feat: URL tootu a hashtagy v textu

daily_top.py

@@ -35,8 +35,7 @@ def api_get(url, token):
         raise
 
 def clean_content(content):
-    text = re.sub(r'<a\b[^>]*class="[^"]*hashtag[^"]*"[^>]*>.*?</a>', "", content, flags=re.IGNORECASE)
-    text = re.sub(r"<[^>]+>", " ", text)
+    text = re.sub(r"<[^>]+>", " ", content)
     text = html.unescape(text)
     return re.sub(r"\s+", " ", text).strip()
 
@@ -56,6 +55,12 @@ def main():
     except Exception:
         sys.exit(1)
 
+    try:
+        trend_tags = api_get(f"{base_url}/api/v1/trends/tags?limit=5", token)
+        tags = [t["name"] for t in trend_tags]
+    except Exception:
+        tags = []
+
     candidates = []
     for s in statuses:
         if "@" in s.get("account", {}).get("acct", ""):
@@ -68,6 +73,7 @@ def main():
         candidates.append({
             "acct": s["account"]["acct"],
             "text": text,
+            "url": s.get("url", ""),
             "reblogs": reblogs,
             "favourites": favourites,
             "score": reblogs + favourites,
@@ -81,9 +87,9 @@ def main():
     out_path = os.path.join("data", f"{today}.json")
 
     with open(out_path, "w", encoding="utf-8") as f:
-        json.dump({"date": today, "top": top}, f, ensure_ascii=False, indent=2)
+        json.dump({"date": today, "top": top, "tags": tags}, f, ensure_ascii=False, indent=2)
 
-    print(f"Uloženo: {out_path} ({len(top)} tootů)")
+    print(f"Uloženo: {out_path} ({len(top)} tootů, {len(tags)} hashtagů)")
 
 if __name__ == "__main__":
     main()