tildefriends/tools/buttfeed.py

#!/usr/bin/env python3

import argparse
import feedparser
import json
import re
import subprocess
import time

parser = argparse.ArgumentParser()
parser.add_argument('--state_file', help = 'Path to a file in which to store state.')
args = parser.parse_args()

k_feeds = {
    'tildefriends': 'https://dev.tildefriends.net/cory/tildefriends.rss',
    'erlbutt': 'https://github.com/cmoid/erlbutt/commits/main.atom',
    'habitat': 'https://tildegit.org/jeremylist/habitat.rss',
    'manyverse': 'https://gitlab.com/staltz/manyverse/-/commits/master?format=atom',
    'ahau': 'https://gitlab.com/ahau/ahau/-/commits/master.atom',
    'patchfox': 'https://github.com/soapdog/patchfox/commits.atom',
}

def fix_title(entry):
    if entry.summary.startswith('<a href=') and '\n' in entry.summary and entry.summary and '\n' in entry.summary:
        return entry.summary.split('\n')[1]
    return entry.title.split('\n')[0]

def get_entries():
    seen = set()
    results = []
    for name, url in k_feeds.items():
        feed = feedparser.parse(url)
        for entry in feed.entries:
            if '/issues/' in entry.link:
                m = re.match(r'^(\d+)#(.*)#$', entry.description)
                if m:
                    results.append((time.mktime(entry.get('updated_parsed')), name, entry.link, f'new issue #{m.group(1)}: {m.group(2)}'))
                    continue
            elif '/releases/' in entry.link:
                m = re.match(r'(.*) released <a href=".*?">(.*?)</a>', entry.title)
                if m:
                    results.append((time.mktime(entry.get('updated_parsed')), name, entry.link, f'{m.group(1)} released {m.group(2)}'))
                    continue
            if entry.summary.startswith('<a href='):
                for m in re.findall(r'<a href="(.*?)">.*?</a>$\s*^([^\n]+)$', entry.summary, re.S | re.M):
                    if not m[0] in seen:
                        seen.add(m[0])
                        results.append((time.mktime(entry.get('updated_parsed')), name, m[0], m[1]))
            else:
                if not entry.link in seen:
                    seen.add(entry.link)
                    results.append((time.mktime(entry.get('updated_parsed')), name, entry.link, entry.title.split('\n')[0]))
    results.sort()
    results.reverse()
    return results

state = {}
if args.state_file:
    try:
        with open(args.state_file, 'r') as f:
            state = json.load(f)
    except:
        pass
cutoff = state.get('last_update') or (time.time() - 2 * 7 * 24 * 60 * 60)

entries = [entry for entry in get_entries() if entry[0] > cutoff]
if entries:
    text = '\n'.join([f' * **{entry[1]}** [{entry[3]}]({entry[2]})' for entry in entries])
    state['last_update'] = entries[0][0]
    if args.state_file:
        content = json.dumps({'type': 'post', 'text': text, 'mentions': []})
        subprocess.check_call(['out/debug/tildefriends', 'publish', '--user', 'cory', '--id', '@DnYDqFfmxdNkYQlpflF9Wkltk2HIhJ5u1MW5njKPLzM=.ed25519', '--content', content])
        with open(args.state_file, 'w') as f:
            json.dump(state, f)
    else:
        print(text)