Set scrape baseline to block images by default

Author: gildesmarais

README.md

@@ -105,7 +105,7 @@ Request body (full options):
   "max_retries": 2,
   "wait_for_selector": "h1",
   "wait_timeout_seconds": 15,
-  "block_images": false,
+  "block_images": true,
   "block_images_and_css": false,
   "wait_for_complete_page_load": true,
   "user_agent": "Mozilla/5.0 ...",
@@ -126,7 +126,7 @@ Request options (contract):
 - `max_retries`: `0..3`, default `2` (attempts = `1 + max_retries`, with `auto` capped by 3 strategy steps).
 - `wait_for_selector`: if set, response waits for selector before capture.
 - `wait_timeout_seconds`: selector wait timeout (capped by service timeout).
-- `block_images`: pass image blocking to driver.
+- `block_images`: pass image blocking to driver. Default `true`.
 
 Currently accepted passthrough options (implemented, not part of stable request-options contract):
 

app/main.py

@@ -64,7 +64,7 @@ class ScrapeRequest(BaseModel):
         ge=1,
         le=DEFAULT_SCRAPE_TIMEOUT_SECONDS,
     )
-    block_images: bool = False
+    block_images: bool = True
     block_images_and_css: bool = False
     wait_for_complete_page_load: bool = True
     user_agent: Optional[str] = None

tests/test_api_contract.py

@@ -59,7 +59,7 @@ def test_request_defaults(self):
         payload = main.ScrapeRequest(url="https://example.com")
         self.assertEqual(payload.navigation_mode, "auto")
         self.assertEqual(payload.max_retries, 2)
-        self.assertFalse(payload.block_images)
+        self.assertTrue(payload.block_images)
         self.assertFalse(payload.block_images_and_css)
         self.assertTrue(payload.wait_for_complete_page_load)
         self.assertIsNone(payload.user_agent)