scrapingbee-cli 1.4.0__tar.gz → 1.4.1__tar.gz

{scrapingbee_cli-1.4.0/src/scrapingbee_cli.egg-info → scrapingbee_cli-1.4.1}/PKG-INFO

@@ -1,12 +1,14 @@
 Metadata-Version: 2.4
 Name: scrapingbee-cli
-Version: 1.4.0
+Version: 1.4.1
 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
 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-1.4.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "scrapingbee-cli"
-version = "1.4.0"
+version = "1.4.1"
 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"
@@ -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-1.4.1}/src/scrapingbee_cli/__init__.py

@@ -3,7 +3,7 @@
 import platform
 import sys
 
-__version__ = "1.4.0"
+__version__ = "1.4.1"
 
 
 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: 1.4.1
         User-Agent-Environment: python
         User-Agent-Environment-Version: 3.14.2
         User-Agent-OS: Darwin arm64

{scrapingbee_cli-1.4.0 → scrapingbee_cli-1.4.1}/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-1.4.1/src/scrapingbee_cli.egg-info}/PKG-INFO

@@ -1,12 +1,14 @@
 Metadata-Version: 2.4
 Name: scrapingbee-cli
-Version: 1.4.0
+Version: 1.4.1
 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
 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