commit c8e19db44cfd42305fd7a8a0361b181d92493a14
Author: Marty Oehme <marty.oehme@gmail.com>
Date: Wed Feb 12 18:24:24 2025 +0100
initial commit
diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..9a1a506
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,14 @@
+/*.json
+/*.html
+
+# Python-generated files
+__pycache__/
+*.py[oc]
+build/
+dist/
+wheels/
+*.egg-info
+
+# Virtual environments
+.venv
+
diff --git a/.python-version b/.python-version
new file mode 100644
index 0000000..24ee5b1
--- /dev/null
+++ b/.python-version
@@ -0,0 +1 @@
+3.13
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..d89281d
--- /dev/null
+++ b/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/convert.py b/convert.py
new file mode 100644
index 0000000..428e5b9
--- /dev/null
+++ b/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))
diff --git a/pyproject.toml b/pyproject.toml
new file mode 100644
index 0000000..07abefc
--- /dev/null
+++ b/pyproject.toml
@@ -0,0 +1,18 @@
+[project]
+name = "shaarli2hoarder"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.13"
+dependencies = [
+ "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/uv.lock b/uv.lock
new file mode 100644
index 0000000..1ba420f
--- /dev/null
+++ b/uv.lock
@@ -0,0 +1,130 @@
+version = 1
+requires-python = ">=3.13"
+
+[[package]]
+name = "beautifulsoup4"
+version = "4.13.3"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+ { name = "soupsieve" },
+ { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/f0/3c/adaf39ce1fb4afdd21b611e3d530b183bb7759c9b673d60db0e347fd4439/beautifulsoup4-4.13.3.tar.gz", hash = "sha256:1bd32405dacc920b42b83ba01644747ed77456a65760e285fbc47633ceddaf8b", size = 619516 }
+wheels = [
+ { url = "https://files.pythonhosted.org/packages/f9/49/6abb616eb3cbab6a7cca303dc02fdf3836de2e0b834bf966a7f5271a34d8/beautifulsoup4-4.13.3-py3-none-any.whl", hash = "sha256:99045d7d3f08f91f0d656bc9b7efbae189426cd913d830294a15eefa0ea4df16", size = 186015 },
+]
+
+[[package]]
+name = "certifi"
+version = "2025.1.31"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/1c/ab/c9f1e32b7b1bf505bf26f0ef697775960db7932abeb7b516de930ba2705f/certifi-2025.1.31.tar.gz", hash = "sha256:3d5da6925056f6f18f119200434a4780a94263f10d1c21d032a6f6b2baa20651", size = 167577 }
+wheels = [
+ { url = "https://files.pythonhosted.org/packages/38/fc/bce832fd4fd99766c04d1ee0eead6b0ec6486fb100ae5e74c1d91292b982/certifi-2025.1.31-py3-none-any.whl", hash = "sha256:ca78db4565a652026a4db2bcdf68f2fb589ea80d0be70e03929ed730746b84fe", size = 166393 },
+]
+
+[[package]]
+name = "charset-normalizer"
+version = "3.4.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/16/b0/572805e227f01586461c80e0fd25d65a2115599cc9dad142fee4b747c357/charset_normalizer-3.4.1.tar.gz", hash = "sha256:44251f18cd68a75b56585dd00dae26183e102cd5e0f9f1466e6df5da2ed64ea3", size = 123188 }
+wheels = [
+ { url = "https://files.pythonhosted.org/packages/38/94/ce8e6f63d18049672c76d07d119304e1e2d7c6098f0841b51c666e9f44a0/charset_normalizer-3.4.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:aabfa34badd18f1da5ec1bc2715cadc8dca465868a4e73a0173466b688f29dda", size = 195698 },
+ { url = "https://files.pythonhosted.org/packages/24/2e/dfdd9770664aae179a96561cc6952ff08f9a8cd09a908f259a9dfa063568/charset_normalizer-3.4.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:22e14b5d70560b8dd51ec22863f370d1e595ac3d024cb8ad7d308b4cd95f8313", size = 140162 },
+ { url = "https://files.pythonhosted.org/packages/24/4e/f646b9093cff8fc86f2d60af2de4dc17c759de9d554f130b140ea4738ca6/charset_normalizer-3.4.1-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8436c508b408b82d87dc5f62496973a1805cd46727c34440b0d29d8a2f50a6c9", size = 150263 },
+ { url = "https://files.pythonhosted.org/packages/5e/67/2937f8d548c3ef6e2f9aab0f6e21001056f692d43282b165e7c56023e6dd/charset_normalizer-3.4.1-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2d074908e1aecee37a7635990b2c6d504cd4766c7bc9fc86d63f9c09af3fa11b", size = 142966 },
+ { url = "https://files.pythonhosted.org/packages/52/ed/b7f4f07de100bdb95c1756d3a4d17b90c1a3c53715c1a476f8738058e0fa/charset_normalizer-3.4.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:955f8851919303c92343d2f66165294848d57e9bba6cf6e3625485a70a038d11", size = 144992 },
+ { url = "https://files.pythonhosted.org/packages/96/2c/d49710a6dbcd3776265f4c923bb73ebe83933dfbaa841c5da850fe0fd20b/charset_normalizer-3.4.1-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:44ecbf16649486d4aebafeaa7ec4c9fed8b88101f4dd612dcaf65d5e815f837f", size = 147162 },
+ { url = "https://files.pythonhosted.org/packages/b4/41/35ff1f9a6bd380303dea55e44c4933b4cc3c4850988927d4082ada230273/charset_normalizer-3.4.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:0924e81d3d5e70f8126529951dac65c1010cdf117bb75eb02dd12339b57749dd", size = 140972 },
+ { url = "https://files.pythonhosted.org/packages/fb/43/c6a0b685fe6910d08ba971f62cd9c3e862a85770395ba5d9cad4fede33ab/charset_normalizer-3.4.1-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:2967f74ad52c3b98de4c3b32e1a44e32975e008a9cd2a8cc8966d6a5218c5cb2", size = 149095 },
+ { url = "https://files.pythonhosted.org/packages/4c/ff/a9a504662452e2d2878512115638966e75633519ec11f25fca3d2049a94a/charset_normalizer-3.4.1-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:c75cb2a3e389853835e84a2d8fb2b81a10645b503eca9bcb98df6b5a43eb8886", size = 152668 },
+ { url = "https://files.pythonhosted.org/packages/6c/71/189996b6d9a4b932564701628af5cee6716733e9165af1d5e1b285c530ed/charset_normalizer-3.4.1-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:09b26ae6b1abf0d27570633b2b078a2a20419c99d66fb2823173d73f188ce601", size = 150073 },
+ { url = "https://files.pythonhosted.org/packages/e4/93/946a86ce20790e11312c87c75ba68d5f6ad2208cfb52b2d6a2c32840d922/charset_normalizer-3.4.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:fa88b843d6e211393a37219e6a1c1df99d35e8fd90446f1118f4216e307e48cd", size = 145732 },
+ { url = "https://files.pythonhosted.org/packages/cd/e5/131d2fb1b0dddafc37be4f3a2fa79aa4c037368be9423061dccadfd90091/charset_normalizer-3.4.1-cp313-cp313-win32.whl", hash = "sha256:eb8178fe3dba6450a3e024e95ac49ed3400e506fd4e9e5c32d30adda88cbd407", size = 95391 },
+ { url = "https://files.pythonhosted.org/packages/27/f2/4f9a69cc7712b9b5ad8fdb87039fd89abba997ad5cbe690d1835d40405b0/charset_normalizer-3.4.1-cp313-cp313-win_amd64.whl", hash = "sha256:b1ac5992a838106edb89654e0aebfc24f5848ae2547d22c2c3f66454daa11971", size = 102702 },
+ { url = "https://files.pythonhosted.org/packages/0e/f6/65ecc6878a89bb1c23a086ea335ad4bf21a588990c3f535a227b9eea9108/charset_normalizer-3.4.1-py3-none-any.whl", hash = "sha256:d98b1668f06378c6dbefec3b92299716b931cd4e6061f3c875a71ced1780ab85", size = 49767 },
+]
+
+[[package]]
+name = "idna"
+version = "3.10"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f1/70/7703c29685631f5a7590aa73f1f1d3fa9a380e654b86af429e0934a32f7d/idna-3.10.tar.gz", hash = "sha256:12f65c9b470abda6dc35cf8e63cc574b1c52b11df2c86030af0ac09b01b13ea9", size = 190490 }
+wheels = [
+ { url = "https://files.pythonhosted.org/packages/76/c6/c88e154df9c4e1a2a66ccf0005a88dfb2650c1dffb6f5ce603dfbd452ce3/idna-3.10-py3-none-any.whl", hash = "sha256:946d195a0d259cbba61165e88e65941f16e9b36ea6ddb97f00452bae8b1287d3", size = 70442 },
+]
+
+[[package]]
+name = "netscape-bookmarks-file-parser"
+version = "1.1"
+source = { git = "https://github.com/FlyingWolFox/Netscape-Bookmarks-File-Parser.git#dd442165dcb8ecc32e03f1dffe84cb7b983522e9" }
+
+[[package]]
+name = "pyjwt"
+version = "2.10.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/e7/46/bd74733ff231675599650d3e47f361794b22ef3e3770998dda30d3b63726/pyjwt-2.10.1.tar.gz", hash = "sha256:3cc5772eb20009233caf06e9d8a0577824723b44e6648ee0a2aedb6cf9381953", size = 87785 }
+wheels = [
+ { url = "https://files.pythonhosted.org/packages/61/ad/689f02752eeec26aed679477e80e632ef1b682313be70793d798c1d5fc8f/PyJWT-2.10.1-py3-none-any.whl", hash = "sha256:dcdd193e30abefd5debf142f9adfcdd2b58004e644f25406ffaebd50bd98dacb", size = 22997 },
+]
+
+[[package]]
+name = "requests"
+version = "2.32.3"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+ { name = "certifi" },
+ { name = "charset-normalizer" },
+ { name = "idna" },
+ { name = "urllib3" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/63/70/2bf7780ad2d390a8d301ad0b550f1581eadbd9a20f896afe06353c2a2913/requests-2.32.3.tar.gz", hash = "sha256:55365417734eb18255590a9ff9eb97e9e1da868d4ccd6402399eaf68af20a760", size = 131218 }
+wheels = [
+ { url = "https://files.pythonhosted.org/packages/f9/9b/335f9764261e915ed497fcdeb11df5dfd6f7bf257d4a6a2a686d80da4d54/requests-2.32.3-py3-none-any.whl", hash = "sha256:70761cfe03c773ceb22aa2f671b4757976145175cdfca038c02654d061d6dcc6", size = 64928 },
+]
+
+[[package]]
+name = "shaarli2hoarder"
+version = "0.1.0"
+source = { virtual = "." }
+dependencies = [
+ { name = "beautifulsoup4" },
+ { name = "netscape-bookmarks-file-parser" },
+ { name = "pyjwt" },
+ { name = "requests" },
+]
+
+[package.metadata]
+requires-dist = [
+ { name = "beautifulsoup4", specifier = ">=4.13.3" },
+ { name = "netscape-bookmarks-file-parser", git = "https://github.com/FlyingWolFox/Netscape-Bookmarks-File-Parser.git" },
+ { name = "pyjwt", specifier = ">=2.10.1" },
+ { name = "requests", specifier = ">=2.32.3" },
+]
+
+[[package]]
+name = "soupsieve"
+version = "2.6"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/d7/ce/fbaeed4f9fb8b2daa961f90591662df6a86c1abf25c548329a86920aedfb/soupsieve-2.6.tar.gz", hash = "sha256:e2e68417777af359ec65daac1057404a3c8a5455bb8abc36f1a9866ab1a51abb", size = 101569 }
+wheels = [
+ { url = "https://files.pythonhosted.org/packages/d1/c2/fe97d779f3ef3b15f05c94a2f1e3d21732574ed441687474db9d342a7315/soupsieve-2.6-py3-none-any.whl", hash = "sha256:e72c4ff06e4fb6e4b5a9f0f55fe6e81514581fca1515028625d0f299c602ccc9", size = 36186 },
+]
+
+[[package]]
+name = "typing-extensions"
+version = "4.12.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/df/db/f35a00659bc03fec321ba8bce9420de607a1d37f8342eee1863174c69557/typing_extensions-4.12.2.tar.gz", hash = "sha256:1a7ead55c7e559dd4dee8856e3a88b41225abfe1ce8df57b7c13915fe121ffb8", size = 85321 }
+wheels = [
+ { url = "https://files.pythonhosted.org/packages/26/9f/ad63fc0248c5379346306f8668cda6e2e2e9c95e01216d2b8ffd9ff037d0/typing_extensions-4.12.2-py3-none-any.whl", hash = "sha256:04e5ca0351e0f3f85c6853954072df659d0d13fac324d0072316b67d7794700d", size = 37438 },
+]
+
+[[package]]
+name = "urllib3"
+version = "2.3.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/aa/63/e53da845320b757bf29ef6a9062f5c669fe997973f966045cb019c3f4b66/urllib3-2.3.0.tar.gz", hash = "sha256:f8c5449b3cf0861679ce7e0503c7b44b5ec981bec0d1d3795a07f1ba96f0204d", size = 307268 }
+wheels = [
+ { url = "https://files.pythonhosted.org/packages/c8/19/4ec628951a74043532ca2cf5d97b7b14863931476d117c471e8e2b1eb39f/urllib3-2.3.0-py3-none-any.whl", hash = "sha256:1cee9ad369867bfdbbb48b7dd50374c0967a0bb7710050facf0dd6911440e3df", size = 128369 },
+]