scrapeunblocker-haystack 0.4.1__tar.gz → 0.4.2__tar.gz

{scrapeunblocker_haystack-0.4.1 → scrapeunblocker_haystack-0.4.2}/CHANGELOG.md

@@ -1,5 +1,12 @@
 # Changelog
 
+## 0.4.2
+
+- `ScrapeUnblockerWebSearch` adds `sitelinks` (the extra links under a result:
+  `title`, `url`, `description`), `rating` (`value`, `max`, `reviews`, `url`)
+  and `rich_snippet` (the facts line under the snippet) to each Document's
+  metadata, from the new `/serpApi` fields.
+
 ## 0.4.1
 
 - `ScrapeUnblockerWebSearch` adds `displayed_url`, `domain`, `source` (the

{scrapeunblocker_haystack-0.4.1 → scrapeunblocker_haystack-0.4.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: scrapeunblocker-haystack
-Version: 0.4.1
+Version: 0.4.2
 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
@@ -186,7 +186,8 @@ print(doc.content)                # {"url": ..., "count": ..., "elements": [...]
 
 Searches Google and returns the organic results as `Document` objects, with the
 snippet as content and `title` / `link` / `position` / `displayed_url` / `domain` /
-`source` (the site's name) / `date` in the metadata.
+`source` (the site's name) / `date` / `sitelinks` / `rating` / `rich_snippet` (the
+facts line under the snippet) in the metadata.
 
 ```python
 from scrapeunblocker_haystack import ScrapeUnblockerWebSearch

{scrapeunblocker_haystack-0.4.1 → scrapeunblocker_haystack-0.4.2}/README.md

@@ -161,7 +161,8 @@ print(doc.content)                # {"url": ..., "count": ..., "elements": [...]
 
 Searches Google and returns the organic results as `Document` objects, with the
 snippet as content and `title` / `link` / `position` / `displayed_url` / `domain` /
-`source` (the site's name) / `date` in the metadata.
+`source` (the site's name) / `date` / `sitelinks` / `rating` / `rich_snippet` (the
+facts line under the snippet) in the metadata.
 
 ```python
 from scrapeunblocker_haystack import ScrapeUnblockerWebSearch

{scrapeunblocker_haystack-0.4.1 → scrapeunblocker_haystack-0.4.2}/src/scrapeunblocker_haystack/search.py

@@ -19,7 +19,7 @@ class ScrapeUnblockerWebSearch:
 
     Each result becomes a Document whose content is the snippet (the title when
     Google shows none), with the title, link, position, displayed URL, domain,
-    site name and date in the metadata.
+    site name, date, sitelinks, star rating and facts line in the metadata.
 
     ### Usage example
 
@@ -112,6 +112,9 @@ class ScrapeUnblockerWebSearch:
                     "domain": result.get("domain"),
                     "source": result.get("source"),
                     "date": result.get("date"),
+                    "sitelinks": result.get("sitelinks") or [],
+                    "rating": result.get("rating"),
+                    "rich_snippet": result.get("richSnippet"),
                     "query": query,
                 },
             )

scrapeunblocker_haystack-0.4.2/src/scrapeunblocker_haystack/version.py

@@ -0,0 +1 @@
+__version__ = "0.4.2"

{scrapeunblocker_haystack-0.4.1 → scrapeunblocker_haystack-0.4.2}/tests/test_components.py

@@ -213,7 +213,10 @@ class TestWebSearch:
                 "organic": [
                     {"title": "First", "url": "https://a.com", "description": "snippet a", "position": "1",
                      "displayedUrl": "https://a.com › docs", "domain": "a.com", "source": "A",
-                     "date": "Oct 2, 2026"},
+                     "date": "Oct 2, 2026",
+                     "sitelinks": [{"title": "Docs", "url": "https://a.com/docs", "description": None}],
+                     "rating": {"value": 4.5, "max": 5.0, "reviews": 120, "url": None},
+                     "richSnippet": "4.5 (120) · Free"},
                     {"title": "Second", "url": "https://b.com", "description": "snippet b", "position": "2"},
                 ]
             }
@@ -231,6 +234,11 @@ class TestWebSearch:
         assert result["documents"][0].meta["source"] == "A"
         assert result["documents"][0].meta["date"] == "Oct 2, 2026"
         assert result["documents"][1].meta["date"] is None
+        assert result["documents"][0].meta["sitelinks"][0]["url"] == "https://a.com/docs"
+        assert result["documents"][0].meta["rating"]["value"] == 4.5
+        assert result["documents"][0].meta["rich_snippet"] == "4.5 (120) · Free"
+        assert result["documents"][1].meta["sitelinks"] == []
+        assert result["documents"][1].meta["rating"] is None
 
         _, kwargs = mock_post.call_args
         assert kwargs["params"]["keyword"] == "test query"

scrapeunblocker_haystack-0.4.1/src/scrapeunblocker_haystack/version.py

@@ -1 +0,0 @@
-__version__ = "0.4.1"