scrapeunblocker-haystack 0.2.1__tar.gz → 0.2.2__tar.gz

{scrapeunblocker_haystack-0.2.1 → scrapeunblocker_haystack-0.2.2}/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## 0.2.2
+
+- With `parsed_data=True`, a page that loads but holds no structured data
+  (the API answers HTTP 422 `no_data_extracted`, not billed, no HTML) no longer
+  shows up as a generic request failure. The fetcher skips it with a clear
+  warning, or raises the new `NoDataExtractedError` when
+  `raise_on_failure=True`. Fetch without `parsed_data` to get the HTML.
+
 ## 0.2.1
 
 - A URL whose page does not exist (the site answers HTTP 404 or 410) no longer

{scrapeunblocker_haystack-0.2.1 → scrapeunblocker_haystack-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: scrapeunblocker-haystack
-Version: 0.2.1
+Version: 0.2.2
 Summary: Haystack integration for ScrapeUnblocker - scrape pages behind anti-bot protections
 Project-URL: Homepage, https://www.scrapeunblocker.com
 Project-URL: Documentation, https://docs.scrapeunblocker.com
@@ -120,6 +120,13 @@ Steps are **non-idempotent**. If a step fails, the fetch raises
 which is logged and skipped by default, or re-raised when
 `raise_on_failure=True`.
 
+#### Pages with nothing to parse
+
+With `parsed_data=True`, a page that loads but holds no structured data yields
+no Document: it is skipped with a warning, or `NoDataExtractedError` is raised
+when `raise_on_failure=True`. The call is not billed; fetch the URL without
+`parsed_data` to get the HTML.
+
 #### Pages that do not exist
 
 If the site answers HTTP 404 or 410, there is no page to index: the URL is

{scrapeunblocker_haystack-0.2.1 → scrapeunblocker_haystack-0.2.2}/README.md

@@ -95,6 +95,13 @@ Steps are **non-idempotent**. If a step fails, the fetch raises
 which is logged and skipped by default, or re-raised when
 `raise_on_failure=True`.
 
+#### Pages with nothing to parse
+
+With `parsed_data=True`, a page that loads but holds no structured data yields
+no Document: it is skipped with a warning, or `NoDataExtractedError` is raised
+when `raise_on_failure=True`. The call is not billed; fetch the URL without
+`parsed_data` to get the HTML.
+
 #### Pages that do not exist
 
 If the site answers HTTP 404 or 410, there is no page to index: the URL is

{scrapeunblocker_haystack-0.2.1 → scrapeunblocker_haystack-0.2.2}/src/scrapeunblocker_haystack/__init__.py

@@ -1,4 +1,5 @@
 from scrapeunblocker_haystack.fetcher import (
+    NoDataExtractedError,
     ScrapeUnblockerFetcher,
     StepExecutionError,
     TargetNotFoundError,
@@ -6,6 +7,7 @@ from scrapeunblocker_haystack.fetcher import (
 from scrapeunblocker_haystack.search import ScrapeUnblockerWebSearch
 
 __all__ = [
+    "NoDataExtractedError",
     "ScrapeUnblockerFetcher",
     "ScrapeUnblockerWebSearch",
     "StepExecutionError",

{scrapeunblocker_haystack-0.2.1 → scrapeunblocker_haystack-0.2.2}/src/scrapeunblocker_haystack/fetcher.py

@@ -35,6 +35,23 @@ class TargetNotFoundError(Exception):
         )
 
 
+class NoDataExtractedError(Exception):
+    """Raised when ``parsed_data`` found no structured data on the page.
+
+    The API answers this as HTTP 422 ``no_data_extracted``: the page loaded but
+    held nothing to extract. It is not billed and carries no HTML; fetch the
+    URL without ``parsed_data`` to get the page itself.
+    """
+
+    def __init__(self, url: str) -> None:
+        self.url = url
+        super().__init__(
+            f"No structured data could be extracted from {url}: the page loaded, but "
+            "nothing on it matched a structured shape. The call was not billed; fetch "
+            "it without parsed_data to get the HTML."
+        )
+
+
 def _target_gone_status(response: requests.Response) -> Optional[int]:
     """The target's own 404/410 answer, or None.
 
@@ -138,7 +155,8 @@ class ScrapeUnblockerFetcher:
         :param base_url: API base URL. Override to target a different environment.
         :param timeout: HTTP timeout in seconds.
         :param raise_on_failure: Raise instead of skipping when a URL cannot be fetched
-            (including when a browser step fails or the page does not exist).
+            (including when a browser step fails, the page does not exist, or
+            `parsed_data` finds nothing to extract).
         """
         self.api_key = api_key
         self.parsed_data = parsed_data
@@ -195,8 +213,11 @@ class ScrapeUnblockerFetcher:
         if gone is not None:
             raise TargetNotFoundError(url, gone, response.text)
 
-        # A failed browser step returns 422 with a structured JSON error.
+        # A failed browser step returns 422 with a structured JSON error; so does
+        # a parsed_data call that found nothing to extract.
         if response.status_code == 422:
+            if self._is_no_data_extracted(response):
+                raise NoDataExtractedError(url)
             error = self._parse_step_error(response)
             if error is not None:
                 raise error
@@ -204,6 +225,14 @@ class ScrapeUnblockerFetcher:
         response.raise_for_status()
         return response
 
+    @staticmethod
+    def _is_no_data_extracted(response: requests.Response) -> bool:
+        try:
+            payload = response.json()
+        except ValueError:
+            return False
+        return isinstance(payload, dict) and payload.get("error") == "no_data_extracted"
+
     @staticmethod
     def _parse_step_error(response: requests.Response) -> Optional[StepExecutionError]:
         try:
@@ -225,7 +254,9 @@ class ScrapeUnblockerFetcher:
         Fetch each URL and return one Document per successfully fetched page.
 
         A URL whose page does not exist (the site answers 404/410) yields no
-        Document; with `raise_on_failure` it raises `TargetNotFoundError`.
+        Document; with `raise_on_failure` it raises `TargetNotFoundError`. With
+        `parsed_data`, a page holding no structured data yields no Document
+        either, or raises `NoDataExtractedError`.
 
         :param urls: URLs to fetch.
         :returns: A dictionary with a `documents` key holding the fetched pages.
@@ -237,10 +268,10 @@ class ScrapeUnblockerFetcher:
         for url in urls:
             try:
                 response = self._fetch(url)
-            except TargetNotFoundError as exc:
+            except (TargetNotFoundError, NoDataExtractedError) as exc:
                 if self.raise_on_failure:
                     raise
-                # A page that does not exist has no content to index.
+                # A page that does not exist, or has nothing to parse, has no content to index.
                 logger.warning("ScrapeUnblocker skipped {url}: {error}", url=url, error=str(exc))
                 continue
             except Exception as exc:

scrapeunblocker_haystack-0.2.2/src/scrapeunblocker_haystack/version.py

@@ -0,0 +1 @@
+__version__ = "0.2.2"

{scrapeunblocker_haystack-0.2.1 → scrapeunblocker_haystack-0.2.2}/tests/test_components.py

@@ -10,6 +10,7 @@ from haystack.utils import Secret
 from scrapeunblocker_haystack import (
     ScrapeUnblockerFetcher,
     ScrapeUnblockerWebSearch,
+    NoDataExtractedError,
     StepExecutionError,
     TargetNotFoundError,
 )
@@ -297,3 +298,44 @@ class TestTargetNotFound:
         fetcher = ScrapeUnblockerFetcher(api_key=API_KEY)
 
         assert len(fetcher.run(urls=["https://example.com"])["documents"]) == 1
+
+
+class TestNoDataExtracted:
+    BODY = {
+        "error": "no_data_extracted",
+        "detail": "The page was rendered, but no structured data could be extracted from it.",
+    }
+
+    @patch("scrapeunblocker_haystack.fetcher.requests.post")
+    def test_empty_parse_is_skipped(self, mock_post):
+        mock_post.side_effect = [
+            _response(status_code=422, json_data=self.BODY),
+            _response(json_data={"data": {"page_type": "product"}}),
+        ]
+        fetcher = ScrapeUnblockerFetcher(api_key=API_KEY, parsed_data=True)
+
+        result = fetcher.run(urls=["https://example.com/empty", "https://example.com"])
+
+        assert [d.meta["url"] for d in result["documents"]] == ["https://example.com"]
+
+    @patch("scrapeunblocker_haystack.fetcher.requests.post")
+    def test_empty_parse_raises_when_asked(self, mock_post):
+        mock_post.return_value = _response(status_code=422, json_data=self.BODY)
+        fetcher = ScrapeUnblockerFetcher(api_key=API_KEY, parsed_data=True, raise_on_failure=True)
+
+        with pytest.raises(NoDataExtractedError) as exc:
+            fetcher.run(urls=["https://example.com/empty"])
+        assert exc.value.url == "https://example.com/empty"
+        assert "not billed" in str(exc.value)
+
+    @patch("scrapeunblocker_haystack.fetcher.requests.post")
+    def test_dead_url_with_parsed_body_is_skipped(self, mock_post):
+        response = _response(
+            status_code=404, json_data={"data": {"page_type": "not_found", "data": {}}}
+        )
+        response.text = '{"data":{"page_type":"not_found","data":{}}}'
+        response.headers = {"Content-Type": "application/json", "X-Origin-Status": "404"}
+        mock_post.return_value = response
+        fetcher = ScrapeUnblockerFetcher(api_key=API_KEY, parsed_data=True)
+
+        assert fetcher.run(urls=["https://example.com/gone"])["documents"] == []

scrapeunblocker_haystack-0.2.1/src/scrapeunblocker_haystack/version.py

@@ -1 +0,0 @@
-__version__ = "0.2.1"