scrapingbee-cli 1.4.2__tar.gz → 1.4.3__tar.gz

{scrapingbee_cli-1.4.2/src/scrapingbee_cli.egg-info → scrapingbee_cli-1.4.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scrapingbee-cli
-Version: 1.4.2
+Version: 1.4.3
 Summary: Command-line client for the ScrapingBee API: scrape pages (single or batch), crawl sites, check usage/credits, and use Google Search, Fast Search, Amazon, Walmart, YouTube, and ChatGPT from the terminal.
 Author: ScrapingBee
 License-Expression: MIT
@@ -97,7 +97,7 @@ scrapingbee [command] [arguments] [options]
 | `scrape [url]` | Scrape a URL (HTML, JS, screenshot, extract) |
 | `crawl` | Crawl sites following links, with AI extraction and save-pattern filtering |
 | `google` / `fast-search` | Search SERP APIs |
-| `amazon-product` / `amazon-search` | Amazon product and search |
+| `amazon-product` / `amazon-pricing` / `amazon-search` | Amazon product, pricing and search |
 | `walmart-search` / `walmart-product` | Walmart search and product |
 | `youtube-search` / `youtube-metadata` | YouTube search and video metadata |
 | `chatgpt` | ChatGPT API (`--search true` for web-enhanced responses) |

{scrapingbee_cli-1.4.2 → scrapingbee_cli-1.4.3}/README.md

@@ -58,7 +58,7 @@ scrapingbee [command] [arguments] [options]
 | `scrape [url]` | Scrape a URL (HTML, JS, screenshot, extract) |
 | `crawl` | Crawl sites following links, with AI extraction and save-pattern filtering |
 | `google` / `fast-search` | Search SERP APIs |
-| `amazon-product` / `amazon-search` | Amazon product and search |
+| `amazon-product` / `amazon-pricing` / `amazon-search` | Amazon product, pricing and search |
 | `walmart-search` / `walmart-product` | Walmart search and product |
 | `youtube-search` / `youtube-metadata` | YouTube search and video metadata |
 | `chatgpt` | ChatGPT API (`--search true` for web-enhanced responses) |

{scrapingbee_cli-1.4.2 → scrapingbee_cli-1.4.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "scrapingbee-cli"
-version = "1.4.2"
+version = "1.4.3"
 description = "Command-line client for the ScrapingBee API: scrape pages (single or batch), crawl sites, check usage/credits, and use Google Search, Fast Search, Amazon, Walmart, YouTube, and ChatGPT from the terminal."
 readme = "README.md"
 license = "MIT"

{scrapingbee_cli-1.4.2 → scrapingbee_cli-1.4.3}/src/scrapingbee_cli/__init__.py

@@ -3,7 +3,7 @@
 import platform
 import sys
 
-__version__ = "1.4.2"
+__version__ = "1.4.3"
 
 
 def user_agent_headers() -> dict[str, str]:
@@ -12,7 +12,7 @@ def user_agent_headers() -> dict[str, str]:
     Returns a dict of headers:
         User-Agent: ScrapingBee/CLI
         User-Agent-Client: scrapingbee-cli
-        User-Agent-Client-Version: 1.4.2
+        User-Agent-Client-Version: 1.4.3
         User-Agent-Environment: python
         User-Agent-Environment-Version: 3.14.2
         User-Agent-OS: Darwin arm64

{scrapingbee_cli-1.4.2 → scrapingbee_cli-1.4.3}/src/scrapingbee_cli/cli.py

@@ -137,6 +137,7 @@ def _handle_scraping_config() -> None:
         "google",
         "fast-search",
         "amazon-product",
+        "amazon-pricing",
         "amazon-search",
         "walmart-search",
         "walmart-product",

{scrapingbee_cli-1.4.2 → scrapingbee_cli-1.4.3}/src/scrapingbee_cli/cli_utils.py

@@ -1231,7 +1231,7 @@ def _validate_page(value: int | None, name: str = "page") -> None:
         raise SystemExit(1)
 
 
-def _validate_price_range(min_price: int | None, max_price: int | None) -> None:
+def _validate_price_range(min_price: float | None, max_price: float | None) -> None:
     """Validate min_price/max_price: non-negative and min <= max."""
     if min_price is not None and min_price < 0:
         click.echo("min_price must be >= 0", err=True)

{scrapingbee_cli-1.4.2 → scrapingbee_cli-1.4.3}/src/scrapingbee_cli/client.py

@@ -294,6 +294,9 @@ class Client:
         light_request: bool | None = None,
         tag: str | None = None,
         date_range: str | None = None,
+        sort_by: str | None = None,
+        min_price: float | None = None,
+        max_price: float | None = None,
         retries: int = 3,
         backoff: float = 2.0,
     ) -> tuple[bytes, dict, int]:
@@ -310,6 +313,9 @@ class Client:
             "light_request": self._bool(light_request),
             "tag": tag,
             "date_range": date_range,
+            "sort_by": sort_by,
+            "min_price": min_price,
+            "max_price": max_price,
         }
         return await self._get_with_retry(
             "/google",
@@ -378,6 +384,40 @@ class Client:
             backoff=backoff,
         )
 
+    async def amazon_pricing(
+        self,
+        asin: str,
+        device: str | None = None,
+        domain: str | None = None,
+        country: str | None = None,
+        zip_code: str | None = None,
+        language: str | None = None,
+        currency: str | None = None,
+        add_html: bool | None = None,
+        light_request: bool | None = None,
+        tag: str | None = None,
+        retries: int = 3,
+        backoff: float = 2.0,
+    ) -> tuple[bytes, dict, int]:
+        params = {
+            "asin": asin,
+            "device": device,
+            "domain": domain,
+            "country": country,
+            "zip_code": zip_code,
+            "language": language,
+            "currency": currency,
+            "add_html": self._bool(add_html),
+            "light_request": self._bool(light_request),
+            "tag": tag,
+        }
+        return await self._get_with_retry(
+            "/amazon/pricing",
+            params,
+            retries=retries,
+            backoff=backoff,
+        )
+
     async def amazon_search(
         self,
         query: str,

{scrapingbee_cli-1.4.2 → scrapingbee_cli-1.4.3}/src/scrapingbee_cli/commands/amazon.py

@@ -198,6 +198,160 @@ def amazon_product_cmd(
     asyncio.run(_single())
 
 
+@click.command("amazon-pricing")
+@click.argument("asin", required=False)
+@optgroup.group("Locale", help="Device, domain, country, language, and currency")
+@optgroup.option(
+    "--device",
+    type=click.Choice(["desktop"], case_sensitive=False),
+    default=None,
+    help="Device: desktop.",
+)
+@optgroup.option(
+    "--domain", type=str, default=None, help="Amazon domain (e.g. com, co.uk, de, fr)."
+)
+@optgroup.option("--country", type=str, default=None, help="Country code (e.g. us, gb, de).")
+@optgroup.option(
+    "--zip-code", type=str, default=None, help="ZIP code for local availability/pricing."
+)
+@optgroup.option(
+    "--language", type=str, default=None, help="Language code (e.g. en_US, es_US, fr_FR)."
+)
+@optgroup.option("--currency", type=str, default=None, help="Currency code (e.g. USD, EUR, GBP).")
+@optgroup.group("Output", help="Response format options")
+@optgroup.option(
+    "--add-html", type=str, default=None, help="Include full HTML in response (true/false)."
+)
+@optgroup.option("--light-request", type=str, default=None, help="Light request mode (true/false).")
+@optgroup.option(
+    "--tag",
+    type=str,
+    default=None,
+    help="Optional label included in API response headers.",
+)
+@_batch_options
+@click.pass_obj
+def amazon_pricing_cmd(
+    obj: dict,
+    asin: str | None,
+    device: str | None,
+    domain: str | None,
+    country: str | None,
+    zip_code: str | None,
+    language: str | None,
+    currency: str | None,
+    add_html: str | None,
+    light_request: str | None,
+    tag: str | None,
+    **kwargs,
+) -> None:
+    """Fetch Amazon pricing details by ASIN."""
+    store_common_options(obj, **kwargs)
+    input_file = obj.get("input_file")
+    try:
+        key = get_api_key(None)
+    except ValueError as e:
+        click.echo(str(e), err=True)
+        raise SystemExit(1)
+
+    if input_file:
+        if asin:
+            click.echo("cannot use both --input-file and positional ASIN", err=True)
+            raise SystemExit(1)
+        try:
+            inputs = read_input_file(input_file, input_column=obj.get("input_column"))
+        except ValueError as e:
+            click.echo(str(e), err=True)
+            raise SystemExit(1)
+        inputs = prepare_batch_inputs(inputs, obj)
+        usage_info = get_batch_usage(None)
+        try:
+            validate_batch_run(obj["concurrency"], len(inputs), usage_info)
+        except ValueError as e:
+            click.echo(str(e), err=True)
+            raise SystemExit(1)
+        concurrency = resolve_batch_concurrency(obj["concurrency"], usage_info, len(inputs))
+
+        skip_n = (
+            _find_completed_n(obj.get("output_dir") or "") if obj.get("resume") else frozenset()
+        )
+
+        async def api_call(client, a):
+            return await client.amazon_pricing(
+                a,
+                device=device,
+                domain=domain,
+                country=country,
+                zip_code=zip_code,
+                language=language,
+                currency=currency,
+                add_html=parse_bool(add_html),
+                light_request=parse_bool(light_request),
+                tag=tag,
+                retries=int(obj.get("retries") or 3),
+                backoff=float(obj.get("backoff") or 2.0),
+            )
+
+        run_api_batch(
+            key=key,
+            inputs=inputs,
+            concurrency=concurrency,
+            from_user=obj["concurrency"] > 0,
+            skip_n=skip_n,
+            output_dir=obj.get("output_dir") or None,
+            verbose=obj["verbose"],
+            show_progress=obj.get("progress", True),
+            api_call=api_call,
+            on_complete=obj.get("on_complete"),
+            output_format=obj.get("output_format"),
+            post_process=obj.get("post_process"),
+            update_csv_path=input_file if obj.get("update_csv") else None,
+            input_column=obj.get("input_column"),
+            output_file=obj.get("output_file") or None,
+            extract_field=obj.get("extract_field"),
+            fields=obj.get("fields"),
+        )
+        return
+
+    if not asin:
+        click.echo("expected one ASIN, or use --input-file for batch", err=True)
+        raise SystemExit(1)
+
+    async def _single() -> None:
+        async with Client(key, BASE_URL) as client:
+            data, headers, status_code = await client.amazon_pricing(
+                asin,
+                device=device,
+                domain=domain,
+                country=country,
+                zip_code=zip_code,
+                language=language,
+                currency=currency,
+                add_html=parse_bool(add_html),
+                light_request=parse_bool(light_request),
+                tag=tag,
+                retries=int(obj.get("retries") or 3),
+                backoff=float(obj.get("backoff") or 2.0),
+            )
+        check_api_response(data, status_code)
+        from ..credits import amazon_credits
+
+        write_output(
+            data,
+            headers,
+            status_code,
+            obj["output_file"],
+            obj["verbose"],
+            smart_extract=obj.get("smart_extract"),
+            extract_field=obj.get("extract_field"),
+            fields=obj.get("fields"),
+            command="amazon-pricing",
+            credit_cost=amazon_credits(parse_bool(light_request)),
+        )
+
+    asyncio.run(_single())
+
+
 @click.command("amazon-search")
 @click.argument("query", required=False)
 @optgroup.group("Pagination & sort", help="Pages and sort order")
@@ -387,4 +541,5 @@ def amazon_search_cmd(
 
 def register(cli: click.Group) -> None:
     cli.add_command(amazon_product_cmd, "amazon-product")
+    cli.add_command(amazon_pricing_cmd, "amazon-pricing")
     cli.add_command(amazon_search_cmd, "amazon-search")

{scrapingbee_cli-1.4.2 → scrapingbee_cli-1.4.3}/src/scrapingbee_cli/commands/google.py

@@ -20,6 +20,7 @@ from ..cli_utils import (
     NormalizedChoice,
     _batch_options,
     _validate_page,
+    _validate_price_range,
     check_api_response,
     norm_val,
     parse_bool,
@@ -92,6 +93,27 @@ def _warn_empty_organic(data: bytes, search_type: str | None) -> None:
     default=None,
     help="Restrict results to the past hour/day/week/month/year.",
 )
+@optgroup.group("Shopping", help="Options for --search-type shopping only")
+@optgroup.option(
+    "--sort-by",
+    type=NormalizedChoice(
+        ["relevance", "reviews", "price-asc", "price-desc"], case_sensitive=False
+    ),
+    default=None,
+    help="Sort Shopping results: relevance, reviews, price-asc, price-desc.",
+)
+@optgroup.option(
+    "--min-price",
+    type=float,
+    default=None,
+    help="Minimum price filter, in the marketplace's native currency.",
+)
+@optgroup.option(
+    "--max-price",
+    type=float,
+    default=None,
+    help="Maximum price filter, in the marketplace's native currency.",
+)
 @optgroup.group("Filters", help="Autocorrection, extra params, and response format")
 @optgroup.option("--nfpr", type=str, default=None, help="Disable autocorrection (true/false).")
 @optgroup.option(
@@ -128,6 +150,9 @@ def google_cmd(
     light_request: str | None,
     tag: str | None,
     date_range: str | None,
+    sort_by: str | None,
+    min_price: float | None,
+    max_price: float | None,
     **kwargs,
 ) -> None:
     """Search Google using the Google Search API."""
@@ -139,6 +164,7 @@ def google_cmd(
         click.echo(str(e), err=True)
         raise SystemExit(1)
     _validate_page(page)
+    _validate_price_range(min_price, max_price)
 
     if input_file:
         if query:
@@ -176,6 +202,9 @@ def google_cmd(
                 light_request=parse_bool(light_request),
                 tag=tag,
                 date_range=norm_val(date_range),
+                sort_by=norm_val(sort_by),
+                min_price=min_price,
+                max_price=max_price,
                 retries=int(obj.get("retries") or 3),
                 backoff=float(obj.get("backoff") or 2.0),
             )
@@ -220,6 +249,9 @@ def google_cmd(
                 light_request=parse_bool(light_request),
                 tag=tag,
                 date_range=norm_val(date_range),
+                sort_by=norm_val(sort_by),
+                min_price=min_price,
+                max_price=max_price,
                 retries=int(obj.get("retries") or 3),
                 backoff=float(obj.get("backoff") or 2.0),
             )

{scrapingbee_cli-1.4.2 → scrapingbee_cli-1.4.3}/src/scrapingbee_cli/credits.py

@@ -12,6 +12,7 @@ ESTIMATED_CREDITS: dict[str, str] = {
     "google": "10-15",
     "fast-search": "10",
     "amazon-product": "5-15",
+    "amazon-pricing": "5-15",
     "amazon-search": "5-15",
     "walmart-search": "10-15",
     "walmart-product": "10-15",

{scrapingbee_cli-1.4.2 → scrapingbee_cli-1.4.3/src/scrapingbee_cli.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scrapingbee-cli
-Version: 1.4.2
+Version: 1.4.3
 Summary: Command-line client for the ScrapingBee API: scrape pages (single or batch), crawl sites, check usage/credits, and use Google Search, Fast Search, Amazon, Walmart, YouTube, and ChatGPT from the terminal.
 Author: ScrapingBee
 License-Expression: MIT
@@ -97,7 +97,7 @@ scrapingbee [command] [arguments] [options]
 | `scrape [url]` | Scrape a URL (HTML, JS, screenshot, extract) |
 | `crawl` | Crawl sites following links, with AI extraction and save-pattern filtering |
 | `google` / `fast-search` | Search SERP APIs |
-| `amazon-product` / `amazon-search` | Amazon product and search |
+| `amazon-product` / `amazon-pricing` / `amazon-search` | Amazon product, pricing and search |
 | `walmart-search` / `walmart-product` | Walmart search and product |
 | `youtube-search` / `youtube-metadata` | YouTube search and video metadata |
 | `chatgpt` | ChatGPT API (`--search true` for web-enhanced responses) |