chore: add Search Console submission helper

Author: Programcode

scripts/gsc_submit.py

@@ -0,0 +1,90 @@
+#!/usr/bin/env python3
+import json
+from pathlib import Path
+
+from google.oauth2.credentials import Credentials
+from google.auth.transport.requests import Request
+from googleapiclient.discovery import build
+from googleapiclient.errors import HttpError
+
+TOKEN = Path('/home/codex/.hermes/gsc_token.json')
+SITE_CANDIDATES = [
+    'https://debate.pi-stack.org/',
+    'sc-domain:pi-stack.org',
+]
+SITEMAP = 'https://debate.pi-stack.org/sitemap.xml'
+URLS = [
+    'https://debate.pi-stack.org/',
+    'https://debate.pi-stack.org/ai-debate-practice',
+    'https://debate.pi-stack.org/debate-case-generator',
+    'https://debate.pi-stack.org/debate-rebuttal-practice',
+    'https://debate.pi-stack.org/ai-debate-coach',
+    'https://debate.pi-stack.org/terms',
+    'https://debate.pi-stack.org/privacy',
+]
+
+def load_creds():
+    data=json.loads(TOKEN.read_text())
+    creds=Credentials(
+        token=data.get('token'),
+        refresh_token=data.get('refresh_token'),
+        token_uri=data.get('token_uri'),
+        client_id=data.get('client_id'),
+        client_secret=data.get('client_secret'),
+        scopes=data.get('scopes'),
+    )
+    if creds.expired and creds.refresh_token:
+        creds.refresh(Request())
+        data['token']=creds.token
+        if creds.expiry:
+            data['expiry']=creds.expiry.isoformat()
+        TOKEN.write_text(json.dumps(data, indent=2))
+        TOKEN.chmod(0o600)
+    return creds
+
+def main():
+    service=build('searchconsole','v1',credentials=load_creds(),cache_discovery=False)
+    sites=service.sites().list().execute().get('siteEntry', [])
+    print('SITES')
+    print(json.dumps(sites, indent=2))
+    site_url=None
+    for cand in SITE_CANDIDATES:
+        if any(s.get('siteUrl') == cand for s in sites):
+            site_url=cand
+            break
+    if not site_url:
+        # Try any property that can cover target.
+        for s in sites:
+            su=s.get('siteUrl','')
+            if 'pi-stack.org' in su or 'debate.pi-stack.org' in su:
+                site_url=su
+                break
+    if not site_url:
+        raise SystemExit('NO_MATCHING_PROPERTY')
+    print('USING_SITE', site_url)
+
+    print('SUBMIT_SITEMAP', SITEMAP)
+    try:
+        service.sitemaps().submit(siteUrl=site_url, feedpath=SITEMAP).execute()
+        print('SITEMAP_SUBMIT_OK')
+    except HttpError as e:
+        print('SITEMAP_SUBMIT_ERROR', e.status_code, e.reason, e.content.decode('utf-8','ignore')[:1000])
+
+    print('SITEMAPS')
+    try:
+        print(json.dumps(service.sitemaps().list(siteUrl=site_url).execute(), indent=2)[:5000])
+    except HttpError as e:
+        print('SITEMAPS_LIST_ERROR', e.status_code, e.reason, e.content.decode('utf-8','ignore')[:1000])
+
+    print('URL_INSPECTION')
+    inspect=build('searchconsole','v1',credentials=load_creds(),cache_discovery=False).urlInspection().index().inspect
+    for u in URLS:
+        try:
+            res=inspect(body={'inspectionUrl':u,'siteUrl':site_url}).execute()
+            idx=res.get('inspectionResult',{}).get('indexStatusResult',{})
+            print(json.dumps({'url':u,'verdict':idx.get('verdict'),'coverageState':idx.get('coverageState'),'robotsTxtState':idx.get('robotsTxtState'),'indexingState':idx.get('indexingState'),'lastCrawlTime':idx.get('lastCrawlTime'),'pageFetchState':idx.get('pageFetchState'),'googleCanonical':idx.get('googleCanonical'),'userCanonical':idx.get('userCanonical')}, indent=2))
+        except HttpError as e:
+            print(json.dumps({'url':u,'error_status':e.status_code,'reason':e.reason,'body':e.content.decode('utf-8','ignore')[:500]}, indent=2))
+
+if __name__ == '__main__':
+    main()