Digest OSS Hacker News: manuale completo + workflow n8n + script audio (riproducibile, MIT)

scripts/fetch_latest_digest.py

@@ -0,0 +1,69 @@
+#!/usr/bin/env python3
+"""Scarica il JSON dell'ultimo digest RIUSCITO del workflow v3 e lo salva in latest-digest.json.
+Chiamato dal cronjob prima della narrazione. Include il testo dei README per la narrazione esaustiva."""
+import json, sys, urllib.request, urllib.error
+
+C = json.load(open('/opt/data/hn-oss-digest/creds.json'))
+H = {'X-N8N-API-KEY': C['n8n_key']}
+BASE = 'https://n8n.as89.it/api/v1'
+WID = 'tZwGIY9rcdybQLPr'
+
+def http(url):
+    req = urllib.request.Request(url, headers=H)
+    with urllib.request.urlopen(req, timeout=60) as r:
+        return r.read().decode()
+
+d = json.loads(http(f'{BASE}/executions?limit=10&status=success&workflowId={WID}'))
+data = d.get('data', [])
+if not data:
+    print('NESSUNA ESECUZIONE RIUSCITA TROVATA')
+    sys.exit(1)
+
+eid = data[0]['id']
+x = json.loads(http(f'{BASE}/executions/{eid}?includeData=true'))
+rd = x['data']['resultData']['runData']
+sel = rd['Seleziona OSS'][0]['data']['main'][0][0]['json']
+
+def node_json(node):
+    """Primo json di output non vuoto del nodo, o None."""
+    runs = rd.get(node)
+    if not runs:
+        return None
+    for conn in runs[0].get('data', {}).get('main', []):
+        if conn:
+            return conn[0].get('json')
+    return None
+
+g = node_json('Gemini riassume')
+src = 'Gemini riassume'
+if not g or 'candidates' not in g:
+    g = node_json('Gemini lite (fallback)')
+    src = 'Gemini lite (fallback)'
+if not g or 'candidates' not in g:
+    print('NESSUN RIASSUNTO DISPONIBILE')
+    sys.exit(1)
+print(f'sorgente riassunto: {src}')
+txt = g['candidates'][0]['content']['parts'][0]['text']
+dj = json.loads(txt)
+
+# item originali (con il testo dei README) allegati alle sezioni finali
+readme_by_url = {it.get('url', ''): it.get('readme', '') for it in sel.get('items', [])}
+for k in ('show', 'repo', 'news'):
+    for it in dj.get('sections', {}).get(k, []):
+        it['readme'] = readme_by_url.get(it.get('url', ''), '')
+
+out = {
+    'executionId': eid,
+    'count': sel.get('count'),
+    'conReadme': sel.get('conReadme'),
+    'sinceOld': sel.get('sinceOld'),
+    'sinceNew': sel.get('sinceNew'),
+    'geminiSource': src,
+    'sections': dj.get('sections', {}),
+}
+with open('/opt/data/hn-oss-digest/latest-digest.json', 'w') as f:
+    json.dump(out, f, ensure_ascii=False, indent=1)
+
+tot = sum(len(out['sections'].get(k, [])) for k in ('show', 'repo', 'news'))
+conr = sum(1 for k in ('show', 'repo', 'news') for it in out['sections'].get(k, []) if it.get('readme'))
+print(f'exec {eid}: {tot} item salvati in latest-digest.json | README allegati: {conr}')