ProjectEulerBot/pe_rss.py at development · Teyzer/ProjectEulerBot · GitHub

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
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
from html.parser import HTMLParser
import xml.etree.ElementTree as ET
from html import unescape
import re

from email.utils import parsedate_to_datetime
from datetime import timezone, datetime


class DiscordHTMLToMarkdown(HTMLParser):
    def __init__(self):
        super().__init__()
        self.out = []
        self.stack = []
        self.in_li = False
        self.href = None

    def handle_starttag(self, tag, attrs):
        attrs = dict(attrs)
        if tag in ("b", "strong"):
            self.out.append("**"); self.stack.append("**")
        elif tag in ("i", "em"):
            self.out.append("*"); self.stack.append("*")
        elif tag == "code":
            self.out.append("`"); self.stack.append("`")
        elif tag in ("p", "div"):
            if self.out and not self.out[-1].endswith("\n\n"):
                self.out.append("\n\n")
            self.stack.append(None)
        elif tag in ("br",):
            self.out.append("\n")
        elif tag in ("ul", "ol"):
            self.stack.append(tag)
        elif tag == "li":
            self.in_li = True
            self.out.append("- ")
            self.stack.append("li")
        elif tag == "a":
            self.href = attrs.get("href")
            self.stack.append("a")
        else:
            self.stack.append(None)

    def handle_endtag(self, tag):
        if tag in ("b", "strong", "i", "em", "code"):
            while self.stack:
                m = self.stack.pop()
                if m in ("**", "*", "`"):
                    self.out.append(m)
                    break
        elif tag == "a":
            if self.href:
                if self.out and re.match(r"(?:^|\n)-\s*$", "".join(self.out[-1:])):
                    self.out.append(self.href)
            self.href = None
            self._pop_to("a")
        elif tag == "li":
            if not self.out or not self.out[-1].endswith("\n"):
                self.out.append("\n")
            self.in_li = False
            self._pop_to("li")
        elif tag in ("ul", "ol"):
            if not self.out or not self.out[-1].endswith("\n\n"):
                self.out.append("\n")
            self._pop_to(tag)
        elif tag in ("p", "div"):
            if not self.out or not self.out[-1].endswith("\n\n"):
                self.out.append("\n\n")
            self._pop_to(None)

    def handle_data(self, data):
        text = unescape(data)
        if self.href:
            text = text.strip()
            if text:
                self.out.append(f"[{text}]({self.href})")
            else:
                self.out.append(self.href)
        else:
            if self.in_li:
                self.out.append(re.sub(r"\s+", " ", text).strip())
            else:
                self.out.append(re.sub(r"[ \t]+", " ", text))

    def _pop_to(self, marker):
        while self.stack:
            m = self.stack.pop()
            if m == marker:
                break

    def get_markdown(self):
        s = "".join(self.out)

        s = re.sub(r"[ \t]+\n", "\n", s)
        s = re.sub(r"\n{3,}", "\n\n", s)
        s = s.strip()
        return s

def html_to_discord_markdown(html: str, title: str | None = None, date_str: str | None = None) -> str:
    parser = DiscordHTMLToMarkdown()
    parser.feed(html)
    body = parser.get_markdown()

    header = ""
    if title and date_str:
        header = f"**[RSS Feed] {title}** ({date_str})\n"
    elif title:
        header = f"**[RSS Feed] {title}** \n"

    return header + body


def parse_rss_items(text: str):
    root = ET.fromstring(text)  # raises if XML is invalid
    items = []
    for it in root.findall(".//item"):
        items.append({
            "title": it.findtext("title", default=""),
            "link": it.findtext("link", default=""),
            "guid": it.findtext("guid", default=""),
            "pubDate": it.findtext("pubDate", default=""),
            "description": it.findtext("description", default=""),
        })
    return items[::-1]


def release_to_unix(s: str) -> datetime:
    """
    Parse strings like:
    'Release date: Sat, 06 Sep 2025 23:00:00 +0100'
    Returns a timezone-aware datetime.
    """
    prefix = "Release date:"
    if s.startswith(prefix):
        s = s[len(prefix):].strip()
    # RFC-822 style with offset like +0100 (no colon)
    return round(datetime.strptime(s, "%a, %d %b %Y %H:%M:%S %z").timestamp())