scrapegraphai 0.0.1__tar.gz

scrapegraphai-0.0.1/LICENSE

@@ -0,0 +1,201 @@
+                                 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 2024 Marco Vinciguerra
+
+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.

scrapegraphai-0.0.1/PKG-INFO

@@ -0,0 +1,133 @@
+Metadata-Version: 2.1
+Name: scrapegraphai
+Version: 0.0.1
+Summary: A web scraping library based on LangChain which uses LLM and direct graph logic to create scraping pipelines.
+Home-page: https://scrapegraph-ai.readthedocs.io/
+License: MIT
+Keywords: langchain,ai,artificial intelligence,gpt,machine learning,rag,nlp,natural language processing,openai,scraping,web scraping,web scraping library,web scraping tool,webscraping,graph,scrapegraph
+Author: Marco Vinciguerra
+Author-email: mvincig11@gmail.com
+Requires-Python: >=3.9,<4.0
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+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: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Dist: beautifulsoup4 (==4.12.3)
+Requires-Dist: langchain (==0.1.6)
+Requires-Dist: langchain_community (==0.0.19)
+Requires-Dist: langchain_core (==0.1.22)
+Requires-Dist: langchain_openai (==0.0.5)
+Requires-Dist: pandas (==2.0.3)
+Requires-Dist: python-dotenv (==1.0.1)
+Requires-Dist: tiktoken (>=0.5.2,<0.6.0)
+Requires-Dist: tqdm (==4.66.1)
+Project-URL: Documentation, https://scrapegraph-doc.onrender.com/
+Project-URL: Repository, https://github.com/VinciGit00/Scrapegraph-ai
+Description-Content-Type: text/markdown
+
+# 🕷️ ScrapeGraphAI: You Only Scrape Once
+
+ScrapeGraphAI is a *web scraping* python library based on LangChain which uses LLM and direct graph logic to create scraping pipelines.
+Just say which information you want to extract and the library will do it for you!
+
+<p align="center">
+  <img src="docs/assets/scrapegraphai_logo.png" alt="Scrapegraph-ai Logo" style="width: 50%;">
+</p>
+
+
+## 🚀 Quick install
+
+```bash
+pip install scrapegraphai
+```
+## 🔍 Demo
+
+Try out ScrapeGraphAI in your browser:
+
+[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/VinciGit00/Scrapegraph-ai)
+
+## 📖 Documentation
+
+The documentation for ScrapeGraphAI can be found [here](https://scrapegraph-ai.readthedocs.io/en/latest/).
+Behind this there is also the docusaurus documentation [here]([https://scrapegraph-ai.readthedocs.io/en/latest/](https://scrapegraph-doc.onrender.com/)).
+
+## Setup the api keys
+
+The procedure per for activatating the openai keys are in the following link: [link](https://scrapegraph-ai.readthedocs.io/en/latest/index.html).
+
+## 💻 Usage
+
+### Case 1: Extracting information using a prompt
+
+You can use the `SmartScraper` class to extract information from a website using a prompt.
+
+The `SmartScraper` class is a direct graph implementation that uses the most common nodes present in a web scraping pipeline. For more information, please see the [documentation](https://scrapegraph-ai.readthedocs.io/en/latest/).
+
+```python
+from scrapegraphai.graphs import SmartScraper
+
+OPENAI_API_KEY = "YOUR_API_KEY"
+
+llm_config = {
+    "api_key": OPENAI_API_KEY,
+    "model_name": "gpt-3.5-turbo",
+}
+
+smart_scraper = SmartScraper("List me all the titles and project descriptions",
+                             "https://perinim.github.io/projects/", llm_config)
+
+answer = smart_scraper.run()
+print(answer)
+```
+
+The output will be a dictionary with the extracted information, for example:
+
+```bash
+{
+    'titles': [
+        'Rotary Pendulum RL'
+        ],
+    'descriptions': [
+        'Open Source project aimed at controlling a real life rotary pendulum using RL algorithms'
+        ]
+}
+```
+
+## 🤝 Contributing
+
+Contributions are welcome! Please check out the todos below, and feel free to open a pull request.
+For more information, please see the [contributing guidelines](CONTRIBUTING.md).
+
+After installing and activating the virtual environment, please remember to install the library using the "dev" extra parameter to have the extra dependencies for development.
+
+```bash
+pip install -e .[dev]
+```
+
+## Contributors
+
+[![Contributors](https://contrib.rocks/image?repo=VinciGit00/Scrapegraph-ai)](https://github.com/VinciGit00/Scrapegraph-ai/graphs/contributors)
+
+## Authors
+
+<p align="center">
+  <img src="docs/assets/logo_authors.png" alt="Authors Logos"">
+</p>
+
+## 📜 License
+
+ScrapeGraphAI is licensed under the Apache 2.0 License. See the [LICENSE](LICENSE) file for more information.
+
+## Acknowledgements
+
+- We would like to thank all the contributors to the project and the open-source community for their support.
+- ScrapeGraphAI is meant to be used for data exploration and research purposes only. We are not responsible for any misuse of the library.
+
+## Thanks to: 
+- [nicolapiazzalunga](https://github.com/nicolapiazzalunga) for having inspired us to the functions: scrapegraph/convert_to_json.py and scrapegraph/convert_to_csv.py
+

scrapegraphai-0.0.1/README.md

@@ -0,0 +1,100 @@
+# 🕷️ ScrapeGraphAI: You Only Scrape Once
+
+ScrapeGraphAI is a *web scraping* python library based on LangChain which uses LLM and direct graph logic to create scraping pipelines.
+Just say which information you want to extract and the library will do it for you!
+
+<p align="center">
+  <img src="docs/assets/scrapegraphai_logo.png" alt="Scrapegraph-ai Logo" style="width: 50%;">
+</p>
+
+
+## 🚀 Quick install
+
+```bash
+pip install scrapegraphai
+```
+## 🔍 Demo
+
+Try out ScrapeGraphAI in your browser:
+
+[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/VinciGit00/Scrapegraph-ai)
+
+## 📖 Documentation
+
+The documentation for ScrapeGraphAI can be found [here](https://scrapegraph-ai.readthedocs.io/en/latest/).
+Behind this there is also the docusaurus documentation [here]([https://scrapegraph-ai.readthedocs.io/en/latest/](https://scrapegraph-doc.onrender.com/)).
+
+## Setup the api keys
+
+The procedure per for activatating the openai keys are in the following link: [link](https://scrapegraph-ai.readthedocs.io/en/latest/index.html).
+
+## 💻 Usage
+
+### Case 1: Extracting information using a prompt
+
+You can use the `SmartScraper` class to extract information from a website using a prompt.
+
+The `SmartScraper` class is a direct graph implementation that uses the most common nodes present in a web scraping pipeline. For more information, please see the [documentation](https://scrapegraph-ai.readthedocs.io/en/latest/).
+
+```python
+from scrapegraphai.graphs import SmartScraper
+
+OPENAI_API_KEY = "YOUR_API_KEY"
+
+llm_config = {
+    "api_key": OPENAI_API_KEY,
+    "model_name": "gpt-3.5-turbo",
+}
+
+smart_scraper = SmartScraper("List me all the titles and project descriptions",
+                             "https://perinim.github.io/projects/", llm_config)
+
+answer = smart_scraper.run()
+print(answer)
+```
+
+The output will be a dictionary with the extracted information, for example:
+
+```bash
+{
+    'titles': [
+        'Rotary Pendulum RL'
+        ],
+    'descriptions': [
+        'Open Source project aimed at controlling a real life rotary pendulum using RL algorithms'
+        ]
+}
+```
+
+## 🤝 Contributing
+
+Contributions are welcome! Please check out the todos below, and feel free to open a pull request.
+For more information, please see the [contributing guidelines](CONTRIBUTING.md).
+
+After installing and activating the virtual environment, please remember to install the library using the "dev" extra parameter to have the extra dependencies for development.
+
+```bash
+pip install -e .[dev]
+```
+
+## Contributors
+
+[![Contributors](https://contrib.rocks/image?repo=VinciGit00/Scrapegraph-ai)](https://github.com/VinciGit00/Scrapegraph-ai/graphs/contributors)
+
+## Authors
+
+<p align="center">
+  <img src="docs/assets/logo_authors.png" alt="Authors Logos"">
+</p>
+
+## 📜 License
+
+ScrapeGraphAI is licensed under the Apache 2.0 License. See the [LICENSE](LICENSE) file for more information.
+
+## Acknowledgements
+
+- We would like to thank all the contributors to the project and the open-source community for their support.
+- ScrapeGraphAI is meant to be used for data exploration and research purposes only. We are not responsible for any misuse of the library.
+
+## Thanks to: 
+- [nicolapiazzalunga](https://github.com/nicolapiazzalunga) for having inspired us to the functions: scrapegraph/convert_to_json.py and scrapegraph/convert_to_csv.py

scrapegraphai-0.0.1/pyproject.toml

@@ -0,0 +1,48 @@
+[tool.poetry]
+name = "scrapegraphai"
+version = "0.0.1"
+description = "A web scraping library based on LangChain which uses LLM and direct graph logic to create scraping pipelines."
+authors = [
+    "Marco Vinciguerra <mvincig11@gmail.com>",
+    "Marco Perini <perinim.98@gmail.com>",
+    "Lorenzo Padoan <lorenzo.padoan977@gmail.com>"
+]
+license = "MIT"
+readme = "README.md"
+homepage = "https://scrapegraph-ai.readthedocs.io/"
+repository = "https://github.com/VinciGit00/Scrapegraph-ai"
+documentation = "https://scrapegraph-doc.onrender.com/"
+keywords = ["langchain", "ai", "artificial intelligence", "gpt", "machine learning", "rag", "nlp", "natural language processing", "openai", "scraping", "web scraping", "web scraping library", "web scraping tool", "webscraping", "graph", "scrapegraph"]
+classifiers = [
+    "Intended Audience :: Developers",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Programming Language :: Python :: 3",
+    "Operating System :: OS Independent",
+]
+
+[tool.poetry.dependencies]
+python = "^3.9"
+langchain = "0.1.6"
+langchain_community = "0.0.19"
+langchain_core = "0.1.22"
+langchain_openai = "0.0.5"
+beautifulsoup4 = "4.12.3"
+pandas = "2.0.3"
+python-dotenv = "1.0.1"
+tiktoken = {version = ">=0.5.2,<0.6.0"}
+tqdm = "4.66.1"
+
+[tool.poetry.dev-dependencies]
+pytest = "8.0.0"
+
+[tool.poetry.group.docs]
+optional = true
+
+[tool.poetry.group.docs.dependencies]
+sphinx = "7.1.2"
+sphinx-rtd-theme = "2.0.0"
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"
+

scrapegraphai-0.0.1/scrapegraphai/__init__.py

@@ -0,0 +1,3 @@
+"""
+    __init__.py file for scrapegraphai folder
+"""

scrapegraphai-0.0.1/scrapegraphai/graphs/__init__.py

@@ -0,0 +1,5 @@
+""" 
+__init__.py file for graphs folder
+"""
+from .base_graph import BaseGraph
+from .smart_scraper_graph import SmartScraper

scrapegraphai-0.0.1/scrapegraphai/graphs/base_graph.py

@@ -0,0 +1,76 @@
+"""
+Module for creating the base graphs
+ """
+
+
+class BaseGraph:
+    """
+    BaseGraph manages the execution flow of a graph composed of interconnected nodes.
+
+    Attributes:
+        nodes (dict): A dictionary mapping each node's name to its corresponding node instance.
+        edges (dict): A dictionary representing the directed edges of the graph where each 
+                      key-value pair corresponds to the from-node and to-node relationship.
+        entry_point (str): The name of the entry point node from which the graph execution begins.
+
+    Methods:
+        execute(initial_state): Executes the graph's nodes starting from the entry point and 
+                                traverses the graph based on the provided initial state.
+
+    Args:
+        nodes (iterable): An iterable of node instances that will be part of the graph.
+        edges (iterable): An iterable of tuples where each tuple represents a directed edge 
+                          in the graph, defined by a pair of nodes (from_node, to_node).
+        entry_point (BaseNode): The node instance that represents the entry point of the graph.
+    """
+
+    def __init__(self, nodes: dict, edges: dict, entry_point: str):
+        """
+        Initializes the graph with nodes, edges, and the entry point.
+        """
+        self.nodes = {node.node_name: node for node in nodes}
+        self.edges = self._create_edges(edges)
+        self.entry_point = entry_point.node_name
+
+    def _create_edges(self, edges: dict) -> dict:
+        """
+        Helper method to create a dictionary of edges from the given iterable of tuples.
+
+        Args:
+            edges (iterable): An iterable of tuples representing the directed edges.
+
+        Returns:
+            dict: A dictionary of edges with the from-node as keys and to-node as values.
+        """
+        edge_dict = {}
+        for from_node, to_node in edges:
+            edge_dict[from_node.node_name] = to_node.node_name
+        return edge_dict
+
+    def execute(self, initial_state: dict) -> dict:
+        """
+        Executes the graph by traversing nodes starting from the entry point. The execution 
+        follows the edges based on the result of each node's execution and continues until 
+        it reaches a node with no outgoing edges.
+
+        Args:
+            initial_state (dict): The initial state to pass to the entry point node.
+
+        Returns:
+            dict: The state after execution has completed, which may have been altered by the nodes.
+        """
+        current_node_name = self.entry_point
+        state = initial_state
+
+        while current_node_name is not None:
+            current_node = self.nodes[current_node_name]
+            result = current_node.execute(state)
+
+            if current_node.node_type == "conditional_node":
+                current_node_name = result
+            elif current_node_name in self.edges:
+                current_node_name = self.edges[current_node_name]
+            else:
+                current_node_name = None
+
+        return state

scrapegraphai-0.0.1/scrapegraphai/graphs/smart_scraper_graph.py

@@ -0,0 +1,107 @@
+""" 
+Module for creating the smart scaper
+"""
+from langchain_openai import ChatOpenAI
+from .base_graph import BaseGraph
+from ..nodes import FetchHTMLNode, ConditionalNode, GetProbableTagsNode
+from ..nodes import GenerateAnswerNode, ParseHTMLNode
+
+
+class SmartScraper:
+    """
+    SmartScraper is a comprehensive web scraping tool that automates the process of extracting
+    information from web pages using a natural language model to interpret and answer prompts.
+
+    Attributes:
+        prompt (str): The user's natural language prompt for the information to be extracted.
+        url (str): The URL of the web page to scrape.
+        llm_config (dict): Configuration parameters for the language model, with 
+        'api_key' being mandatory.
+        llm (ChatOpenAI): An instance of the ChatOpenAI class configured with llm_config.
+        graph (BaseGraph): An instance of the BaseGraph class representing the scraping workflow.
+
+    Methods:
+        run(): Executes the web scraping process and returns the answer to the prompt.
+
+    Args:
+        prompt (str): The user's natural language prompt for the information to be extracted.
+        url (str): The URL of the web page to scrape.
+        llm_config (dict): A dictionary containing configuration options for the language model.
+                           Must include 'api_key', may also specify 'model_name', 
+                           'temperature', and 'streaming'.
+    """
+
+    def __init__(self, prompt: str, url: str, llm_config: dict):
+        """
+        Initializes the SmartScraper with a prompt, URL, and language model configuration.
+        """
+        self.prompt = prompt
+        self.url = url
+        self.llm_config = llm_config
+        self.llm = self._create_llm()
+        self.graph = self._create_graph()
+
+    def _create_llm(self):
+        """
+        Creates an instance of the ChatOpenAI class with the provided language model configuration.
+
+        Returns:
+            ChatOpenAI: An instance of the ChatOpenAI class.
+
+        Raises:
+            ValueError: If 'api_key' is not provided in llm_config.
+        """
+        llm_defaults = {
+            "model_name": "gpt-3.5-turbo",
+            "temperature": 0,
+            "streaming": True
+        }
+        # Update defaults with any LLM parameters that were provided
+        llm_params = {**llm_defaults, **self.llm_config}
+        # Ensure the api_key is set, raise an error if it's not
+        if "api_key" not in llm_params:
+            raise ValueError("LLM configuration must include an 'api_key'.")
+        # Create the ChatOpenAI instance with the provided and default parameters
+        return ChatOpenAI(**llm_params)
+
+    def _create_graph(self):
+        """
+        Creates the graph of nodes representing the workflow for web scraping.
+
+        Returns:
+            BaseGraph: An instance of the BaseGraph class.
+        """
+        fetch_html_node = FetchHTMLNode("fetch_html")
+        get_probable_tags_node = GetProbableTagsNode(
+            self.llm, "get_probable_tags")
+        parse_document_node = ParseHTMLNode("parse_document")
+        generate_answer_node = GenerateAnswerNode(self.llm, "generate_answer")
+        conditional_node = ConditionalNode(
+            "conditional", [parse_document_node, generate_answer_node])
+
+        return BaseGraph(
+            nodes={
+                fetch_html_node,
+                get_probable_tags_node,
+                conditional_node,
+                parse_document_node,
+                generate_answer_node,
+            },
+            edges={
+                (fetch_html_node, get_probable_tags_node),
+                (get_probable_tags_node, conditional_node),
+                (parse_document_node, generate_answer_node)
+            },
+            entry_point=fetch_html_node
+        )
+
+    def run(self) -> str:
+        """
+        Executes the scraping process by running the graph and returns the extracted information.
+
+        Returns:
+            str: The answer extracted from the web page, corresponding to the given prompt.
+        """
+        inputs = {"keys": {"user_input": self.prompt, "url": self.url}}
+        final_state = self.graph.execute(inputs)
+        return final_state["keys"].get("answer", "No answer found.")