File size: 3,145 Bytes
40daea5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 |
#!/usr/bin/env python3
"""Debug why Marlin 5 returns Rail"""
import requests
import xml.etree.ElementTree as ET
import re
def debug_matching():
"""See what matches when searching for Marlin 5"""
# Get Trek XML
url = 'https://www.trekbisiklet.com.tr/output/8582384479'
response = requests.get(url, verify=False, timeout=10)
if response.status_code != 200:
print("Failed to fetch XML")
return
root = ET.fromstring(response.content)
# Search parameters (from smart_warehouse_with_price.py logic)
search_name = "marlin 5"
clean_search = re.sub(r'\s*\(\d{4}\)\s*', '', search_name).strip()
print(f"Searching for: '{search_name}'")
print(f"Clean search: '{clean_search}'")
print(f"Search parts: {clean_search.split()}")
print("\n" + "="*60)
matches = []
for item in root.findall('item'):
rootlabel_elem = item.find('rootlabel')
if rootlabel_elem is None or not rootlabel_elem.text:
continue
item_name = rootlabel_elem.text.lower()
clean_item = re.sub(r'\s*\(\d{4}\)\s*', '', item_name).strip()
# Calculate score (same logic as smart_warehouse_with_price.py)
score = 0
# Exact match
if clean_search == clean_item:
score += 100
# Starts with
elif clean_item.startswith(clean_search + " ") or clean_item == clean_search:
score += 50
else:
# Partial matching
name_parts = clean_search.split()
for part in name_parts:
if part in clean_item:
score += 1
if score > 0:
price_elem = item.find('priceTaxWithCur')
link_elem = item.find('productLink')
matches.append({
'original': rootlabel_elem.text,
'clean': clean_item,
'score': score,
'price': price_elem.text if price_elem is not None else 'N/A',
'link': link_elem.text if link_elem is not None else 'N/A'
})
# Sort by score
matches.sort(key=lambda x: x['score'], reverse=True)
print(f"\nFound {len(matches)} matches:")
print("="*60)
for i, match in enumerate(matches[:20], 1): # Show top 20
print(f"\n{i}. Score: {match['score']}")
print(f" Original: {match['original']}")
print(f" Clean: {match['clean']}")
print(f" Price: {match['price']}")
if match['link'] != 'N/A':
print(f" Link: ...{match['link'][-50:]}")
# Explain why it matched
print(" Why matched:")
if clean_search == match['clean']:
print(" - EXACT MATCH")
elif match['clean'].startswith(clean_search + " "):
print(" - STARTS WITH search")
else:
parts = clean_search.split()
for part in parts:
if part in match['clean']:
print(f" - Contains '{part}'")
if __name__ == "__main__":
debug_matching() |