Export Zen browser workspaces to Chrome-importable HTML bookmarks

zen-to-html-bookmarks.py

#!/usr/bin/env python3
"""
Export Zen browser workspaces to Chrome-importable HTML bookmarks.
Each workspace becomes a bookmark folder; all tabs become bookmarks inside.

Usage:
    python3 zen-to-html-bookmarks.py [output.html]

Requires: lz4  (pip install lz4)
"""

import json
import lz4.block
import os
import struct
import sys
from collections import defaultdict
from pathlib import Path

ZEN_PROFILE = None  # auto-detected from profiles.ini

def find_zen_profile():
    base = Path.home() / "Library/Application Support/zen/Profiles"
    if not base.exists():
        return None
    # Prefer "Default (release)" if it exists
    for name in base.iterdir():
        if "release" in name.name.lower():
            return name / "zen-sessions.jsonlz4"
    # Fall back to first profile found
    profiles = list(base.iterdir())
    if profiles:
        return profiles[0] / "zen-sessions.jsonlz4"
    return None

def read_mozlz4(path):
    with open(path, "rb") as f:
        magic = f.read(8)
        if magic != b"mozLz40\x00":
            raise ValueError(f"Not a mozlz4 file: {path}")
        size = struct.unpack("<I", f.read(4))[0]
        return lz4.block.decompress(f.read(), uncompressed_size=size)

def tab_url_title(tab):
    entries = tab.get("entries", [])
    if not entries:
        return None, None
    idx = min(tab.get("index", len(entries) - 1), len(entries) - 1)
    entry = entries[idx]
    url = entry.get("url", "")
    title = entry.get("title", "") or url
    return url, title

def extract_spaces(d):
    space_map = {s["uuid"]: s["name"] for s in d["spaces"]}
    tabs_by_space = defaultdict(list)

    for tab in d["tabs"]:
        if tab.get("zenIsEmpty"):
            continue
        url, title = tab_url_title(tab)
        if not url or url.startswith("about:") or url.startswith("chrome:"):
            continue
        ws = tab.get("zenWorkspace")
        tabs_by_space[ws].append({"url": url, "title": title})

    spaces = []
    for space in d["spaces"]:
        uuid = space["uuid"]
        name = space["name"] or "Unnamed"
        tabs = tabs_by_space.get(uuid, [])
        spaces.append({"name": name, "tabs": tabs})

    return spaces

def make_html(spaces):
    def esc(s):
        return s.replace("&", "&amp;").replace("<", "&lt;").replace(">", "&gt;").replace('"', "&quot;")

    lines = [
        "<!DOCTYPE NETSCAPE-Bookmark-file-1>",
        '<META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=UTF-8">',
        "<TITLE>Bookmarks</TITLE>",
        "<H1>Bookmarks</H1>",
        "<DL><p>",
        "    <DT><H3>Zen Workspaces</H3>",
        "    <DL><p>",
    ]
    for space in spaces:
        lines.append(f"        <DT><H3>{esc(space['name'])}</H3>")
        lines.append("        <DL><p>")
        for tab in space["tabs"]:
            lines.append(f'            <DT><A HREF="{esc(tab["url"])}">{esc(tab["title"])}</A>')
        lines.append("        </DL><p>")
    lines += ["    </DL><p>", "</DL>"]
    return "\n".join(lines)

def main():
    data_path = find_zen_profile()
    if not data_path or not data_path.exists():
        print("Zen session file not found. Is Zen installed?")
        sys.exit(1)

    args = sys.argv[1:]
    out = Path(args[0]) if args else Path("/tmp/zen_workspaces.html")

    print(f"Reading {data_path} ...")
    raw = read_mozlz4(data_path)
    d = json.loads(raw)

    spaces = extract_spaces(d)
    print(f"Found {len(spaces)} workspaces:")
    for s in spaces:
        print(f"  {s['name']} ({len(s['tabs'])} tabs)")

    out.parent.mkdir(parents=True, exist_ok=True)
    out.write_text(make_html(spaces))
    print(f"\nHTML written to: {out}")
    print("Import via Chrome: chrome://bookmarks → ⋮ → Import bookmarks")
    os.system(f'open "{out}"')

if __name__ == "__main__":
    main()