112 lines
3.6 KiB
Python
Executable File
112 lines
3.6 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""Analyse du HTML Cdiscount pour identifier les sélecteurs."""
|
|
|
|
from bs4 import BeautifulSoup
|
|
import json
|
|
|
|
# Lire le HTML
|
|
with open("scraped/cdiscount_tuf608umrv004_pw.html", "r", encoding="utf-8") as f:
|
|
html = f.read()
|
|
|
|
soup = BeautifulSoup(html, "lxml")
|
|
|
|
print("=" * 80)
|
|
print("ANALYSE HTML CDISCOUNT")
|
|
print("=" * 80)
|
|
|
|
# 1. Titre
|
|
print("\n1. TITRE")
|
|
print("-" * 80)
|
|
h1 = soup.find("h1")
|
|
if h1:
|
|
print(f"Tag: {h1.name}")
|
|
print(f"Classes: {h1.get('class')}")
|
|
print(f"data-e2e: {h1.get('data-e2e')}")
|
|
print(f"Texte: {h1.get_text().strip()[:100]}")
|
|
|
|
# 2. Prix
|
|
print("\n2. PRIX")
|
|
print("-" * 80)
|
|
# Chercher dans JSON-LD
|
|
json_ld_scripts = soup.find_all("script", {"type": "application/ld+json"})
|
|
for script in json_ld_scripts:
|
|
try:
|
|
data = json.loads(script.string)
|
|
if isinstance(data, dict) and data.get("@type") == "Product":
|
|
print(f"Schema.org Product trouvé!")
|
|
print(f" name: {data.get('name')}")
|
|
print(f" price: {data.get('offers', {}).get('price')}")
|
|
print(f" currency: {data.get('offers', {}).get('priceCurrency')}")
|
|
print(f" availability: {data.get('offers', {}).get('availability')}")
|
|
break
|
|
except:
|
|
pass
|
|
|
|
# Chercher les classes de prix
|
|
price_divs = soup.find_all("div", class_=lambda x: x and "price" in x.lower())
|
|
print(f"\nDivs avec 'price' dans la classe: {len(price_divs)}")
|
|
for div in price_divs[:3]:
|
|
print(f" - {div.get('class')} : {div.get_text().strip()[:50]}")
|
|
|
|
# 3. Images
|
|
print("\n3. IMAGES")
|
|
print("-" * 80)
|
|
img_product = soup.find_all("img", alt=True)
|
|
print(f"Images avec alt: {len(img_product)}")
|
|
for img in img_product[:5]:
|
|
alt = img.get("alt", "")
|
|
src = img.get("src", "")
|
|
if "TUF" in alt or "ASUS" in alt:
|
|
print(f" - alt: {alt[:60]}")
|
|
print(f" src: {src[:80]}")
|
|
|
|
# 4. Stock
|
|
print("\n4. DISPONIBILITÉ")
|
|
print("-" * 80)
|
|
availability_divs = soup.find_all(["div", "span"], class_=lambda x: x and ("availability" in str(x).lower() or "stock" in str(x).lower()))
|
|
print(f"Éléments avec 'availability'/'stock': {len(availability_divs)}")
|
|
for elem in availability_divs[:5]:
|
|
print(f" - {elem.name} {elem.get('class')} : {elem.get_text().strip()[:60]}")
|
|
|
|
# 5. Catégorie / Breadcrumb
|
|
print("\n5. CATÉGORIE / BREADCRUMB")
|
|
print("-" * 80)
|
|
breadcrumbs = soup.find_all(["nav", "ol", "ul"], class_=lambda x: x and "breadcrumb" in str(x).lower())
|
|
for bc in breadcrumbs[:2]:
|
|
print(f"Tag: {bc.name}, Classes: {bc.get('class')}")
|
|
links = bc.find_all("a")
|
|
for link in links:
|
|
print(f" - {link.get_text().strip()}")
|
|
|
|
# 6. Specs / Caractéristiques
|
|
print("\n6. CARACTÉRISTIQUES TECHNIQUES")
|
|
print("-" * 80)
|
|
specs_sections = soup.find_all(["table", "dl", "div"], class_=lambda x: x and ("spec" in str(x).lower() or "characteristic" in str(x).lower() or "feature" in str(x).lower()))
|
|
print(f"Sections de specs: {len(specs_sections)}")
|
|
for section in specs_sections[:3]:
|
|
print(f" - {section.name} {section.get('class')}")
|
|
text = section.get_text().strip()[:200]
|
|
print(f" {text}")
|
|
|
|
# 7. SKU / Référence
|
|
print("\n7. SKU / RÉFÉRENCE PRODUIT")
|
|
print("-" * 80)
|
|
# Chercher dans JSON-LD
|
|
for script in json_ld_scripts:
|
|
try:
|
|
data = json.loads(script.string)
|
|
if isinstance(data, dict) and data.get("@type") == "Product":
|
|
print(f"SKU: {data.get('sku')}")
|
|
print(f"mpn: {data.get('mpn')}")
|
|
break
|
|
except:
|
|
pass
|
|
|
|
# Chercher dans l'URL ou les data attributes
|
|
print("\nDans l'URL: f-10709-tuf608umrv004.html")
|
|
print("Possible SKU: tuf608umrv004")
|
|
|
|
print("\n" + "=" * 80)
|
|
print("FIN DE L'ANALYSE")
|
|
print("=" * 80)
|