first commit

scripts/reports/fetch_seo_links.py

@@ -0,0 +1,114 @@
+#!/usr/bin/env python3
+"""
+Pobiera linki SEO z Google Sheets (publiczny CSV export).
+
+Użycie:
+    python scripts/reports/fetch_seo_links.py --domain innsi.pl --month 2026-02
+"""
+
+import argparse
+import csv
+import io
+import json
+import os
+import sys
+from pathlib import Path
+
+if __name__ == "__main__":
+    sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding="utf-8", errors="replace")
+
+import requests
+ROOT = Path(__file__).parent.parent.parent
+sys.path.insert(0, str(ROOT))
+from src.gads_v2.config import load_env
+
+load_env(ROOT / ".env")
+
+
+def fetch_seo_links(domain, month):
+    """Fetch SEO links for given domain and month from Google Sheets.
+
+    Returns list of dicts: [{"date": "2026-02-01", "url": "https://..."}]
+    """
+    env_key = f"GSHEET_SEO_LINKS_{domain}"
+    sheet_config = os.environ.get(env_key, "")
+    if not sheet_config:
+        return None
+
+    if ":" in sheet_config:
+        spreadsheet_id, gid = sheet_config.split(":", 1)
+    else:
+        spreadsheet_id = sheet_config
+        gid = "0"
+
+    export_url = f"https://docs.google.com/spreadsheets/d/{spreadsheet_id}/export?format=csv&gid={gid}"
+
+    r = requests.get(export_url, timeout=30)
+    r.raise_for_status()
+    r.encoding = "utf-8"
+
+    reader = csv.DictReader(io.StringIO(r.text))
+    links = []
+    for row in reader:
+        date = row.get("Data", "").strip()
+        url = row.get("URL", "").strip()
+        if not date or not url:
+            continue
+        # Match month (date format: YYYY-MM-DD)
+        if date[:7] == month:
+            links.append({"date": date, "url": url})
+
+    return links
+
+
+def fetch_seo_activities(domain, month):
+    """Fetch SEO activities description for given domain and month.
+
+    Returns string with activities text, or None.
+    """
+    env_key = f"GSHEET_SEO_ACTIVITIES_{domain}"
+    sheet_config = os.environ.get(env_key, "")
+    if not sheet_config:
+        return None
+
+    if ":" in sheet_config:
+        spreadsheet_id, gid = sheet_config.split(":", 1)
+    else:
+        spreadsheet_id = sheet_config
+        gid = "0"
+
+    export_url = f"https://docs.google.com/spreadsheets/d/{spreadsheet_id}/export?format=csv&gid={gid}"
+
+    r = requests.get(export_url, timeout=30)
+    r.raise_for_status()
+    r.encoding = "utf-8"
+
+    reader = csv.DictReader(io.StringIO(r.text))
+    for row in reader:
+        date = row.get("Data", "").strip()
+        text = row.get("URL", "").strip()  # Column is named URL but contains text
+        if not date or not text:
+            continue
+        if date[:7] == month:
+            return text
+
+    return None
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Pobierz linki SEO z Google Sheets")
+    parser.add_argument("--domain", required=True)
+    parser.add_argument("--month", required=True, help="YYYY-MM")
+    args = parser.parse_args()
+
+    links = fetch_seo_links(args.domain, args.month)
+    if links is None:
+        print(f"Brak konfiguracji GSHEET_SEO_LINKS_{args.domain} w .env")
+        sys.exit(1)
+
+    print(json.dumps(links, indent=2, ensure_ascii=False))
+    print(f"\nLiczba linkow w {args.month}: {len(links)}")
+
+
+if __name__ == "__main__":
+    main()