Spaces:
No application file
No application file
File size: 6,505 Bytes
7a511b0 |
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 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 |
from playwright.sync_api import sync_playwright
import urllib.parse
def scrape_hificorp(page, product_name: str) -> dict | None:
"""
Scrape HiFiCorp for the given product_name.
Returns a dict with keys: title, normal_price, promotion_price, source, product_link
or None if no product found.
"""
search_url = (
"https://www.hificorp.co.za/catalogsearch/result/?q="
+ urllib.parse.quote_plus(product_name)
)
page.goto(search_url, timeout=120_000)
page.wait_for_selector(".product-item-link", timeout=60_000)
product_url = page.locator(
".product-item-link").first.get_attribute("href")
if not product_url:
return None
page.goto(product_url, timeout=120_000)
page.wait_for_selector("h1.page-title", timeout=60_000)
title = page.locator("h1.page-title").inner_text().strip()
# Promotion (final) price
try:
promotion_price = (
page.locator('[data-price-type="finalPrice"] .price')
.first.inner_text()
.strip()
)
except Exception:
promotion_price = None
# Old (normal) price, if present
try:
old_nodes = page.locator('[data-price-type="oldPrice"] .price')
normal_price = (
old_nodes.first.inner_text().strip() if old_nodes.count() else None
)
except Exception:
normal_price = None
# Fallback if no old price
normal_price = normal_price or promotion_price
return {
"title": title,
"normal_price": normal_price,
"promotion_price": promotion_price,
"source": "HiFiCorp",
"product_link": product_url,
}
def scrape_incredible(page, product_name: str) -> dict | None:
"""
Scrape Incredible Connection for the given product_name.
Returns a dict with keys: title, normal_price, promotion_price, source, product_link
or None if no product found.
"""
search_url = (
"https://www.incredible.co.za/catalogsearch/result/?q="
+ urllib.parse.quote_plus(product_name)
)
page.goto(search_url, timeout=120_000)
page.wait_for_selector(".product-item-link", timeout=60_000)
product_url = page.locator(
".product-item-link").first.get_attribute("href")
if not product_url:
return None
page.goto(product_url, timeout=120_000)
page.wait_for_selector("h1.page-title", timeout=60_000)
title = page.locator("h1.page-title").inner_text().strip()
try:
promotion_price = (
page.locator('[data-price-type="finalPrice"] .price')
.first.inner_text()
.strip()
)
except Exception:
promotion_price = None
try:
old_nodes = page.locator('[data-price-type="oldPrice"] .price')
normal_price = (
old_nodes.first.inner_text().strip() if old_nodes.count() else None
)
except Exception:
normal_price = None
normal_price = normal_price or promotion_price
return {
"title": title,
"normal_price": normal_price,
"promotion_price": promotion_price,
"source": "Incredible Connection",
"product_link": product_url,
}
def search_product(product_name: str) -> list[dict]:
"""
Uses Playwright to scrape HiFiCorp and Incredible Connection for product_name.
Returns a list of dictionaries, each dict with keys:
title, normal_price, promotion_price, source, product_link.
If Playwright cannot run or no products found, returns an empty list.
"""
results = []
try:
with sync_playwright() as p:
browser = p.chromium.launch(
headless=True,
args=["--no-sandbox", "--disable-setuid-sandbox",
"--disable-dev-shm-usage"],
)
page = browser.new_page()
# Scrape HiFiCorp
try:
hifi_data = scrape_hificorp(page, product_name)
if hifi_data:
results.append(hifi_data)
except Exception as e:
return (r"HiFiCorp scraping error:", type(e).__name__, e)
browser.close()
except NotImplementedError:
# Playwright cannot launch a browser in this environment
return ("Playwright NotImplementedError: scraping skipped.")
except Exception as e:
# Any other Playwright/browser launch error
print("Playwright launch error:", type(e).__name__, e)
return []
return results
def get_scraped_product_data(product_name: str):
"""
Wrapper function to search for product data.
Returns a list of dictionaries with product details.
"""
if not product_name:
return []
results = search_product(product_name)
# def save_df_to_csv(df: pd.DataFrame, filename="shop_out_results.csv"):
results.to_csv("scraped.csv", index=False)
if not results:
return []
return results
def search_your_product(query: str):
"""Search for a product using the provided query string."""
json_out = search_product(query)
if not json_out:
return "No results found."
else:
product = []
for item in json_out:
product.append({
"title": item["title"],
"normal_price": item["normal_price"],
"promotion_price": item["promotion_price"],
"source": item["source"],
"product_link": item["product_link"]
})
return product
# For debugging or manual runs:
if __name__ == "__main__":
query = input("Enter product name: ")
json_out = search_product(query)
if not json_out:
print("No results found.")
else:
product = []
for item in json_out:
product.append({
"title": item["title"],
"normal_price": item["normal_price"],
"promotion_price": item["promotion_price"],
"source": item["source"],
"product_link": item["product_link"]
})
for items in product:
print(f"Title: {items['title']}")
print(f"Normal Price: {items['normal_price']}")
print(f"Promotion Price: {items['promotion_price']}")
print(f"Source: {items['source']}")
print(f"Product Link: {items['product_link']}")
print("-" * 40)
print(f"Found {len(product)} results for '{query}'.")
print("Search complete!")
|