scrapingbee-cli 1.4.0__tar.gz → 1.4.2__tar.gz

{scrapingbee_cli-1.4.0/src/scrapingbee_cli.egg-info → scrapingbee_cli-1.4.2}/PKG-INFO

@@ -1,12 +1,14 @@
 Metadata-Version: 2.4
 Name: scrapingbee-cli
-Version: 1.4.0
+Version: 1.4.2
 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
 Project-URL: Homepage, https://www.scrapingbee.com/
 Project-URL: Documentation, https://www.scrapingbee.com/documentation/
 Project-URL: Repository, https://github.com/ScrapingBee/scrapingbee-cli
+Project-URL: Changelog, https://github.com/ScrapingBee/scrapingbee-cli/blob/main/CHANGELOG.md
+Project-URL: Issues, https://github.com/ScrapingBee/scrapingbee-cli/issues
 Keywords: scrapingbee,scraping,crawl,scrapy,batch,google-search,amazon,walmart,youtube,chatgpt,cli,api
 Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: Console

{scrapingbee_cli-1.4.0 → scrapingbee_cli-1.4.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "scrapingbee-cli"
-version = "1.4.0"
+version = "1.4.2"
 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"
@@ -48,6 +48,8 @@ dependencies = [
 Homepage = "https://www.scrapingbee.com/"
 Documentation = "https://www.scrapingbee.com/documentation/"
 Repository = "https://github.com/ScrapingBee/scrapingbee-cli"
+Changelog = "https://github.com/ScrapingBee/scrapingbee-cli/blob/main/CHANGELOG.md"
+Issues = "https://github.com/ScrapingBee/scrapingbee-cli/issues"
 
 [project.optional-dependencies]
 dev = [

{scrapingbee_cli-1.4.0 → scrapingbee_cli-1.4.2}/src/scrapingbee_cli/__init__.py

@@ -3,7 +3,7 @@
 import platform
 import sys
 
-__version__ = "1.4.0"
+__version__ = "1.4.2"
 
 
 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: 1.4.0
+        User-Agent-Client-Version: 1.4.2
         User-Agent-Environment: python
         User-Agent-Environment-Version: 3.14.2
         User-Agent-OS: Darwin arm64

{scrapingbee_cli-1.4.0 → scrapingbee_cli-1.4.2}/src/scrapingbee_cli/cli_utils.py

@@ -1304,6 +1304,7 @@ def build_scrape_kwargs(
     device: str | None = None,
     custom_google: str | None = None,
     transparent_status_code: str | None = None,
+    tag: str | None = None,
     body: str | None = None,
     scraping_config: str | None = None,
 ) -> dict[str, Any]:
@@ -1344,6 +1345,7 @@ def build_scrape_kwargs(
         "device": device,
         "custom_google": parse_bool(custom_google),
         "transparent_status_code": parse_bool(transparent_status_code),
+        "tag": tag,
         "body": body,
         "scraping_config": scraping_config,
     }
@@ -1564,6 +1566,7 @@ def write_output(
             ("spb-cost", "Credit Cost"),
             ("spb-resolved-url", "Resolved URL"),
             ("spb-initial-status-code", "Initial Status Code"),
+            ("tag", "Tag"),
         ]:
             if key in headers_lower:
                 _, val = headers_lower[key]

{scrapingbee_cli-1.4.0 → scrapingbee_cli-1.4.2}/src/scrapingbee_cli/client.py

@@ -176,6 +176,7 @@ class Client:
         device: str | None = None,
         custom_google: bool | None = None,
         transparent_status_code: bool | None = None,
+        tag: str | None = None,
         body: str | None = None,
         scraping_config: str | None = None,
         retries: int = 3,
@@ -218,6 +219,7 @@ class Client:
             ("device", device),
             ("custom_google", self._bool(custom_google)),
             ("transparent_status_code", self._bool(transparent_status_code)),
+            ("tag", tag),
             ("scraping_config", scraping_config),
         ]:
             if v is not None:
@@ -290,6 +292,8 @@ class Client:
         extra_params: str | None = None,
         add_html: bool | None = None,
         light_request: bool | None = None,
+        tag: str | None = None,
+        date_range: str | None = None,
         retries: int = 3,
         backoff: float = 2.0,
     ) -> tuple[bytes, dict, int]:
@@ -304,6 +308,8 @@ class Client:
             "extra_params": extra_params,
             "add_html": self._bool(add_html),
             "light_request": self._bool(light_request),
+            "tag": tag,
+            "date_range": date_range,
         }
         return await self._get_with_retry(
             "/google",
@@ -318,6 +324,7 @@ class Client:
         page: int | None = None,
         country_code: str | None = None,
         language: str | None = None,
+        tag: str | None = None,
         retries: int = 3,
         backoff: float = 2.0,
     ) -> tuple[bytes, dict, int]:
@@ -326,6 +333,7 @@ class Client:
             "page": page if page is not None else None,
             "country_code": country_code,
             "language": language,
+            "tag": tag,
         }
         return await self._get_with_retry(
             "/fast_search",
@@ -346,6 +354,7 @@ class Client:
         add_html: bool | None = None,
         light_request: bool | None = None,
         screenshot: bool | None = None,
+        tag: str | None = None,
         retries: int = 3,
         backoff: float = 2.0,
     ) -> tuple[bytes, dict, int]:
@@ -360,6 +369,7 @@ class Client:
             "add_html": self._bool(add_html),
             "light_request": self._bool(light_request),
             "screenshot": self._bool(screenshot),
+            "tag": tag,
         }
         return await self._get_with_retry(
             "/amazon/product",
@@ -386,6 +396,7 @@ class Client:
         add_html: bool | None = None,
         light_request: bool | None = None,
         screenshot: bool | None = None,
+        tag: str | None = None,
         retries: int = 3,
         backoff: float = 2.0,
     ) -> tuple[bytes, dict, int]:
@@ -406,6 +417,7 @@ class Client:
             "add_html": self._bool(add_html),
             "light_request": self._bool(light_request),
             "screenshot": self._bool(screenshot),
+            "tag": tag,
         }
         return await self._get_with_retry(
             "/amazon/search",
@@ -430,6 +442,7 @@ class Client:
         add_html: bool | None = None,
         light_request: bool | None = None,
         screenshot: bool | None = None,
+        tag: str | None = None,
         retries: int = 3,
         backoff: float = 2.0,
     ) -> tuple[bytes, dict, int]:
@@ -448,6 +461,7 @@ class Client:
             "add_html": self._bool(add_html),
             "light_request": self._bool(light_request),
             "screenshot": self._bool(screenshot),
+            "tag": tag,
         }
         return await self._get_with_retry(
             "/walmart/search",
@@ -466,6 +480,7 @@ class Client:
         add_html: bool | None = None,
         light_request: bool | None = None,
         screenshot: bool | None = None,
+        tag: str | None = None,
         retries: int = 3,
         backoff: float = 2.0,
     ) -> tuple[bytes, dict, int]:
@@ -478,6 +493,7 @@ class Client:
             "add_html": self._bool(add_html),
             "light_request": self._bool(light_request),
             "screenshot": self._bool(screenshot),
+            "tag": tag,
         }
         return await self._get_with_retry(
             "/walmart/product",
@@ -504,6 +520,7 @@ class Client:
         location: bool | None = None,
         vr180: bool | None = None,
         purchased: bool | None = None,
+        tag: str | None = None,
         retries: int = 3,
         backoff: float = 2.0,
     ) -> tuple[bytes, dict, int]:
@@ -524,6 +541,7 @@ class Client:
             "location": self._bool(location),
             "vr180": self._bool(vr180),
             "purchased": self._bool(purchased),
+            "tag": tag,
         }
         return await self._get_with_retry(
             "/youtube/search",
@@ -535,12 +553,13 @@ class Client:
     async def youtube_metadata(
         self,
         video_id: str,
+        tag: str | None = None,
         retries: int = 3,
         backoff: float = 2.0,
     ) -> tuple[bytes, dict, int]:
         return await self._get_with_retry(
             "/youtube/metadata",
-            {"video_id": video_id},
+            {"video_id": video_id, "tag": tag},
             retries=retries,
             backoff=backoff,
         )
@@ -551,6 +570,7 @@ class Client:
         search: bool | None = None,
         add_html: bool | None = None,
         country_code: str | None = None,
+        tag: str | None = None,
         retries: int = 3,
         backoff: float = 2.0,
     ) -> tuple[bytes, dict, int]:
@@ -561,6 +581,8 @@ class Client:
             params["add_html"] = str(add_html).lower()
         if country_code is not None:
             params["country_code"] = country_code
+        if tag is not None:
+            params["tag"] = tag
         return await self._get_with_retry(
             "/chatgpt",
             params,

{scrapingbee_cli-1.4.0 → scrapingbee_cli-1.4.2}/src/scrapingbee_cli/commands/amazon.py

@@ -66,6 +66,12 @@ AMAZON_SORT_BY = [
 )
 @optgroup.option("--light-request", type=str, default=None, help="Light request mode (true/false).")
 @optgroup.option("--screenshot", type=str, default=None, help="Take screenshot (true/false).")
+@optgroup.option(
+    "--tag",
+    type=str,
+    default=None,
+    help="Optional label included in API response headers.",
+)
 @_batch_options
 @click.pass_obj
 def amazon_product_cmd(
@@ -80,6 +86,7 @@ def amazon_product_cmd(
     add_html: str | None,
     light_request: str | None,
     screenshot: str | None,
+    tag: str | None,
     **kwargs,
 ) -> None:
     """Fetch Amazon product details by ASIN."""
@@ -125,6 +132,7 @@ def amazon_product_cmd(
                 add_html=parse_bool(add_html),
                 light_request=parse_bool(light_request),
                 screenshot=parse_bool(screenshot),
+                tag=tag,
                 retries=int(obj.get("retries") or 3),
                 backoff=float(obj.get("backoff") or 2.0),
             )
@@ -167,6 +175,7 @@ def amazon_product_cmd(
                 add_html=parse_bool(add_html),
                 light_request=parse_bool(light_request),
                 screenshot=parse_bool(screenshot),
+                tag=tag,
                 retries=int(obj.get("retries") or 3),
                 backoff=float(obj.get("backoff") or 2.0),
             )
@@ -224,6 +233,12 @@ def amazon_product_cmd(
 @optgroup.option("--add-html", type=str, default=None, help="Include full HTML (true/false).")
 @optgroup.option("--light-request", type=str, default=None, help="Light request (true/false).")
 @optgroup.option("--screenshot", type=str, default=None, help="Take screenshot (true/false).")
+@optgroup.option(
+    "--tag",
+    type=str,
+    default=None,
+    help="Optional label included in API response headers.",
+)
 @_batch_options
 @click.pass_obj
 def amazon_search_cmd(
@@ -244,6 +259,7 @@ def amazon_search_cmd(
     add_html: str | None,
     light_request: str | None,
     screenshot: str | None,
+    tag: str | None,
     **kwargs,
 ) -> None:
     """Search Amazon products."""
@@ -297,6 +313,7 @@ def amazon_search_cmd(
                 add_html=parse_bool(add_html),
                 light_request=parse_bool(light_request),
                 screenshot=parse_bool(screenshot),
+                tag=tag,
                 retries=int(obj.get("retries") or 3),
                 backoff=float(obj.get("backoff") or 2.0),
             )
@@ -345,6 +362,7 @@ def amazon_search_cmd(
                 add_html=parse_bool(add_html),
                 light_request=parse_bool(light_request),
                 screenshot=parse_bool(screenshot),
+                tag=tag,
                 retries=int(obj.get("retries") or 3),
                 backoff=float(obj.get("backoff") or 2.0),
             )

{scrapingbee_cli-1.4.0 → scrapingbee_cli-1.4.2}/src/scrapingbee_cli/commands/chatgpt.py

@@ -46,6 +46,12 @@ from ..config import BASE_URL, get_api_key
     default=None,
     help="Country code for geolocation (ISO 3166-1).",
 )
+@click.option(
+    "--tag",
+    type=str,
+    default=None,
+    help="Optional label included in API response headers.",
+)
 @_batch_options  # must be after command-specific options
 @click.pass_obj
 def chatgpt_cmd(
@@ -54,6 +60,7 @@ def chatgpt_cmd(
     search: str | None,
     add_html: str | None,
     country_code: str | None,
+    tag: str | None,
     **kwargs,
 ) -> None:
     """Send a prompt to the ChatGPT API."""
@@ -93,6 +100,7 @@ def chatgpt_cmd(
                 search=parse_bool(search),
                 add_html=parse_bool(add_html),
                 country_code=country_code,
+                tag=tag,
                 retries=int(obj.get("retries") or 3),
                 backoff=float(obj.get("backoff") or 2.0),
             )
@@ -131,6 +139,7 @@ def chatgpt_cmd(
                 search=parse_bool(search),
                 add_html=parse_bool(add_html),
                 country_code=country_code,
+                tag=tag,
                 retries=int(obj.get("retries") or 3),
                 backoff=float(obj.get("backoff") or 2.0),
             )

{scrapingbee_cli-1.4.0 → scrapingbee_cli-1.4.2}/src/scrapingbee_cli/commands/crawl.py

@@ -60,6 +60,7 @@ def _crawl_build_params(
     device: str | None,
     custom_google: str | None,
     transparent_status_code: str | None,
+    tag: str | None = None,
     scraping_config: str | None = None,
 ) -> dict[str, str]:
     """Build ScrapingBee API params dict from crawl options (quick-crawl URL mode)."""
@@ -98,6 +99,7 @@ def _crawl_build_params(
         device=device,
         custom_google=custom_google,
         transparent_status_code=transparent_status_code,
+        tag=tag,
         body=None,
         scraping_config=scraping_config,
     )
@@ -248,6 +250,12 @@ def _crawl_build_params(
     default=None,
     help="Return target status as-is (true/false).",
 )
+@optgroup.option(
+    "--tag",
+    type=str,
+    default=None,
+    help="Optional label included in API response headers.",
+)
 @optgroup.group("Crawl", help="Quick-crawl: depth, pages, output, throttling")
 @optgroup.option(
     "--max-depth",
@@ -372,6 +380,7 @@ def crawl_cmd(
     device: str | None,
     custom_google: str | None,
     transparent_status_code: str | None,
+    tag: str | None,
     max_depth: int,
     max_pages: int,
     allowed_domains: str | None,
@@ -500,6 +509,7 @@ def crawl_cmd(
                 device=device,
                 custom_google=custom_google,
                 transparent_status_code=transparent_status_code,
+                tag=tag,
                 scraping_config=scraping_config,
             )
         except ValueError as e:
@@ -602,6 +612,7 @@ def crawl_cmd(
             "--device": device,
             "--custom-google": custom_google,
             "--transparent-status-code": transparent_status_code,
+            "--tag": tag,
         }
         used = [flag for flag, val in api_flags.items() if val is not None]
         if headers:

{scrapingbee_cli-1.4.0 → scrapingbee_cli-1.4.2}/src/scrapingbee_cli/commands/fast_search.py

@@ -38,6 +38,12 @@ from ..config import BASE_URL, get_api_key
     help="Country code for results (ISO 3166-1, e.g. us, fr).",
 )
 @optgroup.option("--language", type=str, default=None, help="Language code (e.g. en, fr).")
+@optgroup.option(
+    "--tag",
+    type=str,
+    default=None,
+    help="Optional label included in API response headers.",
+)
 @_batch_options
 @click.pass_obj
 def fast_search_cmd(
@@ -46,6 +52,7 @@ def fast_search_cmd(
     page: int | None,
     country_code: str | None,
     language: str | None,
+    tag: str | None,
     **kwargs,
 ) -> None:
     """Search using the Fast Search API (sub-second results)."""
@@ -86,6 +93,7 @@ def fast_search_cmd(
                 page=page,
                 country_code=country_code,
                 language=language,
+                tag=tag,
                 retries=int(obj.get("retries") or 3),
                 backoff=float(obj.get("backoff") or 2.0),
             )
@@ -122,6 +130,7 @@ def fast_search_cmd(
                 page=page,
                 country_code=country_code,
                 language=language,
+                tag=tag,
                 retries=int(obj.get("retries") or 3),
                 backoff=float(obj.get("backoff") or 2.0),
             )

{scrapingbee_cli-1.4.0 → scrapingbee_cli-1.4.2}/src/scrapingbee_cli/commands/google.py

@@ -83,6 +83,15 @@ def _warn_empty_organic(data: bytes, search_type: str | None) -> None:
     default=None,
     help="Language code for results (e.g. en, fr, de). Default: en.",
 )
+@optgroup.option(
+    "--date-range",
+    type=NormalizedChoice(
+        ["past-hour", "past-day", "past-week", "past-month", "past-year"],
+        case_sensitive=False,
+    ),
+    default=None,
+    help="Restrict results to the past hour/day/week/month/year.",
+)
 @optgroup.group("Filters", help="Autocorrection, extra params, and response format")
 @optgroup.option("--nfpr", type=str, default=None, help="Disable autocorrection (true/false).")
 @optgroup.option(
@@ -97,6 +106,12 @@ def _warn_empty_organic(data: bytes, search_type: str | None) -> None:
     default=None,
     help="Light request mode, 10 credits (true/false). Fewer data than regular.",
 )
+@optgroup.option(
+    "--tag",
+    type=str,
+    default=None,
+    help="Optional label included in API response headers.",
+)
 @_batch_options
 @click.pass_obj
 def google_cmd(
@@ -111,6 +126,8 @@ def google_cmd(
     extra_params: str | None,
     add_html: str | None,
     light_request: str | None,
+    tag: str | None,
+    date_range: str | None,
     **kwargs,
 ) -> None:
     """Search Google using the Google Search API."""
@@ -157,6 +174,8 @@ def google_cmd(
                 extra_params=extra_params,
                 add_html=parse_bool(add_html),
                 light_request=parse_bool(light_request),
+                tag=tag,
+                date_range=norm_val(date_range),
                 retries=int(obj.get("retries") or 3),
                 backoff=float(obj.get("backoff") or 2.0),
             )
@@ -199,6 +218,8 @@ def google_cmd(
                 extra_params=extra_params,
                 add_html=parse_bool(add_html),
                 light_request=parse_bool(light_request),
+                tag=tag,
+                date_range=norm_val(date_range),
                 retries=int(obj.get("retries") or 3),
                 backoff=float(obj.get("backoff") or 2.0),
             )

{scrapingbee_cli-1.4.0 → scrapingbee_cli-1.4.2}/src/scrapingbee_cli/commands/scrape.py

@@ -293,6 +293,12 @@ SCRAPE_PRESETS = (
     default=None,
     help="Return target status/body as-is (true/false). No retry on 500.",
 )
+@optgroup.option(
+    "--tag",
+    type=str,
+    default=None,
+    help="Optional label included in API response headers.",
+)
 @optgroup.option(
     "-X",
     "--method",
@@ -351,6 +357,7 @@ def scrape_cmd(
     device: str | None,
     custom_google: str | None,
     transparent_status_code: str | None,
+    tag: str | None,
     method: str,
     body: str | None,
     escalate_proxy: bool,
@@ -476,6 +483,7 @@ def scrape_cmd(
             device=device,
             custom_google=custom_google,
             transparent_status_code=transparent_status_code,
+            tag=tag,
             body=body,
             scraping_config=scraping_config,
         )

{scrapingbee_cli-1.4.0 → scrapingbee_cli-1.4.2}/src/scrapingbee_cli/commands/walmart.py

@@ -72,6 +72,12 @@ WALMART_SORT_BY = ["best-match", "price-low", "price-high", "best-seller"]
 @optgroup.option("--add-html", type=str, default=None, help="Include full HTML (true/false).")
 @optgroup.option("--light-request", type=str, default=None, help="Light request (true/false).")
 @optgroup.option("--screenshot", type=str, default=None, help="Take screenshot (true/false).")
+@optgroup.option(
+    "--tag",
+    type=str,
+    default=None,
+    help="Optional label included in API response headers.",
+)
 @_batch_options
 @click.pass_obj
 def walmart_search_cmd(
@@ -90,6 +96,7 @@ def walmart_search_cmd(
     add_html: str | None,
     light_request: str | None,
     screenshot: str | None,
+    tag: str | None,
     **kwargs,
 ) -> None:
     """Search Walmart products."""
@@ -141,6 +148,7 @@ def walmart_search_cmd(
                 add_html=parse_bool(add_html),
                 light_request=parse_bool(light_request),
                 screenshot=parse_bool(screenshot),
+                tag=tag,
                 retries=int(obj.get("retries") or 3),
                 backoff=float(obj.get("backoff") or 2.0),
             )
@@ -187,6 +195,7 @@ def walmart_search_cmd(
                 add_html=parse_bool(add_html),
                 light_request=parse_bool(light_request),
                 screenshot=parse_bool(screenshot),
+                tag=tag,
                 retries=int(obj.get("retries") or 3),
                 backoff=float(obj.get("backoff") or 2.0),
             )
@@ -225,6 +234,12 @@ def walmart_search_cmd(
 @optgroup.option("--add-html", type=str, default=None, help="Include full HTML (true/false).")
 @optgroup.option("--light-request", type=str, default=None, help="Light request (true/false).")
 @optgroup.option("--screenshot", type=str, default=None, help="Take screenshot (true/false).")
+@optgroup.option(
+    "--tag",
+    type=str,
+    default=None,
+    help="Optional label included in API response headers.",
+)
 @_batch_options
 @click.pass_obj
 def walmart_product_cmd(
@@ -237,6 +252,7 @@ def walmart_product_cmd(
     add_html: str | None,
     light_request: str | None,
     screenshot: str | None,
+    tag: str | None,
     **kwargs,
 ) -> None:
     """Fetch Walmart product details by product ID."""
@@ -280,6 +296,7 @@ def walmart_product_cmd(
                 add_html=parse_bool(add_html),
                 light_request=parse_bool(light_request),
                 screenshot=parse_bool(screenshot),
+                tag=tag,
                 retries=int(obj.get("retries") or 3),
                 backoff=float(obj.get("backoff") or 2.0),
             )
@@ -320,6 +337,7 @@ def walmart_product_cmd(
                 add_html=parse_bool(add_html),
                 light_request=parse_bool(light_request),
                 screenshot=parse_bool(screenshot),
+                tag=tag,
                 retries=int(obj.get("retries") or 3),
                 backoff=float(obj.get("backoff") or 2.0),
             )

{scrapingbee_cli-1.4.0 → scrapingbee_cli-1.4.2}/src/scrapingbee_cli/commands/youtube.py

@@ -155,6 +155,12 @@ YOUTUBE_SORT_BY = ["relevance", "rating", "view-count", "upload-date"]
 @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).")
+@optgroup.option(
+    "--tag",
+    type=str,
+    default=None,
+    help="Optional label included in API response headers.",
+)
 @_batch_options
 @click.pass_obj
 def youtube_search_cmd(
@@ -175,6 +181,7 @@ def youtube_search_cmd(
     location: str | None,
     vr180: str | None,
     purchased: str | None,
+    tag: str | None,
     **kwargs,
 ) -> None:
     """Search YouTube videos."""
@@ -227,6 +234,7 @@ def youtube_search_cmd(
                 location=parse_bool(location),
                 vr180=parse_bool(vr180),
                 purchased=parse_bool(purchased),
+                tag=tag,
                 retries=int(obj.get("retries") or 3),
                 backoff=float(obj.get("backoff") or 2.0),
             )
@@ -276,6 +284,7 @@ def youtube_search_cmd(
                 location=parse_bool(location),
                 vr180=parse_bool(vr180),
                 purchased=parse_bool(purchased),
+                tag=tag,
                 retries=int(obj.get("retries") or 3),
                 backoff=float(obj.get("backoff") or 2.0),
             )
@@ -299,11 +308,18 @@ def youtube_search_cmd(
 
 @click.command("youtube-metadata")
 @click.argument("video_id", required=False)
+@click.option(
+    "--tag",
+    type=str,
+    default=None,
+    help="Optional label included in API response headers.",
+)
 @_batch_options
 @click.pass_obj
 def youtube_metadata_cmd(
     obj: dict,
     video_id: str | None,
+    tag: str | None,
     **kwargs,
 ) -> None:
     """Fetch YouTube video metadata."""
@@ -340,6 +356,7 @@ def youtube_metadata_cmd(
         async def api_call(client, vid):
             return await client.youtube_metadata(
                 _extract_video_id(vid),
+                tag=tag,
                 retries=int(obj.get("retries") or 3),
                 backoff=float(obj.get("backoff") or 2.0),
             )
@@ -373,6 +390,7 @@ def youtube_metadata_cmd(
         async with Client(key, BASE_URL) as client:
             data, headers, status_code = await client.youtube_metadata(
                 _extract_video_id(video_id),
+                tag=tag,
                 retries=int(obj.get("retries") or 3),
                 backoff=float(obj.get("backoff") or 2.0),
             )

{scrapingbee_cli-1.4.0 → scrapingbee_cli-1.4.2}/src/scrapingbee_cli/crawl.py

@@ -90,7 +90,8 @@ def _params_for_discovery(params: dict[str, Any]) -> dict[str, Any]:
 def _preferred_extension_from_scrape_params(params: dict[str, Any]) -> str | None:
     """Return extension when scrape params force a response type (skip detection).
     Priority: screenshot+json_response -> json; screenshot -> png;
-    return_page_markdown -> md; return_page_text -> txt; json_response -> json.
+    return_page_markdown -> md; return_page_text -> txt;
+    json_response / extract_rules / ai_extract_rules / ai_query -> json.
     """
     if _param_truthy(params, "screenshot") and _param_truthy(params, "json_response"):
         return "json"
@@ -102,6 +103,11 @@ def _preferred_extension_from_scrape_params(params: dict[str, Any]) -> str | Non
         return "txt"
     if _param_truthy(params, "json_response"):
         return "json"
+    # extract_rules, ai_extract_rules, ai_query always return JSON regardless of URL.
+    # Without this, URLs ending in .html would be saved as .html despite JSON body
+    # (the URL-path heuristic in extension_for_crawl wins before body sniff).
+    if params.get("extract_rules") or params.get("ai_extract_rules") or params.get("ai_query"):
+        return "json"
     return None
 
 

{scrapingbee_cli-1.4.0 → scrapingbee_cli-1.4.2/src/scrapingbee_cli.egg-info}/PKG-INFO

@@ -1,12 +1,14 @@
 Metadata-Version: 2.4
 Name: scrapingbee-cli
-Version: 1.4.0
+Version: 1.4.2
 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
 Project-URL: Homepage, https://www.scrapingbee.com/
 Project-URL: Documentation, https://www.scrapingbee.com/documentation/
 Project-URL: Repository, https://github.com/ScrapingBee/scrapingbee-cli
+Project-URL: Changelog, https://github.com/ScrapingBee/scrapingbee-cli/blob/main/CHANGELOG.md
+Project-URL: Issues, https://github.com/ScrapingBee/scrapingbee-cli/issues
 Keywords: scrapingbee,scraping,crawl,scrapy,batch,google-search,amazon,walmart,youtube,chatgpt,cli,api
 Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: Console