scrapeunblocker-haystack 0.1.0__tar.gz

scrapeunblocker_haystack-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,21 @@
+name: Publish to PyPI
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      # Required for PyPI Trusted Publishing (OIDC) - no API token needed.
+      id-token: write
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - run: pip install build
+      - run: python -m build
+      - uses: pypa/gh-action-pypi-publish@release/v1

scrapeunblocker_haystack-0.1.0/.github/workflows/test.yml

@@ -0,0 +1,22 @@
+name: Test
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.11", "3.13"]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - run: pip install -e . pytest
+      - run: pytest tests/ -v
+        env:
+          SCRAPEUNBLOCKER_API_KEY: dummy-key-for-tests

scrapeunblocker_haystack-0.1.0/.gitignore

@@ -0,0 +1,7 @@
+__pycache__/
+*.pyc
+*.egg-info/
+dist/
+build/
+.pytest_cache/
+.venv/

scrapeunblocker_haystack-0.1.0/CHANGELOG.md

@@ -0,0 +1,8 @@
+# Changelog
+
+## 0.1.0
+
+Initial release.
+
+- `ScrapeUnblockerFetcher` - fetch pages behind anti-bot protections as Documents
+- `ScrapeUnblockerWebSearch` - Google organic results as Documents

scrapeunblocker_haystack-0.1.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

scrapeunblocker_haystack-0.1.0/PKG-INFO

@@ -0,0 +1,157 @@
+Metadata-Version: 2.4
+Name: scrapeunblocker-haystack
+Version: 0.1.0
+Summary: Haystack integration for ScrapeUnblocker - scrape pages behind anti-bot protections
+Project-URL: Homepage, https://www.scrapeunblocker.com
+Project-URL: Documentation, https://developers.scrapeunblocker.com
+Project-URL: Source, https://github.com/ScrapeUnblocker/scrapeunblocker-haystack
+Project-URL: Issues, https://github.com/ScrapeUnblocker/scrapeunblocker-haystack/issues
+Author-email: ScrapeUnblocker <info@scrapeunblocker.com>
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: anti-bot,haystack,llm,rag,scraping,web-scraping
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.9
+Requires-Dist: haystack-ai>=2.0.0
+Requires-Dist: requests>=2.31.0
+Description-Content-Type: text/markdown
+
+# scrapeunblocker-haystack
+
+[Haystack](https://haystack.deepset.ai/) integration for
+[ScrapeUnblocker](https://www.scrapeunblocker.com) - fetch pages that block
+ordinary HTTP requests.
+
+ScrapeUnblocker renders web pages in a real browser behind anti-bot protections
+such as Cloudflare, DataDome, PerimeterX and Akamai, so your pipeline gets the
+real content instead of a block page, a captcha, or an empty JavaScript shell.
+
+## Installation
+
+```bash
+pip install scrapeunblocker-haystack
+```
+
+## Setup
+
+Get an API key at [scrapeunblocker.com](https://www.scrapeunblocker.com) and
+export it:
+
+```bash
+export SCRAPEUNBLOCKER_API_KEY=<your-api-key>
+```
+
+Both components read that variable by default, or accept a `Secret` explicitly.
+
+## Components
+
+### ScrapeUnblockerFetcher
+
+Fetches URLs and returns one `Document` per page.
+
+```python
+from scrapeunblocker_haystack import ScrapeUnblockerFetcher
+
+fetcher = ScrapeUnblockerFetcher()
+result = fetcher.run(urls=["https://example.com"])
+
+print(result["documents"][0].content[:200])
+```
+
+| Parameter | Default | Description |
+| --- | --- | --- |
+| `api_key` | `SCRAPEUNBLOCKER_API_KEY` env var | ScrapeUnblocker API key |
+| `parsed_data` | `False` | Return AI-parsed structured JSON instead of raw HTML |
+| `proxy_country` | `None` | Two-letter country code for the exit IP |
+| `time_sleep` | `None` | Seconds to wait after load before capturing |
+| `base_url` | `https://api.scrapeunblocker.com` | API base URL |
+| `timeout` | `180` | HTTP timeout in seconds |
+| `raise_on_failure` | `False` | Raise instead of skipping a URL that fails |
+
+By default a URL that cannot be fetched is logged and skipped, so one bad URL
+does not discard the rest of the batch.
+
+### ScrapeUnblockerWebSearch
+
+Searches Google and returns the organic results as `Document` objects, with the
+snippet as content and `title` / `link` / `position` in the metadata.
+
+```python
+from scrapeunblocker_haystack import ScrapeUnblockerWebSearch
+
+search = ScrapeUnblockerWebSearch(top_k=5)
+result = search.run(query="best web scraping api")
+
+for doc in result["documents"]:
+    print(doc.meta["title"], doc.meta["link"])
+```
+
+| Parameter | Default | Description |
+| --- | --- | --- |
+| `api_key` | `SCRAPEUNBLOCKER_API_KEY` env var | ScrapeUnblocker API key |
+| `pages_to_check` | `1` | How many result pages to scrape |
+| `proxy_country` | `None` | Two-letter country code for localised results |
+| `top_k` | `None` | Keep at most this many results |
+
+## In a pipeline
+
+Search the web, fetch the pages behind the results, and answer from them:
+
+```python
+from haystack import Pipeline
+from haystack.components.builders import ChatPromptBuilder
+from haystack.components.converters import HTMLToDocument
+from haystack.components.generators.chat import OpenAIChatGenerator
+from haystack.dataclasses import ChatMessage
+
+from scrapeunblocker_haystack import ScrapeUnblockerFetcher
+
+prompt = [
+    ChatMessage.from_user(
+        "Answer the question using the pages below.\n\n"
+        "{% for doc in documents %}{{ doc.content }}\n{% endfor %}\n"
+        "Question: {{ question }}"
+    )
+]
+
+pipe = Pipeline()
+pipe.add_component("fetcher", ScrapeUnblockerFetcher())
+pipe.add_component("converter", HTMLToDocument())
+pipe.add_component("prompt_builder", ChatPromptBuilder(template=prompt, required_variables="*"))
+pipe.add_component("llm", OpenAIChatGenerator())
+
+pipe.connect("fetcher.documents", "converter.sources")
+pipe.connect("converter.documents", "prompt_builder.documents")
+pipe.connect("prompt_builder.prompt", "llm.messages")
+
+result = pipe.run(
+    {
+        "fetcher": {"urls": ["https://example.com"]},
+        "prompt_builder": {"question": "What is this page about?"},
+    }
+)
+print(result["llm"]["replies"][0].text)
+```
+
+## Serialization
+
+Both components implement `to_dict()` / `from_dict()`, so pipelines using them
+can be saved and reloaded. The API key is serialized as a Haystack `Secret`
+reference, not as its value.
+
+## Links
+
+- ScrapeUnblocker: https://www.scrapeunblocker.com
+- API documentation: https://developers.scrapeunblocker.com
+- Haystack: https://haystack.deepset.ai
+
+## License
+
+Apache-2.0

scrapeunblocker_haystack-0.1.0/README.md

@@ -0,0 +1,132 @@
+# scrapeunblocker-haystack
+
+[Haystack](https://haystack.deepset.ai/) integration for
+[ScrapeUnblocker](https://www.scrapeunblocker.com) - fetch pages that block
+ordinary HTTP requests.
+
+ScrapeUnblocker renders web pages in a real browser behind anti-bot protections
+such as Cloudflare, DataDome, PerimeterX and Akamai, so your pipeline gets the
+real content instead of a block page, a captcha, or an empty JavaScript shell.
+
+## Installation
+
+```bash
+pip install scrapeunblocker-haystack
+```
+
+## Setup
+
+Get an API key at [scrapeunblocker.com](https://www.scrapeunblocker.com) and
+export it:
+
+```bash
+export SCRAPEUNBLOCKER_API_KEY=<your-api-key>
+```
+
+Both components read that variable by default, or accept a `Secret` explicitly.
+
+## Components
+
+### ScrapeUnblockerFetcher
+
+Fetches URLs and returns one `Document` per page.
+
+```python
+from scrapeunblocker_haystack import ScrapeUnblockerFetcher
+
+fetcher = ScrapeUnblockerFetcher()
+result = fetcher.run(urls=["https://example.com"])
+
+print(result["documents"][0].content[:200])
+```
+
+| Parameter | Default | Description |
+| --- | --- | --- |
+| `api_key` | `SCRAPEUNBLOCKER_API_KEY` env var | ScrapeUnblocker API key |
+| `parsed_data` | `False` | Return AI-parsed structured JSON instead of raw HTML |
+| `proxy_country` | `None` | Two-letter country code for the exit IP |
+| `time_sleep` | `None` | Seconds to wait after load before capturing |
+| `base_url` | `https://api.scrapeunblocker.com` | API base URL |
+| `timeout` | `180` | HTTP timeout in seconds |
+| `raise_on_failure` | `False` | Raise instead of skipping a URL that fails |
+
+By default a URL that cannot be fetched is logged and skipped, so one bad URL
+does not discard the rest of the batch.
+
+### ScrapeUnblockerWebSearch
+
+Searches Google and returns the organic results as `Document` objects, with the
+snippet as content and `title` / `link` / `position` in the metadata.
+
+```python
+from scrapeunblocker_haystack import ScrapeUnblockerWebSearch
+
+search = ScrapeUnblockerWebSearch(top_k=5)
+result = search.run(query="best web scraping api")
+
+for doc in result["documents"]:
+    print(doc.meta["title"], doc.meta["link"])
+```
+
+| Parameter | Default | Description |
+| --- | --- | --- |
+| `api_key` | `SCRAPEUNBLOCKER_API_KEY` env var | ScrapeUnblocker API key |
+| `pages_to_check` | `1` | How many result pages to scrape |
+| `proxy_country` | `None` | Two-letter country code for localised results |
+| `top_k` | `None` | Keep at most this many results |
+
+## In a pipeline
+
+Search the web, fetch the pages behind the results, and answer from them:
+
+```python
+from haystack import Pipeline
+from haystack.components.builders import ChatPromptBuilder
+from haystack.components.converters import HTMLToDocument
+from haystack.components.generators.chat import OpenAIChatGenerator
+from haystack.dataclasses import ChatMessage
+
+from scrapeunblocker_haystack import ScrapeUnblockerFetcher
+
+prompt = [
+    ChatMessage.from_user(
+        "Answer the question using the pages below.\n\n"
+        "{% for doc in documents %}{{ doc.content }}\n{% endfor %}\n"
+        "Question: {{ question }}"
+    )
+]
+
+pipe = Pipeline()
+pipe.add_component("fetcher", ScrapeUnblockerFetcher())
+pipe.add_component("converter", HTMLToDocument())
+pipe.add_component("prompt_builder", ChatPromptBuilder(template=prompt, required_variables="*"))
+pipe.add_component("llm", OpenAIChatGenerator())
+
+pipe.connect("fetcher.documents", "converter.sources")
+pipe.connect("converter.documents", "prompt_builder.documents")
+pipe.connect("prompt_builder.prompt", "llm.messages")
+
+result = pipe.run(
+    {
+        "fetcher": {"urls": ["https://example.com"]},
+        "prompt_builder": {"question": "What is this page about?"},
+    }
+)
+print(result["llm"]["replies"][0].text)
+```
+
+## Serialization
+
+Both components implement `to_dict()` / `from_dict()`, so pipelines using them
+can be saved and reloaded. The API key is serialized as a Haystack `Secret`
+reference, not as its value.
+
+## Links
+
+- ScrapeUnblocker: https://www.scrapeunblocker.com
+- API documentation: https://developers.scrapeunblocker.com
+- Haystack: https://haystack.deepset.ai
+
+## License
+
+Apache-2.0

scrapeunblocker_haystack-0.1.0/pyproject.toml

@@ -0,0 +1,39 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "scrapeunblocker-haystack"
+dynamic = ["version"]
+description = "Haystack integration for ScrapeUnblocker - scrape pages behind anti-bot protections"
+readme = "README.md"
+requires-python = ">=3.9"
+license = "Apache-2.0"
+keywords = ["haystack", "scraping", "web-scraping", "anti-bot", "rag", "llm"]
+authors = [{ name = "ScrapeUnblocker", email = "info@scrapeunblocker.com" }]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+]
+dependencies = ["haystack-ai>=2.0.0", "requests>=2.31.0"]
+
+[project.urls]
+Homepage = "https://www.scrapeunblocker.com"
+Documentation = "https://developers.scrapeunblocker.com"
+Source = "https://github.com/ScrapeUnblocker/scrapeunblocker-haystack"
+Issues = "https://github.com/ScrapeUnblocker/scrapeunblocker-haystack/issues"
+
+[tool.hatch.version]
+path = "src/scrapeunblocker_haystack/version.py"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/scrapeunblocker_haystack"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]

scrapeunblocker_haystack-0.1.0/src/scrapeunblocker_haystack/__init__.py

@@ -0,0 +1,4 @@
+from scrapeunblocker_haystack.fetcher import ScrapeUnblockerFetcher
+from scrapeunblocker_haystack.search import ScrapeUnblockerWebSearch
+
+__all__ = ["ScrapeUnblockerFetcher", "ScrapeUnblockerWebSearch"]

scrapeunblocker_haystack-0.1.0/src/scrapeunblocker_haystack/fetcher.py

@@ -0,0 +1,143 @@
+"""Haystack component that fetches pages through the ScrapeUnblocker API."""
+
+from __future__ import annotations
+
+import json
+from typing import Any, Dict, List, Optional
+
+import requests
+from haystack import Document, component, default_from_dict, default_to_dict, logging
+from haystack.utils import Secret, deserialize_secrets_inplace
+
+logger = logging.getLogger(__name__)
+
+DEFAULT_BASE_URL = "https://api.scrapeunblocker.com"
+DEFAULT_TIMEOUT = 180
+
+
+@component
+class ScrapeUnblockerFetcher:
+    """
+    Fetches web pages through the ScrapeUnblocker API and returns them as Documents.
+
+    ScrapeUnblocker renders pages in a real browser behind anti-bot protections
+    (Cloudflare, DataDome, PerimeterX, Akamai), so it reaches pages that a plain
+    HTTP fetch cannot.
+
+    ### Usage example
+
+    ```python
+    from scrapeunblocker_haystack import ScrapeUnblockerFetcher
+
+    fetcher = ScrapeUnblockerFetcher()
+    result = fetcher.run(urls=["https://example.com"])
+    print(result["documents"][0].content[:200])
+    ```
+    """
+
+    def __init__(
+        self,
+        api_key: Secret = Secret.from_env_var("SCRAPEUNBLOCKER_API_KEY"),
+        parsed_data: bool = False,
+        proxy_country: Optional[str] = None,
+        time_sleep: Optional[int] = None,
+        base_url: str = DEFAULT_BASE_URL,
+        timeout: int = DEFAULT_TIMEOUT,
+        raise_on_failure: bool = False,
+    ) -> None:
+        """
+        :param api_key: ScrapeUnblocker API key. Read from `SCRAPEUNBLOCKER_API_KEY` by default.
+        :param parsed_data: Return AI-parsed structured JSON instead of raw HTML.
+        :param proxy_country: Two-letter country code for the exit IP, for geo-restricted content.
+        :param time_sleep: Seconds to wait after page load before capturing.
+        :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.
+        """
+        self.api_key = api_key
+        self.parsed_data = parsed_data
+        self.proxy_country = proxy_country
+        self.time_sleep = time_sleep
+        self.base_url = base_url.rstrip("/")
+        self.timeout = timeout
+        self.raise_on_failure = raise_on_failure
+
+    def to_dict(self) -> Dict[str, Any]:
+        """Serialize this component to a dictionary."""
+        return default_to_dict(
+            self,
+            api_key=self.api_key.to_dict(),
+            parsed_data=self.parsed_data,
+            proxy_country=self.proxy_country,
+            time_sleep=self.time_sleep,
+            base_url=self.base_url,
+            timeout=self.timeout,
+            raise_on_failure=self.raise_on_failure,
+        )
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "ScrapeUnblockerFetcher":
+        """Deserialize this component from a dictionary."""
+        deserialize_secrets_inplace(data["init_parameters"], keys=["api_key"])
+        return default_from_dict(cls, data)
+
+    def _fetch(self, url: str) -> requests.Response:
+        params: Dict[str, Any] = {"url": url}
+        if self.parsed_data:
+            params["parsed_data"] = True
+        if self.proxy_country:
+            params["proxy_country"] = self.proxy_country
+        if self.time_sleep is not None:
+            params["time_sleep"] = self.time_sleep
+
+        response = requests.post(
+            f"{self.base_url}/getPageSource",
+            params=params,
+            headers={"X-ScrapeUnblocker-Key": self.api_key.resolve_value()},
+            timeout=self.timeout,
+        )
+        response.raise_for_status()
+        return response
+
+    @component.output_types(documents=List[Document])
+    def run(self, urls: List[str]) -> Dict[str, List[Document]]:
+        """
+        Fetch each URL and return one Document per successfully fetched page.
+
+        :param urls: URLs to fetch.
+        :returns: A dictionary with a `documents` key holding the fetched pages.
+        """
+        documents: List[Document] = []
+
+        for url in urls:
+            try:
+                response = self._fetch(url)
+            except Exception as exc:
+                if self.raise_on_failure:
+                    raise
+                # One unreachable URL should not discard the rest of the batch.
+                logger.warning(
+                    "ScrapeUnblocker could not fetch {url}: {error}", url=url, error=str(exc)
+                )
+                continue
+
+            if self.parsed_data:
+                try:
+                    content = json.dumps(response.json(), ensure_ascii=False)
+                except ValueError:
+                    content = response.text
+            else:
+                content = response.text
+
+            documents.append(
+                Document(
+                    content=content,
+                    meta={
+                        "url": url,
+                        "content_type": response.headers.get("Content-Type", ""),
+                        "parsed_data": self.parsed_data,
+                    },
+                )
+            )
+
+        return {"documents": documents}

scrapeunblocker_haystack-0.1.0/src/scrapeunblocker_haystack/search.py

@@ -0,0 +1,116 @@
+"""Haystack component that reads Google search results through the ScrapeUnblocker API."""
+
+from __future__ import annotations
+
+from typing import Any, Dict, List, Optional
+
+import requests
+from haystack import Document, component, default_from_dict, default_to_dict
+from haystack.utils import Secret, deserialize_secrets_inplace
+
+DEFAULT_BASE_URL = "https://api.scrapeunblocker.com"
+DEFAULT_TIMEOUT = 180
+
+
+@component
+class ScrapeUnblockerWebSearch:
+    """
+    Searches Google through the ScrapeUnblocker API and returns the organic results.
+
+    Each result becomes a Document whose content is the snippet, with the title,
+    link and position in the metadata.
+
+    ### Usage example
+
+    ```python
+    from scrapeunblocker_haystack import ScrapeUnblockerWebSearch
+
+    search = ScrapeUnblockerWebSearch()
+    result = search.run(query="best web scraping api")
+    for doc in result["documents"]:
+        print(doc.meta["title"], doc.meta["link"])
+    ```
+    """
+
+    def __init__(
+        self,
+        api_key: Secret = Secret.from_env_var("SCRAPEUNBLOCKER_API_KEY"),
+        pages_to_check: int = 1,
+        proxy_country: Optional[str] = None,
+        top_k: Optional[int] = None,
+        base_url: str = DEFAULT_BASE_URL,
+        timeout: int = DEFAULT_TIMEOUT,
+    ) -> None:
+        """
+        :param api_key: ScrapeUnblocker API key. Read from `SCRAPEUNBLOCKER_API_KEY` by default.
+        :param pages_to_check: How many result pages to scrape.
+        :param proxy_country: Two-letter country code for country-specific results.
+        :param top_k: Keep at most this many results. `None` keeps all of them.
+        :param base_url: API base URL. Override to target a different environment.
+        :param timeout: HTTP timeout in seconds.
+        """
+        self.api_key = api_key
+        self.pages_to_check = pages_to_check
+        self.proxy_country = proxy_country
+        self.top_k = top_k
+        self.base_url = base_url.rstrip("/")
+        self.timeout = timeout
+
+    def to_dict(self) -> Dict[str, Any]:
+        """Serialize this component to a dictionary."""
+        return default_to_dict(
+            self,
+            api_key=self.api_key.to_dict(),
+            pages_to_check=self.pages_to_check,
+            proxy_country=self.proxy_country,
+            top_k=self.top_k,
+            base_url=self.base_url,
+            timeout=self.timeout,
+        )
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "ScrapeUnblockerWebSearch":
+        """Deserialize this component from a dictionary."""
+        deserialize_secrets_inplace(data["init_parameters"], keys=["api_key"])
+        return default_from_dict(cls, data)
+
+    @component.output_types(documents=List[Document])
+    def run(self, query: str) -> Dict[str, List[Document]]:
+        """
+        Search Google for `query` and return the organic results as Documents.
+
+        :param query: The search term.
+        :returns: A dictionary with a `documents` key holding the organic results.
+        """
+        params: Dict[str, Any] = {"keyword": query, "pages_to_check": self.pages_to_check}
+        if self.proxy_country:
+            params["proxy_country"] = self.proxy_country
+
+        response = requests.post(
+            f"{self.base_url}/serpApi",
+            params=params,
+            headers={"X-ScrapeUnblocker-Key": self.api_key.resolve_value()},
+            timeout=self.timeout,
+        )
+        response.raise_for_status()
+
+        payload = response.json()
+        organic = payload.get("organic") if isinstance(payload, dict) else None
+        results = organic if isinstance(organic, list) else []
+        if self.top_k is not None:
+            results = results[: self.top_k]
+
+        documents = [
+            Document(
+                content=result.get("description") or result.get("title") or "",
+                meta={
+                    "title": result.get("title"),
+                    "link": result.get("url"),
+                    "position": result.get("position"),
+                    "query": query,
+                },
+            )
+            for result in results
+        ]
+
+        return {"documents": documents}

scrapeunblocker_haystack-0.1.0/src/scrapeunblocker_haystack/version.py

@@ -0,0 +1 @@
+__version__ = "0.1.0"

scrapeunblocker_haystack-0.1.0/tests/test_components.py

@@ -0,0 +1,150 @@
+"""Unit tests for the ScrapeUnblocker Haystack components."""
+
+import json
+from unittest.mock import MagicMock, patch
+
+import pytest
+from haystack import Document
+from haystack.utils import Secret
+
+from scrapeunblocker_haystack import ScrapeUnblockerFetcher, ScrapeUnblockerWebSearch
+
+API_KEY = Secret.from_token("test_key")
+# Haystack refuses to serialize token secrets, so to_dict tests use an env-var secret.
+ENV_KEY = Secret.from_env_var("SCRAPEUNBLOCKER_API_KEY")
+
+
+def _response(text: str = "<html><title>Test</title></html>", json_data=None) -> MagicMock:
+    response = MagicMock()
+    response.text = text
+    response.headers = {"Content-Type": "text/html"}
+    response.raise_for_status.return_value = None
+    if json_data is not None:
+        response.json.return_value = json_data
+    return response
+
+
+class TestFetcher:
+    def test_defaults(self):
+        fetcher = ScrapeUnblockerFetcher(api_key=API_KEY)
+        assert fetcher.parsed_data is False
+        assert fetcher.base_url == "https://api.scrapeunblocker.com"
+
+    def test_base_url_trailing_slash_stripped(self):
+        fetcher = ScrapeUnblockerFetcher(api_key=API_KEY, base_url="https://example.com/")
+        assert fetcher.base_url == "https://example.com"
+
+    def test_to_dict_and_back(self):
+        fetcher = ScrapeUnblockerFetcher(api_key=ENV_KEY, parsed_data=True, proxy_country="de")
+        data = fetcher.to_dict()
+        assert data["init_parameters"]["parsed_data"] is True
+        assert data["init_parameters"]["proxy_country"] == "de"
+
+        restored = ScrapeUnblockerFetcher.from_dict(data)
+        assert restored.parsed_data is True
+        assert restored.proxy_country == "de"
+
+    @patch("scrapeunblocker_haystack.fetcher.requests.post")
+    def test_run_single_url(self, mock_post):
+        mock_post.return_value = _response()
+        fetcher = ScrapeUnblockerFetcher(api_key=API_KEY)
+
+        result = fetcher.run(urls=["https://example.com"])
+
+        assert len(result["documents"]) == 1
+        doc = result["documents"][0]
+        assert isinstance(doc, Document)
+        assert "Test" in doc.content
+        assert doc.meta["url"] == "https://example.com"
+
+        _, kwargs = mock_post.call_args
+        assert kwargs["headers"]["X-ScrapeUnblocker-Key"] == "test_key"
+        assert kwargs["params"] == {"url": "https://example.com"}
+
+    @patch("scrapeunblocker_haystack.fetcher.requests.post")
+    def test_run_forwards_options(self, mock_post):
+        mock_post.return_value = _response(json_data={"ok": True})
+        fetcher = ScrapeUnblockerFetcher(
+            api_key=API_KEY, parsed_data=True, proxy_country="de", time_sleep=5
+        )
+        fetcher.run(urls=["https://example.com"])
+
+        _, kwargs = mock_post.call_args
+        assert kwargs["params"]["parsed_data"] is True
+        assert kwargs["params"]["proxy_country"] == "de"
+        assert kwargs["params"]["time_sleep"] == 5
+
+    @patch("scrapeunblocker_haystack.fetcher.requests.post")
+    def test_parsed_data_serialised_as_json(self, mock_post):
+        mock_post.return_value = _response(json_data={"title": "Test", "price": "9.99"})
+        fetcher = ScrapeUnblockerFetcher(api_key=API_KEY, parsed_data=True)
+
+        result = fetcher.run(urls=["https://example.com"])
+
+        assert json.loads(result["documents"][0].content) == {"title": "Test", "price": "9.99"}
+
+    @patch("scrapeunblocker_haystack.fetcher.requests.post")
+    def test_failure_is_skipped_by_default(self, mock_post):
+        mock_post.side_effect = [Exception("boom"), _response()]
+        fetcher = ScrapeUnblockerFetcher(api_key=API_KEY)
+
+        result = fetcher.run(urls=["https://broken.com", "https://ok.com"])
+
+        assert len(result["documents"]) == 1
+        assert result["documents"][0].meta["url"] == "https://ok.com"
+
+    @patch("scrapeunblocker_haystack.fetcher.requests.post")
+    def test_failure_raises_when_requested(self, mock_post):
+        mock_post.side_effect = Exception("boom")
+        fetcher = ScrapeUnblockerFetcher(api_key=API_KEY, raise_on_failure=True)
+
+        with pytest.raises(Exception, match="boom"):
+            fetcher.run(urls=["https://broken.com"])
+
+
+class TestWebSearch:
+    @patch("scrapeunblocker_haystack.search.requests.post")
+    def test_run(self, mock_post):
+        mock_post.return_value = _response(
+            json_data={
+                "organic": [
+                    {"title": "First", "url": "https://a.com", "description": "snippet a", "position": "1"},
+                    {"title": "Second", "url": "https://b.com", "description": "snippet b", "position": "2"},
+                ]
+            }
+        )
+        search = ScrapeUnblockerWebSearch(api_key=API_KEY)
+
+        result = search.run(query="test query")
+
+        assert len(result["documents"]) == 2
+        assert result["documents"][0].content == "snippet a"
+        assert result["documents"][0].meta["title"] == "First"
+        assert result["documents"][0].meta["link"] == "https://a.com"
+        assert result["documents"][0].meta["query"] == "test query"
+
+        _, kwargs = mock_post.call_args
+        assert kwargs["params"]["keyword"] == "test query"
+
+    @patch("scrapeunblocker_haystack.search.requests.post")
+    def test_top_k(self, mock_post):
+        mock_post.return_value = _response(
+            json_data={"organic": [{"title": str(i), "url": "", "description": str(i)} for i in range(10)]}
+        )
+        search = ScrapeUnblockerWebSearch(api_key=API_KEY, top_k=3)
+
+        assert len(search.run(query="q")["documents"]) == 3
+
+    @patch("scrapeunblocker_haystack.search.requests.post")
+    def test_missing_organic_returns_empty(self, mock_post):
+        mock_post.return_value = _response(json_data={"totalResults": None})
+        search = ScrapeUnblockerWebSearch(api_key=API_KEY)
+
+        assert search.run(query="q")["documents"] == []
+
+    def test_to_dict_and_back(self):
+        search = ScrapeUnblockerWebSearch(api_key=ENV_KEY, top_k=5, proxy_country="us")
+        data = search.to_dict()
+        restored = ScrapeUnblockerWebSearch.from_dict(data)
+        assert restored.top_k == 5
+        assert restored.proxy_country == "us"