1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
|
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=None)
argument_parser.add_argument("--subtitle", default=None)
argument_parser.add_argument("base_url")
argument_parser.add_argument("base_dir", type=pathlib.Path)
args = argument_parser.parse_args()
input_ = sys.stdin.read()
parsed = parser.parse(input_)
parsed = list(parsed)
title = args.title
if not title:
title = [p for p in parsed if isinstance(p, parser.HeadingLine) and p.level == 1][0].heading_text
subtitle = args.subtitle
if not subtitle:
subtitle = [p for p in parsed if isinstance(p, parser.HeadingLine) and p.level == 2][0].heading_text
fg = feed.FeedGenerator()
fg.title(title)
fg.subtitle(subtitle)
fg.link(href=args.base_url, rel="self")
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="")
|
