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

Fix kiskegyed ingredient parsing: spaces around links, multi-word units

Browse Source 
- Use get_text(" ") with whitespace normalization to preserve spaces
  between text nodes and <a> tag content in ingredient lines
- Use non-greedy .+? for unit in dual measurement regex to handle
  multi-word units like "kis fej"

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
authentik Default Admin
2026-02-24 18:47:41 +01:00
parent 20fabb84bf
commit bab59753f3
1 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/scraper.py
+4 -2
View File
@@ -600,7 +600,8 @@ def _parse_kiskegyed(soup: BeautifulSoup, url: str) -> dict:
ingredients.append({"group": group_text}) ingredients.append({"group": group_text})
elif el.name == "ul" and "list" in (el.get("class") or []): elif el.name == "ul" and "list" in (el.get("class") or []):
for li in el.find_all("li"): for li in el.find_all("li"):
line = li.get_text(strip=True) # Use separator to preserve spaces around <a> tags
line = re.sub(r"\s+", " ", li.get_text(" ")).strip()
if not line: if not line:
continue continue
qty, unit, food, extra = _parse_kiskegyed_ingredient(line) qty, unit, food, extra = _parse_kiskegyed_ingredient(line)
@@ -679,8 +680,9 @@ def _parse_kiskegyed_ingredient(line: str) -> tuple[str, str, str, str]:
extras = [] extras = []
# Try: qty unit (alt_measurement) food... # Try: qty unit (alt_measurement) food...
# Unit can be multi-word (e.g. "kis fej"), so use .+? (non-greedy)
m = re.match( m = re.match(
r"^([0-9][0-9.,/½¼¾-]*)\s+(\S+)\s+\(([^)]+)\)\s+(.+)$", line r"^([0-9][0-9.,/½¼¾-]*)\s+(.+?)\s+\(([^)]+)\)\s+(.+)$", line
) )
if m: if m:
qty = m.group(1).strip() qty = m.group(1).strip()