Spaces:
Sleeping
Sleeping
File size: 42,018 Bytes
0cba968 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 | from __future__ import annotations
import csv
import html
import re
import tempfile
from typing import Any, Dict, List, Optional, Tuple
import gradio as gr
from tool import (
DEFAULT_COMPARE_LOCATIONS,
DEFAULT_LOCATION,
MAX_COMPARE_LOCATIONS,
SCRAPE_DO_SIGNUP_URL,
ScrapeDoWalmartTool,
describe_store,
)
# ZeroGPU hardware refuses to keep a Space alive unless it finds at least one
# @spaces.GPU function at startup. This app is pure HTTP and never touches a GPU,
# so the probe below exists only to satisfy that check. It is never called.
try:
import spaces
@spaces.GPU(duration=1)
def _zerogpu_probe() -> str:
return "ok"
except ImportError:
pass
NO_TOKEN_MD = (
"### Paste your Scrape.do API token above\n\n"
f"No token yet? [Create a free account]({SCRAPE_DO_SIGNUP_URL}) — "
"1,000 free credits a month, no credit card. Each Walmart call costs 10 credits."
)
# --------------------------------------------------------------------- helpers
def _esc(value: Any) -> str:
return html.escape("" if value is None else str(value), quote=True)
def _safe_link(url: Any) -> str:
url = str(url or "")
return url if url.startswith(("http://", "https://")) else ""
def _num(value: Any) -> Optional[float]:
if isinstance(value, bool):
return None
try:
return float(str(value).replace(",", "").replace("$", ""))
except (TypeError, ValueError):
return None
def _fmt_int(value: Any) -> str:
number = _num(value)
return f"{int(number):,}" if number is not None else _esc(value)
def _money(value: Any, currency: Any = "USD") -> str:
number = _num(value)
if number is None:
return ""
code = str(currency or "USD").upper()
if code in ("USD", "CAD"):
return f"${number:,.2f}"
return f"{number:,.2f} {code}"
def _tool_or_none(token: str) -> Optional[ScrapeDoWalmartTool]:
if not token or not token.strip():
return None
return ScrapeDoWalmartTool(api_token=token.strip())
def _write_csv(rows: List[Dict[str, Any]], prefix: str) -> Optional[str]:
if not rows:
return None
fieldnames: List[str] = []
for row in rows:
for key in row:
if key not in fieldnames:
fieldnames.append(key)
handle = tempfile.NamedTemporaryFile(
mode="w", suffix=".csv", prefix=f"{prefix}-", delete=False, newline="", encoding="utf-8-sig",
)
writer = csv.DictWriter(handle, fieldnames=fieldnames)
writer.writeheader()
for row in rows:
writer.writerow({key: row.get(key, "") for key in fieldnames})
handle.close()
return handle.name
def _error_md(data: Dict[str, Any]) -> str:
out = f"**That didn't go through.**\n\n{data.get('errorMessage') or 'Unknown error'}"
if data.get("hint"):
out += f"\n\n{data['hint']}"
return out
def _img(src: Any, cls: str) -> str:
link = _safe_link(src)
if not link:
return ""
return (
f'<img class="{cls}" src="{_esc(link)}" alt="" loading="lazy" referrerpolicy="no-referrer" '
"onerror=\"this.style.visibility='hidden'\">"
)
def _stars(rating: Any) -> str:
value = _num(rating)
if value is None:
return ""
full = max(0, min(5, int(round(value))))
return f'<span class="wm-stars">{"★" * full}<span class="wm-stars-off">{"★" * (5 - full)}</span></span>'
def _rating_html(rating: Any, count: Any) -> str:
if _num(rating) is None:
return ""
count_html = f'<span class="wm-count">({_fmt_int(count)})</span>' if count not in (None, "") else ""
return f'<div class="wm-rating">{_stars(rating)}<span class="wm-rating-num">{_num(rating):.1f}</span>{count_html}</div>'
def _price_html(price: Any, list_price: Any, currency: Any = "USD", big: bool = False) -> str:
value = _num(price)
if value is None:
return '<div class="wm-price-na">Price not shown at this store</div>'
was = _num(list_price)
dollars, cents = f"{value:,.2f}".split(".")
amount = (
f'<span class="wm-cur">$</span><span class="wm-dollars">{dollars}</span><span class="wm-cents">{cents}</span>'
if str(currency or "USD").upper() in ("USD", "CAD")
else _esc(_money(value, currency))
)
cls = "wm-price wm-price-big" if big else "wm-price"
if was and was > value:
return (
f'<div class="{cls}"><span class="wm-now">Now</span> <span class="wm-amount wm-sale">{amount}</span>'
f' <span class="wm-was">{_esc(_money(was, currency))}</span></div>'
)
return f'<div class="{cls}"><span class="wm-amount">{amount}</span></div>'
def _stock_html(availability: Any) -> str:
code = str(availability or "").upper()
if not code:
return ""
if code == "IN_STOCK":
return '<span class="wm-stock wm-in">In stock</span>'
if "OUT" in code:
return '<span class="wm-stock wm-out">Out of stock</span>'
label = code.replace("_", " ").capitalize()
return f'<span class="wm-stock wm-limited">{_esc(label)}</span>'
def _fulfillment_html(methods: Any) -> str:
if not isinstance(methods, list) or not methods:
return ""
chips = "".join(f'<span class="wm-chip">{_esc(str(m).replace("_", " ").capitalize())}</span>' for m in methods)
return f'<div class="wm-chips">{chips}</div>'
def _html_to_text(raw: Any, limit: int = 3000) -> str:
text = re.sub(r"(?is)<\s*(script|style)[^>]*>.*?<\s*/\s*\1\s*>", "", str(raw or ""))
text = re.sub(r"(?i)<\s*li[^>]*>", "\n• ", text)
text = re.sub(r"(?i)<\s*(br|/p|/div|/ul|/ol|/h\d)[^>]*>", "\n", text)
text = re.sub(r"<[^>]+>", "", text)
text = html.unescape(text)
lines = [line.strip() for line in text.splitlines()]
text = "\n".join(line for line in lines if line)
return text[:limit] + ("…" if len(text) > limit else "")
def _store_banner(store: Dict[str, Any], prefix: str = "Prices and stock at") -> str:
label = describe_store(store)
if not label:
return ""
return f'<div class="wm-store">{PIN_SVG} {prefix} <b>{_esc(label)}</b></div>'
CART_SVG = (
'<svg viewBox="0 0 24 24" width="{size}" height="{size}" aria-hidden="true"><path fill="#ffc220" '
'd="M7 18c-1.1 0-1.99.9-1.99 2S5.9 22 7 22s2-.9 2-2-.9-2-2-2zM1 2v2h2l3.6 7.59-1.35 2.45c-.16.28-.25.61-.25.96 '
"0 1.1.9 2 2 2h12v-2H7.42c-.14 0-.25-.11-.25-.25l.03-.12.9-1.63h7.45c.75 0 1.41-.41 1.75-1.03l3.58-6.49A1.003 "
'1.003 0 0 0 20 4H5.21l-.94-2H1zm16 16c-1.1 0-1.99.9-1.99 2s.89 2 1.99 2 2-.9 2-2-.9-2-2-2z"/></svg>'
)
PIN_SVG = (
'<svg viewBox="0 0 24 24" width="16" height="16" aria-hidden="true" style="vertical-align:-3px">'
'<path fill="#0071dc" d="M12 2C8.13 2 5 5.13 5 9c0 5.25 7 13 7 13s7-7.75 7-13c0-3.87-3.13-7-7-7zm0 9.5'
'a2.5 2.5 0 110-5 2.5 2.5 0 010 5z"/></svg>'
)
# ------------------------------------------------------------ search results
def render_results(data: Dict[str, Any], hide_sponsored: bool) -> str:
results = data.get("results") or []
shown = [r for r in results if not (hide_sponsored and r.get("sponsored"))]
cards: List[str] = []
for item in shown:
link = _safe_link(item.get("url"))
name = _esc(item.get("name"))
title = (
f'<a class="wm-name" href="{_esc(link)}" target="_blank" rel="noopener noreferrer">{name}</a>'
if link else f'<span class="wm-name">{name}</span>'
)
seller = item.get("seller")
seller_html = (
f'<div class="wm-muted">Sold by {_esc(seller)}</div>'
if seller and "walmart" not in str(seller).lower() else ""
)
cards.append(
'<div class="wm-card">'
f'<div class="wm-img-box">{_img(item.get("image"), "wm-img")}'
+ ('<span class="wm-sponsored">Sponsored</span>' if item.get("sponsored") else "")
+ "</div>"
f"{_price_html(item.get('price'), item.get('list_price'), item.get('currency'))}"
f"{title}"
f"{_rating_html(item.get('rating'), item.get('reviews_count'))}"
f'<div class="wm-line">{_stock_html(item.get("availability"))}</div>'
f"{_fulfillment_html(item.get('fulfillment'))}"
f"{seller_html}"
f'<div class="wm-id">#{_esc(item.get("position"))} · Item {_esc(item.get("item_id"))}</div>'
"</div>"
)
if not cards:
cards.append('<div class="wm-empty">No products came back for this search at this store.</div>')
return (
f'<div class="wm-wrap">{_store_banner(data.get("store") or {})}'
f'<div class="wm-grid">{"".join(cards)}</div></div>'
)
def _result_rows(data: Dict[str, Any]) -> List[Dict[str, Any]]:
store = data.get("store") or {}
rows = []
for item in data.get("results") or []:
rows.append(
{
"position": item.get("position"),
"item_id": item.get("item_id"),
"name": item.get("name"),
"brand": item.get("brand"),
"price": item.get("price"),
"list_price": item.get("list_price"),
"currency": item.get("currency"),
"rating": item.get("rating"),
"reviews_count": item.get("reviews_count"),
"availability": item.get("availability"),
"fulfillment": ", ".join(item.get("fulfillment") or []),
"seller": item.get("seller"),
"sponsored": item.get("sponsored"),
"category": item.get("category"),
"url": item.get("url"),
"image": item.get("image"),
"store_id": store.get("store_id"),
"store_city": store.get("city"),
"store_state": store.get("state"),
"store_zip": store.get("postal_code"),
}
)
return rows
# ------------------------------------------------------------- product page
def render_product(data: Dict[str, Any]) -> str:
product = data.get("product") or {}
images = [src for src in (product.get("images") or []) if _safe_link(src)]
main_img = _img(images[0], "wm-pdp-img") if images else ""
thumbs = "".join(_img(src, "wm-pdp-thumb") for src in images[1:6])
price = _num(product.get("price"))
was = _num(product.get("list_price"))
savings = ""
if price is not None and was and was > price:
saved = was - price
savings = (
f'<span class="wm-save">You save {_esc(_money(saved, product.get("currency")))} '
f"({saved / was * 100:.0f}%)</span>"
)
seller = product.get("seller")
seller_html = f'<div class="wm-line">Sold and shipped by <b>{_esc(seller)}</b></div>' if seller else ""
limit = (
f'<div class="wm-muted">Limit {_esc(product.get("order_limit"))} per order</div>'
if product.get("order_limit") else ""
)
link = _safe_link(product.get("url"))
button = (
f'<a class="wm-btn" href="{_esc(link)}" target="_blank" rel="noopener noreferrer">View on Walmart</a>'
if link else ""
)
def name_values(items: Any, cls: str) -> str:
rows = "".join(
f'<div class="wm-spec-name">{_esc(i.get("name"))}</div><div class="wm-spec-value">{_esc(i.get("value"))}</div>'
for i in (items or []) if isinstance(i, dict) and i.get("name")
)
return f'<div class="{cls}">{rows}</div>' if rows else ""
highlights = name_values(product.get("highlights"), "wm-specs")
specs = name_values(product.get("specifications"), "wm-specs")
about = product.get("short_description") or ""
long_text = _html_to_text(product.get("long_description"))
about_html = ""
if about or long_text:
about_html = '<div class="wm-section"><div class="wm-h">About this item</div>'
if about:
about_html += f'<div class="wm-text">{_esc(_html_to_text(about, 1200))}</div>'
if long_text:
about_html += f'<div class="wm-text">{_esc(long_text).replace(chr(10), "<br>")}</div>'
about_html += "</div>"
facts = []
for label, key in [
("Condition", "condition"), ("Model number", "model_number"), ("UPC", "upc"),
("GTIN", "gtin"), ("Returns", "return_policy"), ("Item ID", "item_id"),
]:
if product.get(key):
facts.append({"name": label, "value": product[key]})
facts_html = name_values(facts, "wm-specs")
category = product.get("category") or ""
crumbs = " › ".join(_esc(part) for part in str(category).split("/") if part and part != "Home Page")
return (
f'<div class="wm-wrap">{_store_banner(data.get("store") or {})}'
'<div class="wm-pdp">'
f'<div class="wm-pdp-media">{main_img}<div class="wm-pdp-thumbs">{thumbs}</div></div>'
'<div class="wm-pdp-info">'
+ (f'<div class="wm-crumbs">{crumbs}</div>' if crumbs else "")
+ (f'<div class="wm-brand">{_esc(product.get("brand"))}</div>' if product.get("brand") else "")
+ f'<div class="wm-pdp-name">{_esc(product.get("name"))}</div>'
f"{_rating_html(product.get('rating'), product.get('reviews_count'))}"
f"{_price_html(product.get('price'), product.get('list_price'), product.get('currency'), big=True)}"
f"{savings}"
f'<div class="wm-line">{_stock_html(product.get("availability"))}</div>'
f"{_fulfillment_html(product.get('fulfillment'))}"
f"{seller_html}{limit}{button}"
"</div></div>"
+ (
'<div class="wm-panel">'
+ (f'<div class="wm-section"><div class="wm-h">Highlights</div>{highlights}</div>' if highlights else "")
+ about_html
+ (f'<div class="wm-section"><div class="wm-h">Specifications</div>{specs}</div>' if specs else "")
+ (f'<div class="wm-section"><div class="wm-h">Product details</div>{facts_html}</div>' if facts_html else "")
+ "</div>"
if (highlights or about_html or specs or facts_html) else ""
)
+ "</div>"
)
# ------------------------------------------------------------------- compare
def _place(row: Dict[str, Any]) -> str:
place = ", ".join(p for p in [row.get("city"), row.get("state")] if p)
return place or f"ZIP/store {row.get('location')}"
def render_compare(data: Dict[str, Any]) -> str:
product = data.get("product") or {}
rows = data.get("stores") or []
priced = sorted(
(r for r in rows if _num(r.get("price")) is not None), key=lambda r: _num(r.get("price")) or 0
)
unpriced = [r for r in rows if _num(r.get("price")) is None]
top = max((_num(r.get("price")) or 0 for r in priced), default=0)
best = _num(priced[0].get("price")) if priced else None
link = _safe_link(product.get("url"))
name = _esc(product.get("name") or f"Item {data.get('item_id')}")
name_html = (
f'<a class="wm-name" href="{_esc(link)}" target="_blank" rel="noopener noreferrer">{name}</a>' if link
else f'<span class="wm-name">{name}</span>'
)
head = (
'<div class="wm-cmp-head">'
f'<div class="wm-cmp-img">{_img(product.get("image"), "wm-img")}</div>'
'<div>'
+ (f'<div class="wm-brand">{_esc(product.get("brand"))}</div>' if product.get("brand") else "")
+ f"{name_html}{_rating_html(product.get('rating'), product.get('reviews_count'))}"
f'<div class="wm-muted">Item {_esc(data.get("item_id"))}</div>'
"</div></div>"
)
lines: List[str] = []
for row in priced:
price = _num(row.get("price")) or 0
width = (price / top * 100) if top else 0
is_best = best is not None and abs(price - best) < 0.005
store_bits = " · ".join(
p for p in [f"Walmart #{row['store_id']}" if row.get("store_id") else "", str(row.get("postal_code") or "")] if p
)
lines.append(
f'<div class="wm-cmp-row{" wm-best" if is_best else ""}">'
f'<div class="wm-cmp-store"><b>{_esc(_place(row))}</b><span>{_esc(store_bits)}</span></div>'
f'<div class="wm-cmp-bar"><span style="width:{width:.0f}%"></span></div>'
f'<div class="wm-cmp-price">{_esc(_money(price, row.get("currency")))}'
+ (
f' <span class="wm-was">{_esc(_money(row.get("list_price"), row.get("currency")))}</span>'
if (_num(row.get("list_price")) or 0) > price else ""
)
+ "</div>"
f'<div class="wm-cmp-stock">{_stock_html(row.get("availability"))}{_fulfillment_html(row.get("fulfillment"))}</div>'
+ ('<span class="wm-badge">Lowest price</span>' if is_best and len(priced) > 1 else "")
+ "</div>"
)
for row in unpriced:
reason = row.get("error") or "No price shown at this store."
lines.append(
'<div class="wm-cmp-row wm-cmp-missing">'
f'<div class="wm-cmp-store"><b>{_esc(_place(row))}</b><span>{_esc(row.get("store_id") and "Walmart #" + str(row["store_id"]) or "")}</span></div>'
f'<div class="wm-cmp-note">{_esc(reason)}</div>'
f'<div class="wm-cmp-stock">{_stock_html(row.get("availability"))}</div>'
"</div>"
)
return f'<div class="wm-wrap">{head}<div class="wm-cmp-list">{"".join(lines)}</div></div>'
# ---------------------------------------------------------------- handlers
RESULT_HEADERS = ["#", "Product", "Price", "List price", "Rating", "Reviews", "Stock", "Item ID"]
COMPARE_HEADERS = ["Store", "Location", "ZIP", "Price", "List price", "Stock", "Fulfillment"]
def _picker(choices: List[Tuple[str, str]]) -> Any:
return gr.Dropdown(choices=choices, value=None, visible=bool(choices))
def run_search(
token: str, query: str, location: str, hide_sponsored: bool
) -> Tuple[str, str, List[List[Any]], Dict[str, Any], Optional[str], Any]:
tool = _tool_or_none(token)
if tool is None:
return NO_TOKEN_MD, "", [], {}, None, _picker([])
if not query or not query.strip():
return "Type what you're looking for, e.g. `whole milk`.", "", [], {}, None, _picker([])
data = tool.search(query, location)
if data.get("status") != "success":
return _error_md(data), "", [], data, None, _picker([])
results = data.get("results") or []
prices = [_num(r.get("price")) for r in results if _num(r.get("price")) is not None]
in_stock = sum(1 for r in results if str(r.get("availability") or "").upper() == "IN_STOCK")
on_sale = sum(
1 for r in results
if _num(r.get("list_price")) and _num(r.get("price")) is not None and _num(r["list_price"]) > _num(r["price"])
)
sponsored = sum(1 for r in results if r.get("sponsored"))
parts = [f"**{len(results)}** products", f"**{in_stock}** in stock", f"**{on_sale}** on sale"]
if prices:
parts.append(f"prices **{_money(min(prices))}–{_money(max(prices))}**")
if sponsored:
parts.append(f"{sponsored} sponsored" + (" (hidden)" if hide_sponsored else ""))
summary = " · ".join(parts)
store_label = describe_store(data.get("store"))
footer = []
if store_label:
footer.append(store_label)
if data.get("total_results"):
footer.append(f"{_fmt_int(data['total_results'])} matches on Walmart")
footer.append(f"{data.get('credits_used')} credits used")
summary += "\n\n" + " · ".join(footer)
rows = _result_rows(data)
table = [
[
r["position"], (r["name"] or "")[:90], _money(r["price"], r["currency"]),
_money(r["list_price"], r["currency"]), r["rating"], r["reviews_count"],
str(r["availability"] or "").replace("_", " ").lower(), r["item_id"],
]
for r in rows
]
choices = [
(f"{r.get('position')}. {str(r.get('name') or '')[:70]} — {_money(r.get('price'), r.get('currency')) or 'no price'}",
str(r["item_id"]))
for r in results if r.get("item_id")
]
csv_path = _write_csv(rows, "walmart-search")
return summary, render_results(data, bool(hide_sponsored)), table, data, csv_path, _picker(choices)
def send_to_tabs(picked: Optional[str], product_ref: str, compare_ref: str) -> Tuple[str, str, str]:
if not picked:
return product_ref, compare_ref, ""
return picked, picked, "Sent. Open the **Product details** or **Compare prices** tab and press the button."
def run_product(token: str, ref: str, location: str) -> Tuple[str, str, Dict[str, Any]]:
tool = _tool_or_none(token)
if tool is None:
return NO_TOKEN_MD, "", {}
if not ref or not ref.strip():
return "Paste a Walmart product link or item id, or type a product name.", "", {}
data = tool.product(ref, location)
if data.get("status") != "success":
return _error_md(data), "", data
lines = []
if data.get("note"):
lines.append(data["note"])
lines.append(f"{data.get('credits_used')} credits used.")
return "\n\n".join(lines), render_product(data), data
def run_compare(
token: str, ref: str, locations: str
) -> Tuple[str, str, List[List[Any]], Dict[str, Any], Optional[str]]:
tool = _tool_or_none(token)
if tool is None:
return NO_TOKEN_MD, "", [], {}, None
if not ref or not ref.strip():
return "Paste a Walmart product link or item id, or type a product name.", "", [], {}, None
data = tool.compare(ref, locations)
if data.get("status") != "success":
return _error_md(data), "", [], data, None
rows = data.get("stores") or []
priced = [r for r in rows if _num(r.get("price")) is not None]
lines = []
if data.get("note"):
lines.append(data["note"])
cheapest, dearest = data.get("cheapest"), data.get("most_expensive")
if cheapest and dearest:
low, high = _num(cheapest["price"]) or 0, _num(dearest["price"]) or 0
line = f"Cheapest at **{_place(cheapest)}**: **{_money(low)}**."
if high - low >= 0.01:
line += (
f" That's **{_money(high - low)} ({(high - low) / high * 100:.0f}%) less** than "
f"**{_place(dearest)}** at {_money(high)}."
)
elif len(priced) > 1:
line = f"Same price, **{_money(low)}**, at every store that showed one."
lines.append(line)
else:
lines.append("None of these stores showed a price for this product.")
lines.append(f"Prices found at {len(priced)} of {len(rows)} stores · {data.get('credits_used')} credits used")
if data.get("warnings"):
lines.append("\n".join(f"- {w}" for w in data["warnings"]))
table = [
[
f"#{r.get('store_id')}" if r.get("store_id") else "",
_place(r),
r.get("postal_code") or r.get("location"),
_money(r.get("price"), r.get("currency")) or "—",
_money(r.get("list_price"), r.get("currency")),
str(r.get("availability") or r.get("error") or "").replace("_", " ").lower(),
", ".join(r.get("fulfillment") or []),
]
for r in rows
]
product = data.get("product") or {}
csv_rows = [
{
"item_id": data.get("item_id"),
"product": product.get("name"),
"location_input": r.get("location"),
"store_id": r.get("store_id"),
"city": r.get("city"),
"state": r.get("state"),
"zip": r.get("postal_code"),
"price": r.get("price"),
"list_price": r.get("list_price"),
"currency": r.get("currency"),
"availability": r.get("availability"),
"fulfillment": ", ".join(r.get("fulfillment") or []),
"seller": r.get("seller"),
"error": r.get("error"),
}
for r in rows
]
csv_path = _write_csv(csv_rows, "walmart-price-compare")
return "\n\n".join(lines), render_compare(data), table, data, csv_path
# ----------------------------------------------------------------------- UI
STYLE = """
<style>
.gradio-container, .gradio-container button, .gradio-container input,
.gradio-container textarea, .gradio-container select {
font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "Helvetica Neue", Arial, sans-serif;
}
/* hero */
.wm-hero { position: relative; overflow: hidden; border-radius: 16px; padding: 30px 32px 28px 32px; margin-bottom: 16px;
background: radial-gradient(circle at 85% 20%, #1a8cff 0%, rgba(26,140,255,0) 45%), #0071dc;
font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "Helvetica Neue", Arial, sans-serif; }
.wm-hero, .wm-hero * { color: #ffffff !important; }
.wm-hero-inner { position: relative; z-index: 1; max-width: 620px; }
.wm-hero h1 { font-size: 2.05rem !important; font-weight: 700 !important; margin: 0 0 10px 0 !important;
display: flex; align-items: center; gap: 10px; letter-spacing: -0.01em; }
.wm-hero p { margin: 0 0 8px 0 !important; font-size: 1rem !important; line-height: 1.55 !important; opacity: 0.96; }
.wm-hero strong { font-weight: 700 !important; }
.wm-hero a { text-decoration: underline !important; }
.wm-hero a.wm-cta { display: inline-block; margin-top: 12px; padding: 11px 24px; border-radius: 999px;
background: #ffc220 !important; color: #1a1a1a !important; font-weight: 700 !important; text-decoration: none !important; }
.wm-hero a.wm-cta:hover { background: #ffd451 !important; }
.wm-hero-card { position: absolute; right: 34px; top: 50%; transform: translateY(-50%); width: 270px; z-index: 1;
background: #ffffff; border-radius: 14px; padding: 14px 16px; box-shadow: 0 8px 24px rgba(0,0,0,.18); }
.wm-hero-card, .wm-hero-card * { color: #2e2f32 !important; }
.wm-hc-title { font-size: 0.8rem; font-weight: 700; margin-bottom: 10px; color: #74767c !important; text-transform: uppercase; letter-spacing: .04em; }
.wm-hc-row { display: flex; align-items: center; gap: 8px; margin: 7px 0; font-size: 0.82rem; }
.wm-hc-row span:first-child { width: 92px; }
.wm-hc-bar { flex: 1; height: 8px; border-radius: 999px; background: #e3e4e5; overflow: hidden; }
.wm-hc-bar i { display: block; height: 100%; background: #0071dc; border-radius: 999px; }
.wm-hc-row.best .wm-hc-bar i { background: #2a8703; }
.wm-hc-tag { font-size: 0.7rem; font-weight: 700; color: #2a8703 !important; }
@media (max-width: 900px) { .wm-hero-card { display: none; } }
.wm-panel { background: #ffffff; border: 1px solid #e3e4e5; border-radius: 16px; padding: 4px 22px 22px 22px; margin-top: 14px; }
.wm-note { font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "Helvetica Neue", Arial, sans-serif; border-left: 3px solid #ffc220; background: #fff8e1; padding: 12px 16px; border-radius: 0 8px 8px 0;
font-size: 0.9rem; margin-bottom: 12px; color: #2e2f32 !important; }
.gradio-container .primary, .gradio-container button.primary,
.gradio-container button[variant="primary"] {
background: #0071dc !important; background-image: none !important; border-color: #0071dc !important;
color: #ffffff !important; border-radius: 999px !important; font-weight: 700 !important;
}
.gradio-container .primary:hover, .gradio-container button.primary:hover,
.gradio-container button[variant="primary"]:hover { background: #004f9a !important; }
.gradio-container .tab-nav button.selected { color: #0071dc !important; border-bottom-color: #0071dc !important; }
/* shared */
.wm-wrap { color: #2e2f32 !important; font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "Helvetica Neue", Arial, sans-serif; }
.wm-wrap img { margin: 0 !important; max-width: none; }
.wm-muted { color: #74767c !important; font-size: 0.8rem; margin-top: 3px; }
.wm-empty { background: #ffffff; border: 1px solid #e3e4e5; border-radius: 12px; padding: 20px; color: #74767c !important; }
.wm-store { background: #f2f8fd; border: 1px solid #cfe3f6; border-radius: 10px; padding: 9px 14px; margin-bottom: 12px;
font-size: 0.9rem; color: #2e2f32 !important; }
.wm-store b { color: #2e2f32 !important; }
.wm-line { margin-top: 4px; font-size: 0.85rem; color: #2e2f32 !important; }
.wm-line b { color: #2e2f32 !important; }
.wm-price { display: flex; align-items: baseline; flex-wrap: wrap; gap: 4px; margin: 8px 0 4px 0; color: #2e2f32 !important; }
.wm-amount { color: #2e2f32 !important; font-weight: 700; display: inline-flex; align-items: flex-start; }
.wm-cur, .wm-cents { font-size: 0.8rem; line-height: 1.5; color: inherit !important; }
.wm-dollars { font-size: 1.45rem; line-height: 1; color: inherit !important; }
.wm-price-big .wm-dollars { font-size: 2.2rem; }
.wm-price-big .wm-cur, .wm-price-big .wm-cents { font-size: 1rem; }
.wm-now { color: #2a8703 !important; font-weight: 700; font-size: 0.95rem; }
.wm-amount.wm-sale { color: #2a8703 !important; }
.wm-was { color: #74767c !important; text-decoration: line-through; font-size: 0.85rem; }
.wm-price-na { color: #74767c !important; font-size: 0.85rem; margin: 8px 0 4px 0; }
.wm-save { display: inline-block; background: #eaf3e6; color: #2a8703 !important; font-weight: 700; font-size: 0.8rem;
border-radius: 4px; padding: 3px 8px; margin-bottom: 4px; }
.wm-rating { display: flex; align-items: center; gap: 5px; margin-top: 4px; font-size: 0.8rem; }
.wm-stars { color: #2e2f32 !important; letter-spacing: 0.5px; font-size: 0.85rem; }
.wm-stars-off { color: #d0d1d3 !important; }
.wm-rating-num { color: #2e2f32 !important; font-weight: 600; }
.wm-count { color: #74767c !important; }
.wm-stock { font-size: 0.8rem; font-weight: 600; }
.wm-in { color: #2a8703 !important; }
.wm-out { color: #de1c24 !important; }
.wm-limited { color: #b35c00 !important; }
.wm-chips { display: flex; flex-wrap: wrap; gap: 5px; margin-top: 6px; }
.wm-chip { background: #f2f8fd; color: #004f9a !important; border: 1px solid #cfe3f6; border-radius: 999px; padding: 2px 9px; font-size: 0.75rem; font-weight: 600; }
.wm-name { color: #2e2f32 !important; font-size: 0.9rem; line-height: 1.35; text-decoration: none !important;
display: -webkit-box; -webkit-line-clamp: 3; -webkit-box-orient: vertical; overflow: hidden; }
a.wm-name:hover { text-decoration: underline !important; color: #0071dc !important; }
.wm-id { color: #a4a5a8 !important; font-size: 0.72rem; margin-top: 8px; }
.wm-brand { color: #0071dc !important; font-size: 0.85rem; font-weight: 600; text-decoration: underline; }
.wm-section { margin-top: 22px; }
.wm-h { font-size: 1.1rem; font-weight: 700; color: #2e2f32 !important; margin-bottom: 10px; }
.wm-text { color: #2e2f32 !important; font-size: 0.9rem; line-height: 1.6; margin-bottom: 10px; }
.wm-btn { display: inline-block; margin-top: 14px; padding: 10px 22px; border-radius: 999px; background: #0071dc !important;
color: #ffffff !important; font-weight: 700; text-decoration: none !important; font-size: 0.9rem; }
.wm-btn:hover { background: #004f9a !important; }
/* search grid */
.wm-grid { display: grid; grid-template-columns: repeat(auto-fill, minmax(min(210px, 100%), 1fr)); gap: 12px; }
.wm-card { background: #ffffff; border: 1px solid #e3e4e5; border-radius: 12px; padding: 12px 14px 12px 14px; }
.wm-card:hover { box-shadow: 0 2px 10px rgba(0,0,0,.10); }
.wm-img-box { position: relative; height: 170px; display: flex; align-items: center; justify-content: center;
background: #ffffff; border-radius: 8px; }
.wm-img { max-width: 100%; max-height: 100%; object-fit: contain; }
.wm-sponsored { position: absolute; top: 0; left: 0; background: #f2f2f2; color: #74767c !important;
font-size: 0.68rem; border-radius: 4px; padding: 1px 6px; }
/* product page */
.wm-pdp { display: grid; grid-template-columns: minmax(0, 1fr) minmax(0, 1.1fr); gap: 28px; background: #ffffff;
border: 1px solid #e3e4e5; border-radius: 16px; padding: 22px; }
@media (max-width: 760px) { .wm-pdp { grid-template-columns: 1fr; } }
.wm-pdp-media { display: flex; flex-direction: column; gap: 10px; }
.wm-pdp-img { width: 100%; max-height: 380px; object-fit: contain; }
.wm-pdp-thumbs { display: flex; gap: 8px; flex-wrap: wrap; }
.wm-pdp-thumb { width: 62px; height: 62px; object-fit: contain; border: 1px solid #e3e4e5; border-radius: 8px; background: #ffffff; }
.wm-crumbs { color: #74767c !important; font-size: 0.75rem; margin-bottom: 8px; }
.wm-pdp-name { font-size: 1.35rem; font-weight: 600; line-height: 1.3; color: #2e2f32 !important; margin-top: 4px; }
.wm-specs { display: grid; grid-template-columns: minmax(120px, 0.6fr) 1fr; border-top: 1px solid #e3e4e5; background: #ffffff; }
.wm-spec-name, .wm-spec-value { padding: 9px 12px; border-bottom: 1px solid #e3e4e5; font-size: 0.88rem; }
.wm-spec-name { color: #74767c !important; }
.wm-spec-value { color: #2e2f32 !important; }
/* compare */
.wm-cmp-head { display: flex; gap: 16px; align-items: center; background: #ffffff; border: 1px solid #e3e4e5;
border-radius: 12px; padding: 14px 16px; }
.wm-cmp-img { width: 90px; height: 90px; display: flex; align-items: center; justify-content: center; flex-shrink: 0; }
.wm-cmp-list { display: flex; flex-direction: column; gap: 8px; margin-top: 12px; }
.wm-cmp-row { position: relative; display: grid; grid-template-columns: 200px 1fr 130px 210px; gap: 14px; align-items: center;
background: #ffffff; border: 1px solid #e3e4e5; border-radius: 12px; padding: 12px 16px; }
@media (max-width: 860px) { .wm-cmp-row { grid-template-columns: 1fr; gap: 6px; } }
.wm-cmp-row.wm-best { border-color: #2a8703; box-shadow: 0 0 0 1px #2a8703 inset; }
.wm-cmp-store b { display: block; color: #2e2f32 !important; font-size: 0.95rem; }
.wm-cmp-store span { color: #74767c !important; font-size: 0.78rem; }
.wm-cmp-bar { height: 10px; background: #e3e4e5; border-radius: 999px; overflow: hidden; }
.wm-cmp-bar span { display: block; height: 100%; background: #0071dc; border-radius: 999px; }
.wm-best .wm-cmp-bar span { background: #2a8703; }
.wm-cmp-price { font-size: 1.2rem; font-weight: 700; color: #2e2f32 !important; }
.wm-best .wm-cmp-price { color: #2a8703 !important; }
.wm-cmp-stock .wm-chips { margin-top: 3px; }
.wm-badge { position: absolute; top: -9px; right: 14px; background: #2a8703; color: #ffffff !important; font-size: 0.7rem;
font-weight: 700; border-radius: 4px; padding: 2px 8px; }
.wm-cmp-missing { opacity: 0.85; }
.wm-cmp-note { color: #74767c !important; font-size: 0.85rem; grid-column: span 2; }
footer { display: none !important; }
</style>
"""
HERO = f"""
<div class="wm-hero">
<div class="wm-hero-inner">
<h1>{CART_SVG.format(size=34)} Walmart Scraper</h1>
<p><strong>Walmart prices change from store to store.</strong> Search products at any US store by ZIP code,
pull a product's full details, or check one product's price and stock at up to five stores side by side.</p>
<p>Built on the <a href="https://scrape.do/documentation/walmart-scraper-api/" target="_blank" rel="noopener noreferrer">Scrape.do Walmart API</a>,
which picks the store for you and gets past Walmart's bot protection. Use it for price monitoring,
assortment research, MAP checks, or to give an AI agent live retail prices.</p>
<a class="wm-cta" href="{SCRAPE_DO_SIGNUP_URL}" target="_blank" rel="noopener noreferrer">Get a free API token →</a>
</div>
<div class="wm-hero-card" aria-hidden="true">
<div class="wm-hc-title">One product · four stores</div>
<div class="wm-hc-row"><span>Store A</span><span class="wm-hc-bar"><i style="width:92%"></i></span></div>
<div class="wm-hc-row best"><span>Store B</span><span class="wm-hc-bar"><i style="width:71%"></i></span><span class="wm-hc-tag">Lowest</span></div>
<div class="wm-hc-row"><span>Store C</span><span class="wm-hc-bar"><i style="width:100%"></i></span></div>
<div class="wm-hc-row"><span>Store D</span><span class="wm-hc-bar"><i style="width:84%"></i></span></div>
</div>
</div>
"""
CREDIT_NOTE = """
<div class="wm-note">
Every call costs 10 credits: one search, one product, or one store in a price comparison. Failed calls
are free. The free 1,000 credits cover about 100 calls. Typing a product name instead of pasting a link
adds one search (10 credits) to find it.
</div>
"""
FOOTER_MD = f"""
---
### Use it as a smolagents Tool
```python
from smolagents import CodeAgent, InferenceClientModel
from tool import ScrapeDoWalmartTool
agent = CodeAgent(
tools=[ScrapeDoWalmartTool(api_token="YOUR_SCRAPEDO_TOKEN")],
model=InferenceClientModel(),
)
agent.run("Find the cheapest gallon of whole milk at the Walmart nearest ZIP 60074, then compare its price in Dallas and Los Angeles.")
```
Or set `SCRAPE_DO_API_TOKEN` in the environment and instantiate with no arguments.
Want to scrape category pages and track price changes over time? The
[Walmart scraping guide](https://scrape.do/blog/walmart-scraping/) walks through it in Python.
[Scrape.do](https://scrape.do/) · [Walmart API docs](https://scrape.do/documentation/walmart-scraper-api/) · [Sign up free]({SCRAPE_DO_SIGNUP_URL})
"""
def build_demo() -> gr.Blocks:
with gr.Blocks(title="Walmart Scraper — Scrape.do") as demo:
gr.HTML(STYLE)
gr.HTML(HERO)
with gr.Row():
api_token = gr.Textbox(
label="Scrape.do API token",
placeholder="Paste your token here",
type="password",
info="Free tier: 1,000 credits a month, about 100 calls.",
scale=3,
)
location = gr.Textbox(
label="Store: ZIP code or Walmart store number",
value=DEFAULT_LOCATION,
placeholder="07094",
info="Prices and stock are for the nearest store.",
scale=2,
)
gr.HTML(CREDIT_NOTE)
with gr.Tabs():
with gr.Tab("Search products"):
with gr.Row():
query = gr.Textbox(label="Search Walmart", placeholder="whole milk", scale=4)
hide_sponsored = gr.Checkbox(label="Hide sponsored", value=False, scale=1)
search_btn = gr.Button("Search Walmart", variant="primary")
search_summary = gr.Markdown()
results_view = gr.HTML()
results_table = gr.Dataframe(headers=RESULT_HEADERS, wrap=True, label="Products")
results_csv = gr.File(label="Download results as CSV")
pick = gr.Dropdown(
label="Open one of these products in the Details and Compare tabs",
choices=[],
value=None,
visible=False,
)
pick_note = gr.Markdown()
with gr.Accordion("Raw JSON response", open=False):
results_json = gr.JSON()
with gr.Tab("Product details"):
product_ref = gr.Textbox(
label="Walmart product link, item id, or product name",
placeholder="https://www.walmart.com/ip/…/17221971947 or 17221971947",
)
product_btn = gr.Button("Get product details", variant="primary")
product_summary = gr.Markdown()
product_view = gr.HTML()
with gr.Accordion("Raw JSON response", open=False):
product_json = gr.JSON()
with gr.Tab("Compare prices by ZIP"):
gr.Markdown(
"Same product, different stores. Enter up to "
f"{MAX_COMPARE_LOCATIONS} ZIP codes or store numbers; each one costs 10 credits."
)
compare_ref = gr.Textbox(
label="Walmart product link, item id, or product name",
placeholder="https://www.walmart.com/ip/…/17221971947 or 17221971947",
)
compare_locations = gr.Textbox(
label="ZIP codes or store numbers, separated by commas",
value=", ".join(DEFAULT_COMPARE_LOCATIONS),
info="Default: Secaucus NJ, Deer Park IL, Dallas TX, Los Angeles CA.",
)
compare_btn = gr.Button("Compare prices", variant="primary")
compare_summary = gr.Markdown()
compare_view = gr.HTML()
compare_table = gr.Dataframe(headers=COMPARE_HEADERS, wrap=True, label="Price by store")
compare_csv = gr.File(label="Download comparison as CSV")
with gr.Accordion("Raw JSON response", open=False):
compare_json = gr.JSON()
search_inputs = [api_token, query, location, hide_sponsored]
search_outputs = [search_summary, results_view, results_table, results_json, results_csv, pick]
search_btn.click(fn=run_search, inputs=search_inputs, outputs=search_outputs)
query.submit(fn=run_search, inputs=search_inputs, outputs=search_outputs)
pick.change(fn=send_to_tabs, inputs=[pick, product_ref, compare_ref], outputs=[product_ref, compare_ref, pick_note])
product_inputs = [api_token, product_ref, location]
product_outputs = [product_summary, product_view, product_json]
product_btn.click(fn=run_product, inputs=product_inputs, outputs=product_outputs)
product_ref.submit(fn=run_product, inputs=product_inputs, outputs=product_outputs)
compare_inputs = [api_token, compare_ref, compare_locations]
compare_outputs = [compare_summary, compare_view, compare_table, compare_json, compare_csv]
compare_btn.click(fn=run_compare, inputs=compare_inputs, outputs=compare_outputs)
compare_ref.submit(fn=run_compare, inputs=compare_inputs, outputs=compare_outputs)
gr.Markdown(FOOTER_MD)
return demo
# Hugging Face Spaces launches the module-level `demo` object rather than
# calling launch() itself, so build it at import time.
demo = build_demo()
if __name__ == "__main__":
demo.launch()
|