admin/recipe-importer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

v0.8.0: gastrohobbi.hu parser, fix ingredient fraction parsing

Browse Source 
Add gastrohobbi.hu parser (WPBakery page builder layout): ingredients
with groups, instructions with embedded lists, tags from JSON-LD
articleSection, prep time extraction.

Fix ingredient line parser: fractions like "1/2" no longer split due to
regex backtracking, en-dash ranges normalized, unicode fractions (½¼¾)
recognized as quantity start across all parsers.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
authentik Default Admin
2026-02-24 19:17:13 +01:00
parent ba5dae2caa
commit 0ec9ce0c6d
3 changed files with 197 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/scraper.py
+171 -5
View File
@@ -78,6 +78,7 @@ def supported_sites() -> list[dict]:
"nosalty": "https://www.nosalty.hu",
"sobors": "https://sobors.hu",
"kiskegyed": "https://www.kiskegyed.hu",
"gastrohobbi": "https://gastrohobbi.hu",
}
return [{"name": s + ".hu", "url": _SITE_URLS.get(s, "#")} for s, _ in _PARSERS]
@@ -682,7 +683,7 @@ def _parse_kiskegyed_ingredient(line: str) -> tuple[str, str, str, str]:
# Try: qty unit (alt_measurement) food...
# Unit can be multi-word (e.g. "kis fej"), so use .+? (non-greedy)
m = re.match(
r"^([0-9][0-9.,/½¼¾-]*)\s+(.+?)\s+\(([^)]+)\)\s+(.+)$", line
r"^([0-9½¼¾][0-9.,/½¼¾-]*)\s+(.+?)\s+\(([^)]+)\)\s+(.+)$", line
)
if m:
qty = m.group(1).strip()
@@ -697,12 +698,12 @@ def _parse_kiskegyed_ingredient(line: str) -> tuple[str, str, str, str]:
return (qty, unit, food_raw, "; ".join(extras))
# Try: qty unit food...
m2 = re.match(r"^([0-9][0-9.,/½¼¾-]*)\s+(\S+)\s+(.+)$", line)
m2 = re.match(r"^([0-9½¼¾][0-9.,/½¼¾-]*)\s+(\S+)\s+(.+)$", line)
if m2:
return (m2.group(1).strip(), m2.group(2).strip(), m2.group(3).strip(), "")
# Try: qty food (e.g. "2 tojás")
m3 = re.match(r"^([0-9][0-9.,/½¼¾-]*)\s+(.+)$", line)
m3 = re.match(r"^([0-9½¼¾][0-9.,/½¼¾-]*)\s+(.+)$", line)
if m3:
return (m3.group(1).strip(), "", m3.group(2).strip(), "")
@@ -710,6 +711,168 @@ def _parse_kiskegyed_ingredient(line: str) -> tuple[str, str, str, str]:
return ("", "", line, "")
# ---------------------------------------------------------------------------
# gastrohobbi.hu
# ---------------------------------------------------------------------------
@_register("gastrohobbi")
def _parse_gastrohobbi(soup: BeautifulSoup, url: str) -> dict:
# Title: h1.mpcth-post-title > span
title = ""
title_el = soup.select_one("h1.mpcth-post-title span.mpcth-color-main-border")
if title_el:
title = title_el.get_text(strip=True)
if not title:
title = _og(soup, "og:title") or _text(soup.find("title"))
if title:
title = re.sub(r"\s*[-–|]\s*GastroHobbi.*$", "", title, flags=re.IGNORECASE).strip()
# Description: first <p> in the first wpb_text_column before the inner recipe row
description = ""
first_text_col = soup.select_one("div.wpb-content-wrapper div.wpb_text_column div.wpb_wrapper")
if first_text_col:
p = first_text_col.find("p")
if p:
description = p.get_text(strip=True)
if not description:
description = _og(soup, "og:description") or ""
image_url = _og(soup, "og:image")
# --- Ingredients ---
# Find h3 containing "Hozzávalók" then walk siblings for ul and group h3 elements
ingredients = []
_gastrohobbi_parse_ingredients(soup, ingredients)
# --- Instructions ---
# Find h3 containing "Elkészítés:" then collect following <p> elements
instructions = []
prep_time = ""
_gastrohobbi_parse_instructions(soup, instructions)
# Extract prep time from h3 containing "Elkészítési idő:"
for h3 in soup.find_all("h3"):
text = h3.get_text(strip=True)
if "elkészítési idő" in text.lower():
# Text after the <em> tag: "Elkészítési idő: 60 perc"
# The time part is outside the <em><strong> wrapper
em = h3.find("em")
if em:
em.decompose()
time_text = h3.get_text(strip=True).strip()
if time_text:
prep_time = time_text
break
# --- Tags ---
# From JSON-LD Article.articleSection
tags = []
skip_tags = {"receptjeink", "receptek"}
for script in soup.find_all("script", type="application/ld+json"):
try:
data = json.loads(script.string or "")
graph = data.get("@graph", [data]) if isinstance(data, dict) else data
for item in graph:
if isinstance(item, dict) and item.get("@type") == "Article":
sections = item.get("articleSection", [])
if isinstance(sections, list):
tags = [s.strip() for s in sections
if s.strip() and s.strip().lower() not in skip_tags]
break
except (json.JSONDecodeError, TypeError, AttributeError):
continue
# Append prep time to description if available
if prep_time:
if description:
description += f" (Elkészítési idő: {prep_time})"
else:
description = f"Elkészítési idő: {prep_time}"
return {
"title": title or "Ismeretlen recept",
"description": description,
"image_url": image_url,
"ingredients": ingredients,
"instructions": instructions,
"tags": tags,
"original_url": url,
}
def _gastrohobbi_parse_ingredients(soup: BeautifulSoup, ingredients: list):
"""Parse ingredients from gastrohobbi.hu — find Hozzávalók h3 then walk siblings."""
# Find the h3 that contains "Hozzávalók"
header = None
for h3 in soup.find_all("h3"):
if "hozzávalók" in h3.get_text(strip=True).lower():
header = h3
break
if not header:
return
# Walk siblings after the header within the same container
for sib in header.find_next_siblings():
tag = sib.name
text = sib.get_text(strip=True)
if not text:
continue
# Stop at the "Elkészítés" section
if tag == "h3" and "elkészítés" in text.lower():
break
# Ingredient group header (plain h3 without em>strong, e.g. "A csipetkéhez:")
if tag == "h3":
group_name = text.rstrip(":")
if group_name:
ingredients.append({"group": group_name})
continue
# Ingredient list
if tag == "ul":
for li in sib.find_all("li", recursive=False):
p = li.find("p")
line = p.get_text(strip=True) if p else li.get_text(strip=True)
if not line:
continue
qty, unit, food = _parse_ingredient_line(line)
ingredients.append({
"quantity": qty, "unit": unit, "food": food, "extra": "",
})
def _gastrohobbi_parse_instructions(soup: BeautifulSoup, instructions: list):
"""Parse instructions from gastrohobbi.hu — find Elkészítés h3 then collect <p> siblings."""
header = None
for h3 in soup.find_all("h3"):
text = h3.get_text(strip=True)
if text.lower().startswith("elkészítés") and "idő" not in text.lower():
header = h3
break
if not header:
return
for sib in header.find_next_siblings():
tag = sib.name
text = sib.get_text(strip=True)
# Stop at prep time h3 or any other section header
if tag == "h3":
break
if tag == "p":
# Skip empty / whitespace-only paragraphs
if not text or text == "\xa0":
continue
instructions.append(text)
elif tag == "ul":
# Embedded list in instructions (e.g. cooking time options)
for li in sib.find_all("li"):
# Skip wrapper li elements that contain nested lists
if li.find("ul"):
continue
li_text = li.get_text(strip=True)
if li_text:
instructions.append(f" • {li_text}")
def _parse_sobors_article_ingredients(container, ingredients: list):
"""Parse article-style ingredients from sobors.hu (h4 headers + ul > li plain text)."""
for el in container.find_all(["h4", "ul"]):
@@ -736,11 +899,14 @@ def _parse_sobors_article_ingredients(container, ingredients: list):
def _parse_ingredient_line(line: str) -> tuple[str, str, str]:
"""Parse a plain-text ingredient line like '2 dl tejföl' into (qty, unit, food)."""
m = re.match(r"^([0-9][0-9.,/½¼¾-]*)\s*(\S+)\s+(.+)$", line)
# Normalize en-dash/em-dash ranges: "10 – 15" → "10-15"
line = re.sub(r"\s*[–—]\s*", "-", line)
# qty unit food (e.g. "2 dl tejföl", "½ tk őrölt kömény")
m = re.match(r"^([0-9½¼¾][0-9.,/½¼¾-]*)\s+(\S+)\s+(.+)$", line)
if m:
return (m.group(1).strip(), m.group(2).strip(), m.group(3).strip())
# Just quantity + food (e.g. "2 tojás")
m2 = re.match(r"^([0-9][0-9.,/½¼¾-]*)\s+(.+)$", line)
m2 = re.match(r"^([0-9½¼¾][0-9.,/½¼¾-]*)\s+(.+)$", line)
if m2:
return (m2.group(1).strip(), "", m2.group(2).strip())
return ("", "", line)