myntra-scraper 0.1.0__tar.gz

myntra_scraper-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Buğrahan Saka
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

myntra_scraper-0.1.0/MANIFEST.in

@@ -0,0 +1,3 @@
+include README.md LICENSE
+recursive-include tests *.py *.html
+recursive-include examples *.py

myntra_scraper-0.1.0/PKG-INFO

@@ -0,0 +1,146 @@
+Metadata-Version: 2.4
+Name: myntra-scraper
+Version: 0.1.0
+Summary: Scrape Myntra listings (price, MRP, discount, rating) with real pagination, and product pages (price and stock per size and seller) with Python.
+Author: Buğrahan Saka
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/bugrahansss/myntra-scraper
+Project-URL: Source, https://github.com/bugrahansss/myntra-scraper
+Project-URL: Issues, https://github.com/bugrahansss/myntra-scraper/issues
+Project-URL: Scrape.do, https://scrape.do/?utm_source=pypi&utm_medium=package&utm_campaign=myntra-scraper
+Keywords: myntra,web scraping,fashion,ecommerce,scraper,akamai,india
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Internet :: WWW/HTTP :: Indexing/Search
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests>=2.25
+Dynamic: license-file
+
+# myntra-scraper
+
+[![PyPI](https://img.shields.io/pypi/v/myntra-scraper)](https://pypi.org/project/myntra-scraper/)
+[![Python](https://img.shields.io/pypi/pyversions/myntra-scraper)](https://pypi.org/project/myntra-scraper/)
+[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
+
+A Python scraper for [Myntra](https://www.myntra.com), India's largest fashion marketplace. Two jobs:
+
+- **Listings and search:** any listing or search URL (`/men-tshirts`, `/levis?rawQuery=levis`, with sort and filters) → name, brand, price, MRP, discount, rating, rating count, sizes, colour, image and URL. **Real pagination**, 50 products per page, sponsored products left out.
+- **Product pages:** price, MRP, rating and attributes, plus **one row per size and seller with that seller's price and the exact units in stock**.
+
+Output as Python dicts, JSON or CSV. One dependency (`requests`), no browser.
+
+```bash
+pip install myntra-scraper
+```
+
+## Why a plain request fails
+
+Myntra sits behind Akamai Bot Manager (`_abck`, `bm_sz` cookies). A script doesn't get an error, it gets nothing:
+
+| Request | Result |
+| --- | --- |
+| `requests`, default or Chrome user agent | connection opens, no bytes, timeout after 20 s |
+| `curl` (HTTP/2) | `stream was not closed cleanly: INTERNAL_ERROR` |
+| Through Scrape.do, no parameters | 200 in ~3 s, full page, 1 credit |
+
+Pages are fetched through the [Scrape.do](https://scrape.do/?utm_source=github&utm_medium=readme&utm_campaign=myntra-scraper) API with a plain request: no `render`, no `super`, 1 credit per page. You need a Scrape.do API token; the free plan includes 1,000 credits a month.
+
+## Quick start
+
+```python
+from myntra_scraper import MyntraScraper
+
+scraper = MyntraScraper(token="YOUR_SCRAPEDO_TOKEN")  # or set SCRAPEDO_TOKEN
+
+# 3 pages of 50 = 150 products (4 credits: one page visit + three API pages)
+rows = scraper.get_listing("https://www.myntra.com/men-tshirts?sort=new", max_pages=3)
+for row in rows[:3]:
+    print(row["brand"], row["name"], row["price_inr"], row["mrp_inr"], row["discount_pct"])
+
+product = scraper.get_product(rows[0]["url"])
+print(product["units_in_stock"], product["sizes_in_stock"], "/", product["sizes_total"], "sizes in stock")
+for size in product["sizes"]:
+    print(size["size"], size["seller"], size["price_inr"], size["units"])
+```
+
+### Command line
+
+```bash
+export SCRAPEDO_TOKEN=your_token
+
+# 3 pages of a listing, CSV
+myntra-scraper listing "https://www.myntra.com/men-tshirts?sort=new" --pages 3 -f csv -o myntra-listing.csv
+
+# product summaries for the first 10 products from that file
+myntra-scraper product -i myntra-listing.csv --limit 10 -f csv -o myntra-products.csv
+
+# one row per size and seller
+myntra-scraper product -i myntra-listing.csv --limit 10 --sizes -f csv -o myntra-sizes.csv
+```
+
+`product` reads the `url` column of the listing CSV, so the commands chain.
+
+### Output
+
+Size rows (from the fictional test page in [`tests/fixtures`](tests/fixtures/product_page.html)):
+
+```json
+[
+  {"product_id": 90000001, "size": "M", "sku_id": 900000012, "available": true,
+   "seller": "Example Retail Two", "seller_id": 202, "price_inr": 449, "mrp_inr": 999, "units": 5},
+  {"product_id": 90000001, "size": "M", "sku_id": 900000012, "available": true,
+   "seller": "Example Retail One", "seller_id": 101, "price_inr": 469, "mrp_inr": 999, "units": 30}
+]
+```
+
+Listing columns: `product_id, name, brand, price_inr, mrp_inr, discount_pct, rating, rating_count, sizes, gender, article_type, colour, image, url`.
+
+Product columns: `product_id, name, brand, price_inr, mrp_inr, discount_pct, rating, rating_count, colour, article_type, gender, country_of_origin, sizes_in_stock, sizes_total, units_in_stock, lowest_size_price_inr, highest_size_price_inr, sellers, url` (plus `attributes` and `sizes` in Python/JSON).
+
+## How it works
+
+**The data is one JSON object.** Myntra renders every page on the server and puts the data in an inline script, `window.__myx = {...}`. Listings keep their products in `searchData.results.products`, product pages keep everything in `pdpData`. The scraper finds the assignment and reads the object with `json.JSONDecoder.raw_decode`. No CSS selectors.
+
+**Sponsored products are separate.** A listing page carries the organic results in `products` and the ads in `plaProducts` (18 of them on a men's T-shirts page). Only the organic products are returned.
+
+**`?p=2` is ignored.** Ask the HTML for page 2, 3 or 50 and you get the first 50 products again. In our test, page 2 of a listing sorted by newest shared 49 of 50 products with page 1. The site pages through its search API, `/gateway/v4/search/<slug>`, which:
+
+1. returns 401 without the cookies a page visit sets (`at`, `_abck`, `bm_sz` and others), and
+2. ignores `p` and `o` as well, unless the request carries a `pagination-context` header. Every API response returns a new `pagination-context` header; sending it back moves to the next 50.
+
+So `get_listing(max_pages=N)` visits the listing once for its cookies, then calls the search API N times, passing the cursor from each response to the next request (Scrape.do forwards the cookie and cursor headers with `extraHeaders=true`). In our test, four API pages returned 200 distinct products.
+
+**Listing price vs size price.** A listing card has one price. On the product page every size lists its sellers, each with its own price and stock count. On a Levi's T-shirt listed at ₹389, sizes M and XL had a seller at ₹389 while sizes S and L were only available from a second seller at ₹402. The `sizes` rows keep that split.
+
+## Limits
+
+- **One location.** Prices and stock are what Myntra shows without a delivery pincode.
+- **Credits.** `max_pages=1` reads the listing HTML (1 credit). More pages cost one page visit plus one credit per API page.
+- **Errors.** Non-200 responses raise `ScrapeError` with the status code. A 200 without Myntra's data (an Akamai page) is treated as a failure. Server errors, 429s and empty pages are retried twice; client errors are not.
+
+## Responsible use
+
+The scraper reads listing, product and search pages, which Myntra's robots.txt allows (`Allow: /`); it does not touch cart, checkout, account or size-chart paths. Product data is not personal data. Read Myntra's terms for your use case and keep request rates modest. This is not legal advice.
+
+## Development
+
+```bash
+git clone https://github.com/bugrahansss/myntra-scraper
+cd myntra-scraper
+pip install -e .
+python -m unittest discover -s tests -v
+```
+
+The tests run offline against fictional fixture pages.
+
+## License
+
+MIT
+
+---
+
+Built and tested with [Scrape.do](https://scrape.do/?utm_source=github&utm_medium=readme&utm_campaign=myntra-scraper), November 2026.

myntra_scraper-0.1.0/README.md

@@ -0,0 +1,124 @@
+# myntra-scraper
+
+[![PyPI](https://img.shields.io/pypi/v/myntra-scraper)](https://pypi.org/project/myntra-scraper/)
+[![Python](https://img.shields.io/pypi/pyversions/myntra-scraper)](https://pypi.org/project/myntra-scraper/)
+[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
+
+A Python scraper for [Myntra](https://www.myntra.com), India's largest fashion marketplace. Two jobs:
+
+- **Listings and search:** any listing or search URL (`/men-tshirts`, `/levis?rawQuery=levis`, with sort and filters) → name, brand, price, MRP, discount, rating, rating count, sizes, colour, image and URL. **Real pagination**, 50 products per page, sponsored products left out.
+- **Product pages:** price, MRP, rating and attributes, plus **one row per size and seller with that seller's price and the exact units in stock**.
+
+Output as Python dicts, JSON or CSV. One dependency (`requests`), no browser.
+
+```bash
+pip install myntra-scraper
+```
+
+## Why a plain request fails
+
+Myntra sits behind Akamai Bot Manager (`_abck`, `bm_sz` cookies). A script doesn't get an error, it gets nothing:
+
+| Request | Result |
+| --- | --- |
+| `requests`, default or Chrome user agent | connection opens, no bytes, timeout after 20 s |
+| `curl` (HTTP/2) | `stream was not closed cleanly: INTERNAL_ERROR` |
+| Through Scrape.do, no parameters | 200 in ~3 s, full page, 1 credit |
+
+Pages are fetched through the [Scrape.do](https://scrape.do/?utm_source=github&utm_medium=readme&utm_campaign=myntra-scraper) API with a plain request: no `render`, no `super`, 1 credit per page. You need a Scrape.do API token; the free plan includes 1,000 credits a month.
+
+## Quick start
+
+```python
+from myntra_scraper import MyntraScraper
+
+scraper = MyntraScraper(token="YOUR_SCRAPEDO_TOKEN")  # or set SCRAPEDO_TOKEN
+
+# 3 pages of 50 = 150 products (4 credits: one page visit + three API pages)
+rows = scraper.get_listing("https://www.myntra.com/men-tshirts?sort=new", max_pages=3)
+for row in rows[:3]:
+    print(row["brand"], row["name"], row["price_inr"], row["mrp_inr"], row["discount_pct"])
+
+product = scraper.get_product(rows[0]["url"])
+print(product["units_in_stock"], product["sizes_in_stock"], "/", product["sizes_total"], "sizes in stock")
+for size in product["sizes"]:
+    print(size["size"], size["seller"], size["price_inr"], size["units"])
+```
+
+### Command line
+
+```bash
+export SCRAPEDO_TOKEN=your_token
+
+# 3 pages of a listing, CSV
+myntra-scraper listing "https://www.myntra.com/men-tshirts?sort=new" --pages 3 -f csv -o myntra-listing.csv
+
+# product summaries for the first 10 products from that file
+myntra-scraper product -i myntra-listing.csv --limit 10 -f csv -o myntra-products.csv
+
+# one row per size and seller
+myntra-scraper product -i myntra-listing.csv --limit 10 --sizes -f csv -o myntra-sizes.csv
+```
+
+`product` reads the `url` column of the listing CSV, so the commands chain.
+
+### Output
+
+Size rows (from the fictional test page in [`tests/fixtures`](tests/fixtures/product_page.html)):
+
+```json
+[
+  {"product_id": 90000001, "size": "M", "sku_id": 900000012, "available": true,
+   "seller": "Example Retail Two", "seller_id": 202, "price_inr": 449, "mrp_inr": 999, "units": 5},
+  {"product_id": 90000001, "size": "M", "sku_id": 900000012, "available": true,
+   "seller": "Example Retail One", "seller_id": 101, "price_inr": 469, "mrp_inr": 999, "units": 30}
+]
+```
+
+Listing columns: `product_id, name, brand, price_inr, mrp_inr, discount_pct, rating, rating_count, sizes, gender, article_type, colour, image, url`.
+
+Product columns: `product_id, name, brand, price_inr, mrp_inr, discount_pct, rating, rating_count, colour, article_type, gender, country_of_origin, sizes_in_stock, sizes_total, units_in_stock, lowest_size_price_inr, highest_size_price_inr, sellers, url` (plus `attributes` and `sizes` in Python/JSON).
+
+## How it works
+
+**The data is one JSON object.** Myntra renders every page on the server and puts the data in an inline script, `window.__myx = {...}`. Listings keep their products in `searchData.results.products`, product pages keep everything in `pdpData`. The scraper finds the assignment and reads the object with `json.JSONDecoder.raw_decode`. No CSS selectors.
+
+**Sponsored products are separate.** A listing page carries the organic results in `products` and the ads in `plaProducts` (18 of them on a men's T-shirts page). Only the organic products are returned.
+
+**`?p=2` is ignored.** Ask the HTML for page 2, 3 or 50 and you get the first 50 products again. In our test, page 2 of a listing sorted by newest shared 49 of 50 products with page 1. The site pages through its search API, `/gateway/v4/search/<slug>`, which:
+
+1. returns 401 without the cookies a page visit sets (`at`, `_abck`, `bm_sz` and others), and
+2. ignores `p` and `o` as well, unless the request carries a `pagination-context` header. Every API response returns a new `pagination-context` header; sending it back moves to the next 50.
+
+So `get_listing(max_pages=N)` visits the listing once for its cookies, then calls the search API N times, passing the cursor from each response to the next request (Scrape.do forwards the cookie and cursor headers with `extraHeaders=true`). In our test, four API pages returned 200 distinct products.
+
+**Listing price vs size price.** A listing card has one price. On the product page every size lists its sellers, each with its own price and stock count. On a Levi's T-shirt listed at ₹389, sizes M and XL had a seller at ₹389 while sizes S and L were only available from a second seller at ₹402. The `sizes` rows keep that split.
+
+## Limits
+
+- **One location.** Prices and stock are what Myntra shows without a delivery pincode.
+- **Credits.** `max_pages=1` reads the listing HTML (1 credit). More pages cost one page visit plus one credit per API page.
+- **Errors.** Non-200 responses raise `ScrapeError` with the status code. A 200 without Myntra's data (an Akamai page) is treated as a failure. Server errors, 429s and empty pages are retried twice; client errors are not.
+
+## Responsible use
+
+The scraper reads listing, product and search pages, which Myntra's robots.txt allows (`Allow: /`); it does not touch cart, checkout, account or size-chart paths. Product data is not personal data. Read Myntra's terms for your use case and keep request rates modest. This is not legal advice.
+
+## Development
+
+```bash
+git clone https://github.com/bugrahansss/myntra-scraper
+cd myntra-scraper
+pip install -e .
+python -m unittest discover -s tests -v
+```
+
+The tests run offline against fictional fixture pages.
+
+## License
+
+MIT
+
+---
+
+Built and tested with [Scrape.do](https://scrape.do/?utm_source=github&utm_medium=readme&utm_campaign=myntra-scraper), November 2026.

myntra_scraper-0.1.0/examples/listing_to_sizes.py

@@ -0,0 +1,54 @@
+"""Read a few pages of a Myntra listing, then stock and price per size for the first products.
+
+Usage:
+    export SCRAPEDO_TOKEN=your_token
+    python listing_to_sizes.py "https://www.myntra.com/men-tshirts?sort=new" 3 10
+
+Writes myntra-listing.csv (price, MRP, discount, rating per product) and
+myntra-sizes.csv (one row per size and seller: price, MRP, units in stock).
+"""
+
+import csv
+import sys
+
+from myntra_scraper import LISTING_FIELDS, SIZE_FIELDS, MyntraScraper, ScrapeError
+
+
+def write(path, fields, rows):
+    with open(path, "w", newline="", encoding="utf-8") as handle:
+        writer = csv.DictWriter(handle, fieldnames=fields, extrasaction="ignore")
+        writer.writeheader()
+        writer.writerows(rows)
+
+
+def main(listing_url: str, pages: int = 3, max_products: int = 10) -> None:
+    scraper = MyntraScraper()  # reads SCRAPEDO_TOKEN
+    listing = scraper.get_listing(listing_url, max_pages=pages)
+    write("myntra-listing.csv", LISTING_FIELDS, listing)
+    print(f"Saved {len(listing)} products to myntra-listing.csv")
+
+    sizes = []
+    for row in listing[:max_products]:
+        try:
+            product = scraper.get_product(row["url"])
+        except ScrapeError as exc:
+            print(f"skipped {row['url']}: {exc}")
+            continue
+        if not product:
+            continue
+        sizes.extend(product["sizes"])
+        print(
+            f"{product['name'][:50]} | listed Rs {row['price_inr']} | sizes Rs "
+            f"{product['lowest_size_price_inr']}-{product['highest_size_price_inr']} | "
+            f"{product['units_in_stock']} units, {product['sizes_in_stock']}/{product['sizes_total']} sizes in stock"
+        )
+    write("myntra-sizes.csv", SIZE_FIELDS, sizes)
+    print(f"Saved {len(sizes)} size rows to myntra-sizes.csv")
+
+
+if __name__ == "__main__":
+    main(
+        sys.argv[1],
+        int(sys.argv[2]) if len(sys.argv) > 2 else 3,
+        int(sys.argv[3]) if len(sys.argv) > 3 else 10,
+    )

myntra_scraper-0.1.0/pyproject.toml

@@ -0,0 +1,34 @@
+[build-system]
+requires = ["setuptools>=77"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "myntra-scraper"
+version = "0.1.0"
+description = "Scrape Myntra listings (price, MRP, discount, rating) with real pagination, and product pages (price and stock per size and seller) with Python."
+readme = "README.md"
+requires-python = ">=3.8"
+license = "MIT"
+license-files = ["LICENSE"]
+authors = [{ name = "Buğrahan Saka" }]
+keywords = ["myntra", "web scraping", "fashion", "ecommerce", "scraper", "akamai", "india"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Topic :: Internet :: WWW/HTTP :: Indexing/Search",
+]
+dependencies = ["requests>=2.25"]
+
+[project.urls]
+Homepage = "https://github.com/bugrahansss/myntra-scraper"
+Source = "https://github.com/bugrahansss/myntra-scraper"
+Issues = "https://github.com/bugrahansss/myntra-scraper/issues"
+"Scrape.do" = "https://scrape.do/?utm_source=pypi&utm_medium=package&utm_campaign=myntra-scraper"
+
+[project.scripts]
+myntra-scraper = "myntra_scraper.cli:main"
+
+[tool.setuptools.packages.find]
+where = ["src"]

myntra_scraper-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

myntra_scraper-0.1.0/src/myntra_scraper/__init__.py

@@ -0,0 +1,32 @@
+"""Scrape Myntra listings and product pages (price, MRP, sizes, stock per seller) with Python."""
+
+from .client import MyntraScraper, ScrapeError
+from .parser import (
+    LISTING_FIELDS,
+    PRODUCT_FIELDS,
+    SIZE_FIELDS,
+    extract_myx,
+    listing_info,
+    parse_listing,
+    parse_product,
+    parse_products,
+    parse_sizes,
+    product_url,
+)
+
+__all__ = [
+    "LISTING_FIELDS",
+    "MyntraScraper",
+    "PRODUCT_FIELDS",
+    "SIZE_FIELDS",
+    "ScrapeError",
+    "extract_myx",
+    "listing_info",
+    "parse_listing",
+    "parse_product",
+    "parse_products",
+    "parse_sizes",
+    "product_url",
+]
+
+__version__ = "0.1.0"

myntra_scraper-0.1.0/src/myntra_scraper/cli.py

@@ -0,0 +1,110 @@
+"""Command line entry point: ``myntra-scraper listing URL`` / ``myntra-scraper product URL ...``."""
+
+from __future__ import annotations
+
+import argparse
+import csv
+import json
+import sys
+from typing import List, Optional
+
+from . import __version__
+from .client import TOKEN_ENV, MyntraScraper, ScrapeError
+from .parser import LISTING_FIELDS, PRODUCT_FIELDS, SIZE_FIELDS
+
+
+def build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(
+        prog="myntra-scraper",
+        description="Scrape Myntra listings and product pages (price, MRP, sizes, stock per seller) into JSON or CSV.",
+    )
+    parser.add_argument("--version", action="version", version=f"%(prog)s {__version__}")
+    sub = parser.add_subparsers(dest="command", required=True)
+
+    lst = sub.add_parser("listing", help="Products of a listing or search page, 50 per page")
+    lst.add_argument("url", help="A Myntra listing or search URL, e.g. https://www.myntra.com/men-tshirts?sort=new")
+    lst.add_argument("--pages", type=int, default=1, help="Pages of 50 to read (default 1)")
+
+    prod = sub.add_parser("product", help="Product pages: summary, or one row per size and seller with --sizes")
+    prod.add_argument("urls", nargs="*", help="Myntra product URLs or style ids")
+    prod.add_argument("-i", "--input", help="Text file with one URL per line, or a CSV with a 'url' column")
+    prod.add_argument("--limit", type=int, default=0, help="Stop after this many products (0 = all)")
+    prod.add_argument("--sizes", action="store_true", help="Output one row per size and seller")
+
+    for p in (lst, prod):
+        p.add_argument("-t", "--token", help=f"Scrape.do API token (default: ${TOKEN_ENV})")
+        p.add_argument("-f", "--format", choices=("json", "csv"), default="json")
+        p.add_argument("-o", "--output", help="Write to this file instead of stdout")
+    return parser
+
+
+def _read_urls(args: argparse.Namespace) -> List[str]:
+    urls = list(args.urls)
+    if args.input:
+        with open(args.input, encoding="utf-8", newline="") as handle:
+            if args.input.endswith(".csv"):
+                urls.extend(row["url"] for row in csv.DictReader(handle) if row.get("url"))
+            else:
+                urls.extend(line.strip() for line in handle if line.strip() and not line.startswith("#"))
+    return urls[: args.limit] if args.limit else urls
+
+
+def _write(rows: List[dict], fields: List[str], fmt: str, stream) -> None:
+    if fmt == "csv":
+        writer = csv.DictWriter(stream, fieldnames=fields, extrasaction="ignore")
+        writer.writeheader()
+        writer.writerows(rows)
+    else:
+        json.dump(rows, stream, indent=2, ensure_ascii=False)
+        stream.write("\n")
+
+
+def main(argv: Optional[List[str]] = None) -> int:
+    args = build_parser().parse_args(argv)
+    try:
+        scraper = MyntraScraper(token=args.token)
+    except ValueError as exc:
+        print(exc, file=sys.stderr)
+        return 2
+
+    failures = 0
+    if args.command == "listing":
+        fields = LISTING_FIELDS
+        try:
+            rows = scraper.get_listing(args.url, max_pages=max(1, args.pages))
+        except (ScrapeError, ValueError) as exc:
+            print(f"fail  {args.url}: {exc}", file=sys.stderr)
+            return 1
+        print(f"{len(rows)} products", file=sys.stderr)
+    else:
+        fields = SIZE_FIELDS if args.sizes else PRODUCT_FIELDS
+        urls = _read_urls(args)
+        if not urls:
+            print("No URLs given. Pass product URLs or --input FILE.", file=sys.stderr)
+            return 2
+        rows = []
+        for url in urls:
+            try:
+                product = scraper.get_product(url)
+            except (ScrapeError, ValueError) as exc:
+                failures += 1
+                print(f"fail  {url}: {exc}", file=sys.stderr)
+                continue
+            if not product:
+                failures += 1
+                print(f"fail  {url}: no product data", file=sys.stderr)
+                continue
+            rows.extend(product["sizes"] if args.sizes else [product])
+            print(f"ok    {url}", file=sys.stderr)
+
+    if args.output:
+        with open(args.output, "w", encoding="utf-8", newline="" if args.format == "csv" else None) as handle:
+            _write(rows, fields, args.format, handle)
+        print(f"Saved {len(rows)} rows to {args.output}", file=sys.stderr)
+    else:
+        _write(rows, fields, args.format, sys.stdout)
+    return 1 if failures and not rows else 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())