+    domain: str = Query(None),
+    start_date: datetime = Query(None),
+    end_date: datetime = Query(None),
+    search_term: str = Query(None),
+    db: Session = Depends(get_db)
+):
+    query = db.query(HistoryEntry)
+
+    if domain:
+        query = query.filter(HistoryEntry.domain == domain)
+
+    if start_date:
+        query = query.filter(HistoryEntry.visit_time >= start_date)
+
+    if end_date:
+        query = query.filter(HistoryEntry.visit_time <= end_date)
+
+    if search_term:
+        query = query.filter(HistoryEntry.title.ilike(f"%{search_term}%"))
+
+    return query.all()
+
+@app.get("/bookmarks/search")
+async def search_bookmarks(
+    domain: str = Query(None),
+    folder: str = Query(None),
+    search_term: str = Query(None),
+    db: Session = Depends(get_db)
+):
+    query = db.query(Bookmark)
+
+    if domain:
+        query = query.filter(Bookmark.domain == domain)
+
+    if folder:
+        query = query.filter(Bookmark.folder == folder)
+
+    if search_term:
+        query = query.filter(Bookmark.title.ilike(f"%{search_term}%"))
+
+    return query.all()

app/page_info.py

@@ -0,0 +1,16 @@
+import asyncio
+import aiohttp
+from bs4 import BeautifulSoup
+from typing import Optional
+
+class PageInfoFetcher:
+    async def get_page_title(self, url: str) -> Optional[str]:
+        try:
+            async with aiohttp.ClientSession() as session:
+                async with session.get(url, timeout=5) as response:
+                    if response.status == 200:
+                        html = await response.text()
+                        soup = BeautifulSoup(html, 'html.parser')
+                        return soup.title.string if soup.title else None
+        except:
+            return None

app/scheduler.py

@@ -0,0 +1,85 @@
+from fastapi import BackgroundTasks
+from datetime import datetime, timedelta
+import asyncio
+from .database import SessionLocal, HistoryEntry, Bookmark
+from .browser import BrowserHistoryCollector
+from .page_info import PageInfoFetcher
+from sqlalchemy import func
+
+class HistoryScheduler:
+    def __init__(self):
+        self.browser_collector = BrowserHistoryCollector()
+        self.page_fetcher = PageInfoFetcher()
+        self.last_history_update = None
+
+    async def update_bookmarks(self):
+        bookmarks = self.browser_collector.fetch_bookmarks()
+
+        db = SessionLocal()
+        try:
+            # First, get all existing URLs to avoid duplicates
+            existing_urls = {
+                url: (added_time, folder)
+                for url, added_time, folder in
+                db.query(Bookmark.url, Bookmark.added_time, Bookmark.folder).all()
+            }
+
+            new_entries = []
+            for added_time, url, title, folder in bookmarks:
+                # Only add if URL doesn't exist or if it's in a different folder
+                if (url not in existing_urls or
+                    existing_urls[url][1] != folder):
+                    domain = self.browser_collector.get_domain(url)
+                    entry = Bookmark(
+                        url=url,
+                        title=title,
+                        added_time=added_time,
+                        folder=folder,
+                        domain=domain
+                    )
+                    new_entries.append(entry)
+
+            if new_entries:
+                db.bulk_save_objects(new_entries)
+                db.commit()
+        finally:
+            db.close()
+
+    async def update_history(self):
+        while True:
+            db = SessionLocal()
+            try:
+                # Get the latest timestamp from our database
+                latest_entry = db.query(func.max(HistoryEntry.visit_time)).scalar()
+
+                # Fetch new history
+                history = self.browser_collector.fetch_history()
+
+                # Filter to only get entries newer than our latest entry
+                new_entries = []
+                for visit_time, url, title in history:
+                    if not latest_entry or visit_time > latest_entry:
+                        domain = self.browser_collector.get_domain(url)
+                        if not title:
+                            title = await self.page_fetcher.get_page_title(url)
+
+                        entry = HistoryEntry(
+                            url=url,
+                            title=title,
+                            visit_time=visit_time,
+                            domain=domain
+                        )
+                        new_entries.append(entry)
+
+                if new_entries:
+                    db.bulk_save_objects(new_entries)
+                    db.commit()
+
+                # Update bookmarks
+                await self.update_bookmarks()
+
+            finally:
+                db.close()
+
+            # Wait for 5 minutes before next update
+            await asyncio.sleep(300)