feat(scrape): read framework-embedded page data in the json format (#2405)

Stainless-Generated-From: bf74153d65d37d8ee3e41340c709a51be9133e8f

Author: stlc-bot

src/context/dev/types/batch_cancel_response.py

@@ -36,7 +36,10 @@ class Formats(BaseModel):
     """Images found on the page."""
 
     json_: Optional[bool] = FieldInfo(alias="json", default=None)
-    """An object matching `jsonParams.schema`, extracted from the page."""
+    """
+    An object matching `jsonParams.schema`, extracted from the page text and its
+    embedded data (JSON-LD, meta tags, framework state).
+    """
 
     markdown: Optional[bool] = None
     """Page content as Markdown."""

src/context/dev/types/batch_list_response.py

@@ -56,7 +56,10 @@ class DataFormats(BaseModel):
     """Images found on the page."""
 
     json_: Optional[bool] = FieldInfo(alias="json", default=None)
-    """An object matching `jsonParams.schema`, extracted from the page."""
+    """
+    An object matching `jsonParams.schema`, extracted from the page text and its
+    embedded data (JSON-LD, meta tags, framework state).
+    """
 
     markdown: Optional[bool] = None
     """Page content as Markdown."""

src/context/dev/types/batch_retrieve_response.py

@@ -56,7 +56,10 @@ class Formats(BaseModel):
     """Images found on the page."""
 
     json_: Optional[bool] = FieldInfo(alias="json", default=None)
-    """An object matching `jsonParams.schema`, extracted from the page."""
+    """
+    An object matching `jsonParams.schema`, extracted from the page text and its
+    embedded data (JSON-LD, meta tags, framework state).
+    """
 
     markdown: Optional[bool] = None
     """Page content as Markdown."""

src/context/dev/types/batch_submit_params.py

@@ -756,7 +756,10 @@ class InputScrapeDataBatchUnifiedScrapeDataFormats(TypedDict, total=False):
     """Images found on the page."""
 
     json: bool
-    """An object matching `jsonParams.schema`, extracted from the page."""
+    """
+    An object matching `jsonParams.schema`, extracted from the page text and its
+    embedded data (JSON-LD, meta tags, framework state).
+    """
 
     markdown: bool
     """Page content as Markdown."""
@@ -2310,7 +2313,10 @@ class InputCrawlDataBatchUnifiedCrawlDataFormats(TypedDict, total=False):
     """Images found on the page."""
 
     json: bool
-    """An object matching `jsonParams.schema`, extracted from the page."""
+    """
+    An object matching `jsonParams.schema`, extracted from the page text and its
+    embedded data (JSON-LD, meta tags, framework state).
+    """
 
     markdown: bool
     """Page content as Markdown."""

src/context/dev/types/batch_submit_response.py

@@ -48,7 +48,10 @@ class Formats(BaseModel):
     """Images found on the page."""
 
     json_: Optional[bool] = FieldInfo(alias="json", default=None)
-    """An object matching `jsonParams.schema`, extracted from the page."""
+    """
+    An object matching `jsonParams.schema`, extracted from the page text and its
+    embedded data (JSON-LD, meta tags, framework state).
+    """
 
     markdown: Optional[bool] = None
     """Page content as Markdown."""

src/context/dev/types/web_scrape_params.py

@@ -111,7 +111,10 @@ class Formats(TypedDict, total=False):
     """Images found on the page."""
 
     json: bool
-    """An object matching `jsonParams.schema`, extracted from the page."""
+    """
+    An object matching `jsonParams.schema`, extracted from the page text and its
+    embedded data (JSON-LD, meta tags, framework state).
+    """
 
     markdown: bool
     """Page content as Markdown."""