EEEEH - what I was working on today and yesterday? (Chrome on MacOS version)

eeeeeeh.py

#!/usr/bin/env python3

import sqlite3
import os
import re
import shutil
import tempfile
from datetime import datetime, timedelta, timezone

def get_chrome_history_path():
    """
    Finds the path to the Chrome history file on macOS.
    """
    home = os.path.expanduser("~")
    history_path = os.path.join(
        home, "Library/Application Support/Google/Chrome/Default/History"
    )
    return history_path

def main():
    """
    Main function to query Chrome history for unique GitHub PRs and Issues from the last 24 hours.
    """
    history_db = get_chrome_history_path()
    
    if not os.path.exists(history_db):
        print("Error: Chrome history database not found.")
        print(f"Looked for: {history_db}")
        return

    # Chrome locks its database file while running. We must copy it to a temporary
    # location to avoid the lock and to prevent unnecessary SSD wear.
    temp_dir = tempfile.gettempdir()
    temp_db = os.path.join(temp_dir, f"chrome_history_copy_{os.getpid()}.db")
    
    try:
        shutil.copyfile(history_db, temp_db)

        # Connect to the copied database
        con = sqlite3.connect(temp_db)
        cursor = con.cursor()

        # Calculate the timestamp for 24 hours ago
        # Chrome stores timestamps in microseconds since Jan 1, 1601 (UTC)
        # Use timezone-aware datetimes to avoid deprecation warnings
        time_24_hours_ago = datetime.now(timezone.utc) - timedelta(days=1)
        epoch_start = datetime(1601, 1, 1, tzinfo=timezone.utc)
        chrome_epoch_offset = (time_24_hours_ago - epoch_start).total_seconds() * 1000000
        
        # SQL query to select URLs from the 'urls' table from the last day
        query = f"""
            SELECT url, title 
            FROM urls 
            WHERE last_visit_time > {int(chrome_epoch_offset)}
            ORDER BY last_visit_time DESC
        """

        cursor.execute(query)

        # Use a dictionary to store unique items. In Python 3.7+, dicts preserve
        # insertion order. Since we query with DESC, we'll get items in reverse
        # chronological order of their last visit.
        unique_items = {}
        
        # Regex to match GitHub PRs/Issues and Red Hat Jira issues
        url_pattern = re.compile(
            r"(https://github\.com/.+?/.+?/(pull|issues)/\d+)|"
            r"(https://issues\.redhat\.com/browse/[A-Za-z]+-\d+)"
        )

        for url, title in cursor.fetchall():
            match = url_pattern.match(url)
            if match:
                # To get only the base URL without query params or fragments
                base_url = match.group(0)
                if base_url not in unique_items:
                    unique_items[base_url] = title.strip()
        
        print("--- Activity from the Last 24 Hours (in chronological order) ---")

        if not unique_items:
            print("No unique GitHub or Jira URLs found in the last 24 hours.")
        else:
            # ANSI escape codes for terminal formatting
            BOLD = '\033[1m'
            RESET = '\033[0m'

            # Reverse the dictionary items to print in chronological order
            for url, title in reversed(list(unique_items.items())):
                if "by lzap" in title:
                    print(f"{BOLD}- {title}{RESET}")
                    print(f"{BOLD}  {url}{RESET}\n")
                else:
                    print(f"- {title}")
                    print(f"  {url}\n")

    except (sqlite3.Error, IOError) as e:
        print(f"An error occurred: {e}")
    finally:
        if 'con' in locals() and con:
            con.close()
        # Clean up the temporary database file
        if os.path.exists(temp_db):
            os.remove(temp_db)

if __name__ == "__main__":
    main()