aboutsummaryrefslogtreecommitdiff
path: root/gemini-to-web
diff options
context:
space:
mode:
authoralex <alex@pdp7.net>2026-02-15 10:42:00 +0100
committeralex <alex@pdp7.net>2026-02-15 10:42:00 +0100
commitcc5d4e07146da033ded55c216b41378bca9a10b4 (patch)
tree0fb4e8dff5d64a9c47d02706716e4377a81a6d04 /gemini-to-web
parent144273180f8b4fdcc3356bbe72c7bdc799f2c6eb (diff)
Add RSS generation
Remove old deprecated CLI converter in __init__
Diffstat (limited to 'gemini-to-web')
-rw-r--r--gemini-to-web/README.md3
-rwxr-xr-xgemini-to-web/example/build.sh4
-rw-r--r--gemini-to-web/pyproject.toml2
-rw-r--r--gemini-to-web/src/gemini_to_web/__init__.py25
-rw-r--r--gemini-to-web/src/gemini_to_web/indexer.py8
-rw-r--r--gemini-to-web/src/gemini_to_web/rss.py63
-rw-r--r--gemini-to-web/uv.lock33
7 files changed, 109 insertions, 29 deletions
diff --git a/gemini-to-web/README.md b/gemini-to-web/README.md
index 503fc8c..2c492db 100644
--- a/gemini-to-web/README.md
+++ b/gemini-to-web/README.md
@@ -33,4 +33,7 @@ $ uv run coppewebite-to-html <<EOT
`coppewebite-indexer` outputs a list of gemtext links, sorted in reverse chronological order, suitable for use as a Gemini page subscription.
You can use `coppewebite-indexer` to create a gemlog index automatically.
+
+`coppewebite-to-rss` reads from standard input a gemtext file and produces the equivalent RSS to the gemtext subscription.
+
Refer to the [`example`](example) directory for an example.
diff --git a/gemini-to-web/example/build.sh b/gemini-to-web/example/build.sh
index 93346a8..e792215 100755
--- a/gemini-to-web/example/build.sh
+++ b/gemini-to-web/example/build.sh
@@ -5,6 +5,8 @@ set -eu
rm -rf target
mkdir target
+cp -r source/* target/
+
{
cat <<HEAD
# Welcome to my blog
@@ -13,4 +15,4 @@ HEAD
find . -path './source/2???/??/*.gmi' -type f -print0 | uv --project .. run coppewebite-indexer source/
} >target/index.gmi
-cp -r source/* target/
+uv --project .. run coppewebite-to-rss <target/index.gmi >target/index.rss --title Example --subtitle Subtitle --base-url https://www.example.com target/
diff --git a/gemini-to-web/pyproject.toml b/gemini-to-web/pyproject.toml
index bf58d08..5226714 100644
--- a/gemini-to-web/pyproject.toml
+++ b/gemini-to-web/pyproject.toml
@@ -6,6 +6,7 @@ authors = [
]
requires-python = ">=3.12"
dependencies = [
+ "feedgen>=1.0.0",
"htmlgenerator>=1.2.32",
"lxml>=6.0.2",
]
@@ -14,6 +15,7 @@ dependencies = [
coppewebite-parse = "gemini_to_web.parser:cli_parse"
coppewebite-to-html = "gemini_to_web.html:cli_to_html"
coppewebite-indexer = "gemini_to_web.indexer:cli_indexer"
+coppewebite-to-rss = "gemini_to_web.rss:cli_to_rss"
[build-system]
requires = ["uv_build>=0.9.30,<0.10.0"]
diff --git a/gemini-to-web/src/gemini_to_web/__init__.py b/gemini-to-web/src/gemini_to_web/__init__.py
index 0b2b70e..827031f 100644
--- a/gemini-to-web/src/gemini_to_web/__init__.py
+++ b/gemini-to-web/src/gemini_to_web/__init__.py
@@ -1,25 +1,4 @@
-import argparse
-import pathlib
-import shutil
+import re
-import htmlgenerator
-from gemini_to_web import html
-
-def converter():
- parser = argparse.ArgumentParser()
- parser.add_argument("source", type=pathlib.Path)
- parser.add_argument("target", type=pathlib.Path)
- args = parser.parse_args()
-
- shutil.copytree(args.source, args.target)
- for gmi in args.target.glob("**/*.gmi"):
- html_path = gmi.with_suffix(".html")
- html_path.write_text(
- html.pretty(
- htmlgenerator.render(
- html.to_html(gmi.read_text()),
- {}
- )
- )
- )
+ENTRY_ELEMENT_TITLE = re.compile(r"^(\d{4}-\d{2}-\d{2}) (.*)$")
diff --git a/gemini-to-web/src/gemini_to_web/indexer.py b/gemini-to-web/src/gemini_to_web/indexer.py
index 3d463e3..a6ceee0 100644
--- a/gemini-to-web/src/gemini_to_web/indexer.py
+++ b/gemini-to-web/src/gemini_to_web/indexer.py
@@ -1,15 +1,12 @@
import argparse
import pathlib
-import re
import sys
+import gemini_to_web
from gemini_to_web import parser
from gemini_to_web import html
-ENTRY_ELEMENT_TITLE = re.compile(r"^(\d{4}-\d{2}-\d{2}) (.*)$")
-
-
def cli_indexer():
argument_parser = argparse.ArgumentParser()
argument_parser.add_argument("base_path", type=pathlib.Path)
@@ -25,9 +22,10 @@ def cli_indexer():
parsed = parser.parse(path.read_text())
parsed = list(parsed)
first_header_title = html.first_header_title_extractor(parsed)
- match = ENTRY_ELEMENT_TITLE.match(first_header_title)
+ match = gemini_to_web.ENTRY_ELEMENT_TITLE.match(first_header_title)
if match:
posts.append((match.group(1), path.relative_to(args.base_path), match.group(2)))
posts = sorted(posts, reverse=True)
for date, path, title in posts:
+ path = str(path).removesuffix(".gmi")
print(f"=> {path} {date} {title}")
diff --git a/gemini-to-web/src/gemini_to_web/rss.py b/gemini-to-web/src/gemini_to_web/rss.py
new file mode 100644
index 0000000..a03a4aa
--- /dev/null
+++ b/gemini-to-web/src/gemini_to_web/rss.py
@@ -0,0 +1,63 @@
+import argparse
+import datetime
+import pathlib
+import sys
+
+from feedgen import feed
+import htmlgenerator
+
+import gemini_to_web
+from gemini_to_web import html
+from gemini_to_web import parser
+
+
+def cli_to_rss():
+ argument_parser = argparse.ArgumentParser()
+ argument_parser.add_argument("--title", default="")
+ argument_parser.add_argument("--subtitle", default=None)
+ argument_parser.add_argument("--base-url", default="")
+ argument_parser.add_argument("base_dir", type=pathlib.Path)
+ args = argument_parser.parse_args()
+
+ fg = feed.FeedGenerator()
+ fg.title(args.title)
+ fg.subtitle(args.subtitle)
+ fg.link(href=args.base_url, rel="self")
+
+ input_ = sys.stdin.read()
+ parsed = parser.parse(input_)
+ parsed = list(parsed)
+
+ entries = []
+ for element in parsed:
+ match element:
+ case parser.LinkLine(url, link_name):
+ match = gemini_to_web.ENTRY_ELEMENT_TITLE.match(link_name)
+ if match:
+ entries.append((match.group(1), url, match.group(2)))
+ case _:
+ pass
+
+ entries = sorted(entries, reverse=True)
+ entries = entries[0:10]
+
+ for (date, url, title) in entries:
+ feed_entry = fg.add_entry()
+ feed_entry.link(href=args.base_url + "/" + url)
+ feed_entry.published(
+ datetime.datetime.combine(
+ datetime.date.fromisoformat(date),
+ datetime.datetime.min.time(),
+ tzinfo=datetime.UTC,
+ )
+ )
+ feed_entry.title(title)
+ parsed = parser.parse((args.base_dir / pathlib.Path(url).with_suffix(".gmi")).read_text())
+ parsed = list(parsed)
+ parsed = parsed[1:]
+ content = html.to_html(parsed)
+ rendered = htmlgenerator.render(content[1], {})
+ rendered = html.pretty(rendered)
+ feed_entry.content(rendered.encode("utf8"), type="html")
+
+ print(fg.rss_str(pretty=True).decode("utf8"), end="")
diff --git a/gemini-to-web/uv.lock b/gemini-to-web/uv.lock
index 1a55425..8810df8 100644
--- a/gemini-to-web/uv.lock
+++ b/gemini-to-web/uv.lock
@@ -3,16 +3,28 @@ revision = 3
requires-python = ">=3.12"
[[package]]
+name = "feedgen"
+version = "1.0.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+ { name = "lxml" },
+ { name = "python-dateutil" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/6b/59/be0a6f852b5dfbf19e6c8e962c8f41407697f9f52a7902250ed98683ae89/feedgen-1.0.0.tar.gz", hash = "sha256:d9bd51c3b5e956a2a52998c3708c4d2c729f2fcc311188e1e5d3b9726393546a", size = 258496, upload-time = "2023-12-25T18:04:08.421Z" }
+
+[[package]]
name = "gemini-to-web"
version = "0.0.0"
source = { editable = "." }
dependencies = [
+ { name = "feedgen" },
{ name = "htmlgenerator" },
{ name = "lxml" },
]
[package.metadata]
requires-dist = [
+ { name = "feedgen", specifier = ">=1.0.0" },
{ name = "htmlgenerator", specifier = ">=1.2.32" },
{ name = "lxml", specifier = ">=6.0.2" },
]
@@ -105,3 +117,24 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/fe/1a/b248b355834c8e32614650b8008c69ffeb0ceb149c793961dd8c0b991bb3/lxml-6.0.2-cp314-cp314t-win_amd64.whl", hash = "sha256:252a22982dca42f6155125ac76d3432e548a7625d56f5a273ee78a5057216eca", size = 4406837, upload-time = "2025-09-22T04:03:34.027Z" },
{ url = "https://files.pythonhosted.org/packages/92/aa/df863bcc39c5e0946263454aba394de8a9084dbaff8ad143846b0d844739/lxml-6.0.2-cp314-cp314t-win_arm64.whl", hash = "sha256:bb4c1847b303835d89d785a18801a883436cdfd5dc3d62947f9c49e24f0f5a2c", size = 3822205, upload-time = "2025-09-22T04:03:36.249Z" },
]
+
+[[package]]
+name = "python-dateutil"
+version = "2.9.0.post0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+ { name = "six" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/66/c0/0c8b6ad9f17a802ee498c46e004a0eb49bc148f2fd230864601a86dcf6db/python-dateutil-2.9.0.post0.tar.gz", hash = "sha256:37dd54208da7e1cd875388217d5e00ebd4179249f90fb72437e91a35459a0ad3", size = 342432, upload-time = "2024-03-01T18:36:20.211Z" }
+wheels = [
+ { url = "https://files.pythonhosted.org/packages/ec/57/56b9bcc3c9c6a792fcbaf139543cee77261f3651ca9da0c93f5c1221264b/python_dateutil-2.9.0.post0-py2.py3-none-any.whl", hash = "sha256:a8b2bc7bffae282281c8140a97d3aa9c14da0b136dfe83f850eea9a5f7470427", size = 229892, upload-time = "2024-03-01T18:36:18.57Z" },
+]
+
+[[package]]
+name = "six"
+version = "1.17.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/94/e7/b2c673351809dca68a0e064b6af791aa332cf192da575fd474ed7d6f16a2/six-1.17.0.tar.gz", hash = "sha256:ff70335d468e7eb6ec65b95b99d3a2836546063f63acc5171de367e834932a81", size = 34031, upload-time = "2024-12-04T17:35:28.174Z" }
+wheels = [
+ { url = "https://files.pythonhosted.org/packages/b7/ce/149a00dd41f10bc29e5921b496af8b574d8413afcd5e30dfa0ed46c2cc5e/six-1.17.0-py2.py3-none-any.whl", hash = "sha256:4721f391ed90541fddacab5acf947aa0d3dc7d27b2e1e8eda2be8970586c3274", size = 11050, upload-time = "2024-12-04T17:35:26.475Z" },
+]
generated by cgit v1.2.3 (git 2.46.0) at 2026-06-08 03:26:15 +0000