From 36252f6f19ac5284687c228a56b9e8b12a970055 Mon Sep 17 00:00:00 2001
From: Marty Oehme <contact@martyoeh.me>
Date: Wed, 12 Mar 2025 14:16:59 +0100
Subject: [PATCH] Add shaarli2hoarder
---
pyproject.toml | 11 ++++-
shaarli2hoarder/.gitignore | 14 ++++++
shaarli2hoarder/.python-version | 1 +
shaarli2hoarder/README.md | 12 +++++
shaarli2hoarder/convert.py | 80 +++++++++++++++++++++++++++++++++
5 files changed, 117 insertions(+), 1 deletion(-)
create mode 100644 shaarli2hoarder/.gitignore
create mode 100644 shaarli2hoarder/.python-version
create mode 100644 shaarli2hoarder/README.md
create mode 100644 shaarli2hoarder/convert.py
diff --git a/pyproject.toml b/pyproject.toml
index d8a4b28..93a02e4 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -4,7 +4,16 @@ version = "0.1.0"
description = "Add your description here"
readme = "README.md"
requires-python = ">=3.13"
-dependencies = []
+dependencies = [
+ # REQUIRED FOR CURRENT SHAARLI2HOARDER IMPLEMENTATION ONLY
+ # "beautifulsoup4>=4.13.3",
+ # "netscape-bookmarks-file-parser",
+ # "pyjwt>=2.10.1",
+ # "requests>=2.32.3",
+]
[tool.pyright]
typeCheckingMode = "basic"
+
+[tool.uv.sources]
+netscape-bookmarks-file-parser = { git = "https://github.com/FlyingWolFox/Netscape-Bookmarks-File-Parser.git" }
diff --git a/shaarli2hoarder/.gitignore b/shaarli2hoarder/.gitignore
new file mode 100644
index 0000000..97d03a5
--- /dev/null
+++ b/shaarli2hoarder/.gitignore
@@ -0,0 +1,14 @@
+*.json
+*.html
+
+# Python-generated files
+__pycache__/
+*.py[oc]
+build/
+dist/
+wheels/
+*.egg-info
+
+# Virtual environments
+.venv
+
diff --git a/shaarli2hoarder/.python-version b/shaarli2hoarder/.python-version
new file mode 100644
index 0000000..24ee5b1
--- /dev/null
+++ b/shaarli2hoarder/.python-version
@@ -0,0 +1 @@
+3.13
diff --git a/shaarli2hoarder/README.md b/shaarli2hoarder/README.md
new file mode 100644
index 0000000..d89281d
--- /dev/null
+++ b/shaarli2hoarder/README.md
@@ -0,0 +1,12 @@
+# Shaarli 2 Hoarder converter
+
+Convert your shaarli bookmarks to hoarder json format.
+
+Simply run it like the following `uv run python convert.py <shaarli-export-file>`,
+pointing th efile at your exported html file from shaarli.
+
+It will print out the JSON representation of those bookmarks,
+readable by Hoarder.
+
+Run it like the following `uv run python convert.py bookmarks.html > out.json`
+to generate a valid json file which you can then import thorugh the hoarder interface.
diff --git a/shaarli2hoarder/convert.py b/shaarli2hoarder/convert.py
new file mode 100644
index 0000000..428e5b9
--- /dev/null
+++ b/shaarli2hoarder/convert.py
@@ -0,0 +1,80 @@
+import json
+import sys
+
+from bs4 import BeautifulSoup
+
+if len(sys.argv) < 2:
+ print("ERROR: Pass the bookmarks file as argument.")
+ sys.exit(1)
+path = sys.argv[1]
+
+
+def parse_bookmark(html_content):
+ soup = BeautifulSoup(html_content, "html.parser")
+
+ bookmarks = []
+
+ if len(soup.find_all("dl")) != 1:
+ print("WARNING! More than one Bookmark element found. File may be corrupt.")
+
+ first = True
+ last_desc = ""
+ for el in soup.find_all("a"):
+ bm_el = {}
+ url = el["href"]
+ title = el.string.strip() if el.string else url
+
+ # date elements
+ add_date = el.get("add_date", "")
+ last_modified = el.get("last_modified", "")
+ tag_string = el.get("tags", "")
+ tags = tag_string.split(",") if tag_string else []
+
+ # TODO: url contains '/shaare/' == note type
+
+ # desc / note
+ desc_el = el.parent.find_next_sibling("dd")
+ # Have to fix the non-closed <dt> tabs :\
+ # For now, in vim do: `:%s/<DT>.*/\0<\/DT>` to add a closing el to each line
+ description = desc_el.contents[0].strip() if desc_el else ""
+ if description and description == last_desc:
+ description = ""
+ if description:
+ last_desc = description
+
+ # print(f"URL: {url}, TITLE: {title}")
+ # print(f"ADD: {add_date}, MOD: {last_modified}, TAGS: {tags}")
+ # print(f"DESC: {description.strip()}")
+
+ content = {}
+ if "/shaare/" in url:
+ content = {"type": "text", "text": description}
+ # print(f"Detected note-style url ({url}) turning description to content.")
+ description = ""
+ else:
+ content = {"type": "link", "url": url}
+
+ bm_el = {
+ "title": title,
+ "note": description,
+ "createdAt": int(last_modified if last_modified else add_date),
+ "content": content,
+ }
+ if tags:
+ bm_el["tags"] = tags
+ if description:
+ bm_el["note"] = description
+ bookmarks.append(bm_el)
+
+ return bookmarks
+
+
+with open(path) as f:
+ contents = f.readlines()
+ for i, line in enumerate(contents):
+ if "<DT>" in line:
+ contents[i] = f"{line.rstrip()}</DT>"
+
+ bookmarks = parse_bookmark("\n".join(contents))
+
+ print(json.dumps({"bookmarks": bookmarks}, indent=2))