v0.6.0: Sobors.hu parser, HTTP auth, recipe validation, UI polish

- New sobors.hu parser with ingredient groups and section headers - Incomplete recipe warnings (missing ingredients/instructions) - Optional HTTP Basic Auth (configurable on settings page) - Brand text: "Recept" in white, "Importáló" in blue - Larger logo (36px), favicon using logo_notext.svg Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-24 18:07:05 +01:00
parent 76290770f4
commit a0bcb62588
7 changed files with 237 additions and 12 deletions
@@ -418,6 +418,98 @@ def _parse_nosalty_ingredient(li, ingredients: list):
    })


+# ---------------------------------------------------------------------------
+# sobors.hu
+# ---------------------------------------------------------------------------
+
+
+@_register("sobors")
+def _parse_sobors(soup: BeautifulSoup, url: str) -> dict:
+    # Title: h3.recept_nev
+    title = ""
+    title_el = soup.find("h3", class_="recept_nev")
+    if title_el:
+        title = title_el.get_text(strip=True)
+    if not title:
+        title = _og(soup, "og:title") or _text(soup.find("title"))
+    if title:
+        title = re.sub(r"\s*[-–|]\s*SóBors.*$", "", title, flags=re.IGNORECASE).strip()
+
+    description = _og(soup, "og:description") or ""
+    image_url = _og(soup, "og:image")
+
+    # --- Ingredients ---
+    # Container: div.hozzavalok-container
+    # Groups: section > h4 (group header), section > ul > li
+    # Each li > span > span.mennyiseg, span.mertekegyseg, span.hozzavalo
+    ingredients = []
+    ing_container = soup.find("div", class_="hozzavalok-container")
+    if ing_container:
+        for section in ing_container.find_all("section"):
+            h4 = section.find("h4")
+            if h4:
+                group_name = h4.get_text(strip=True).rstrip(":")
+                if group_name:
+                    ingredients.append({"group": group_name})
+            for li in section.find_all("li"):
+                qty_el = li.find("span", class_="mennyiseg")
+                unit_el = li.find("span", class_="mertekegyseg")
+                food_el = li.find("span", class_="hozzavalo")
+                food = _text(food_el)
+                if not food:
+                    continue
+                qty = _text(qty_el)
+                unit = _text(unit_el)
+                ingredients.append({
+                    "quantity": qty,
+                    "unit": unit,
+                    "food": food,
+                    "extra": "",
+                })
+
+    # --- Instructions ---
+    # Container: div.recept_leiras.recept_he-elkeszites
+    # Content: <p> tags for steps, <h3><strong>Section</strong></h3> for section headers
+    instructions = []
+    inst_container = soup.find("div", class_="recept_leiras")
+    if inst_container:
+        for el in inst_container.find_all(["h3", "p"]):
+            if el.name == "h3":
+                header = el.get_text(strip=True)
+                if header:
+                    instructions.append(f"--- {header} ---")
+            elif el.name == "p":
+                txt = el.get_text(strip=True)
+                if txt:
+                    # Strip leading numbering like "1.   " from reader recipes
+                    txt = re.sub(r"^\d+\.\s+", "", txt)
+                    instructions.append(txt)
+
+    # --- Tags ---
+    # Container: div.cikk-cimkek > ul.cikk-cimkek-list > li > a
+    # Skip the generic "Receptek" category tag and "Olvasói receptek" tag
+    tags = []
+    tag_container = soup.find("div", class_="cikk-cimkek")
+    if tag_container:
+        tag_list = tag_container.find("ul", class_="cikk-cimkek-list")
+        if tag_list:
+            skip = {"receptek", "olvasói receptek"}
+            for a in tag_list.find_all("a"):
+                tag_text = a.get_text(strip=True)
+                if tag_text and tag_text.lower() not in skip:
+                    tags.append(tag_text)
+
+    return {
+        "title": title or "Ismeretlen recept",
+        "description": description,
+        "image_url": image_url,
+        "ingredients": ingredients,
+        "instructions": instructions,
+        "tags": tags,
+        "original_url": url,
+    }
+
+
 def _split_qty_unit(raw: str) -> tuple[str, str]:
    """Split a merged quantity+unit string like '200g' into ('200', 'g')."""
    raw = raw.strip()