scrapegraphai 0.0.1__py3-none-any.whl

scrapegraphai/__init__.py

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

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/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/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.")

scrapegraphai/info/dictionaries.py

@@ -0,0 +1,40 @@
+"""
+Module for defining dictionaries and token limits
+"""
+
+schema_example = {
+    "properties": {
+        "person_name": {"type": "string"},
+        "person_surname": {"type": "string"},
+        "profession": {"type": "string"},
+        "hobbies": {"type": "string"},
+        "projects": {
+            "type": "array",
+            "items": {
+                "type": "object",
+                "properties": {
+                    "project_name": {"type": "string"},
+                    "project_description": {"type": "string"},
+                    "url": {"type": "string"}
+                },
+                "required": ["project_name", "project_description", "url"],
+            },
+        },
+    },
+    "required": ["person_name", "person_surname", "profession", "hobbies", "projects"],
+}
+
+models_tokens = {
+    "gpt-3.5-turbo-0125": 16385,
+    "gpt-3.5-turbo": 4096,
+    "gpt-3.5-turbo-1106": 16385,
+    "gpt-3.5-turbo-instruct": 4096,
+    "gpt-4-0125-preview": 128000,
+    "gpt-4-turbo-preview": 128000,
+    "gpt-4-1106-preview": 128000,
+    "gpt-4-vision-preview": 128000,
+    "gpt-4": 8192,
+    "gpt-4-0613": 8192,
+    "gpt-4-32k": 32768,
+    "gpt-4-32k-0613": 32768,
+}

scrapegraphai/nodes/__init__.py

@@ -0,0 +1,8 @@
+""" 
+__init__.py file for node folder 
+"""
+from .fetch_html_node import FetchHTMLNode
+from .conditional_node import ConditionalNode
+from .get_probable_tags_node import GetProbableTagsNode
+from .generate_answer_node import GenerateAnswerNode
+from .parse_html_node import ParseHTMLNode

scrapegraphai/nodes/base_node.py

@@ -0,0 +1,66 @@
+""" 
+Module for creating the basic node
+"""
+from abc import ABC, abstractmethod
+
+
+class BaseNode(ABC):
+    """
+    An abstract base class for nodes in a graph-based workflow. Each node is 
+    intended to perform a specific action when executed as part of the graph's 
+    processing flow.
+
+    Attributes:
+        node_name (str): A unique identifier for the node.
+        node_type (str): Specifies the node's type, which influences how the 
+                         node interacts within the graph. Valid values are 
+                         "node" for standard nodes and "conditional_node" for 
+                         nodes that determine the flow based on conditions.
+
+    Methods:
+        execute(state): An abstract method that subclasses must implement. This 
+                        method should contain the logic that the node executes 
+                        when it is reached in the graph's flow. It takes the 
+                        graph's current state as input and returns the updated 
+                        state after execution.
+
+    Args:
+        node_name (str): The unique identifier name for the node. This name is 
+                         used to reference the node within the graph.
+        node_type (str): The type of the node, limited to "node" or 
+                         "conditional_node". This categorization helps in 
+                         determining the node's role and behavior within the 
+                         graph.
+
+    Raises:
+        ValueError: If the provided `node_type` is not one of the allowed 
+                    values ("node" or "conditional_node"), a ValueError is 
+                    raised to indicate the incorrect usage.
+    """
+
+    def __init__(self, node_name: str, node_type: str):
+        """
+        Initialize the node with a unique identifier and a specified node type.
+
+        Args:
+            node_name (str): The unique identifier name for the node.
+            node_type (str): The type of the node, limited to "node" or "conditional_node".
+
+        Raises:
+            ValueError: If node_type is not "node" or "conditional_node".
+        """
+        self.node_name = node_name
+        if node_type not in ["node", "conditional_node"]:
+            raise ValueError(
+                f"node_type must be 'node' or 'conditional_node', got '{node_type}'")
+        self.node_type = node_type
+
+    @abstractmethod
+    def execute(self, state: dict):
+        """
+        Execute the node's logic and return the updated state.
+        Args:
+            state (dict): The current state of the graph.
+        :return: The updated state after executing this node.
+        """
+        pass

scrapegraphai/nodes/conditional_node.py

@@ -0,0 +1,68 @@
+""" 
+Module for implementing the conditional node
+"""
+from .base_node import BaseNode
+
+
+class ConditionalNode(BaseNode):
+    """
+    A node that determines the next step in the graph's execution flow based on 
+    the presence and content of a specified key in the graph's state. It extends 
+    the BaseNode by adding condition-based logic to the execution process.
+
+    This node type is used to implement branching logic within the graph, allowing 
+    for dynamic paths based on the data available in the current state.
+
+    Attributes:
+        key_name (str): The name of the key in the state to check for its presence.
+        next_nodes (list): A list of two node instances. The first node is chosen 
+                           for execution if the key exists and has a non-empty value, 
+                           and the second node is chosen if the key does not exist or 
+                           is empty.
+
+    Args:
+        key_name (str): The name of the key to check in the graph's state. This is 
+                        used to determine the path the graph's execution should take.
+        next_nodes (list): A list containing exactly two node instances, specifying 
+                           the next nodes to execute based on the condition's outcome.
+        node_name (str, optional): The unique identifier name for the node. Defaults 
+                                   to "ConditionalNode".
+
+    Raises:
+        ValueError: If next_nodes does not contain exactly two elements, indicating 
+                    a misconfiguration in specifying the conditional paths.
+    """
+
+    def __init__(self, key_name: str, next_nodes: list, node_name="ConditionalNode"):
+        """
+        Initializes the node with the key to check and the next node names based on the condition.
+
+        Args:
+            key_name (str): The name of the key to check in the state.
+            next_nodes (list): A list containing exactly two names of the next nodes.
+                               The first is used if the key exists, the second if it does not.
+
+        Raises:
+            ValueError: If next_nodes does not contain exactly two elements.
+        """
+
+        super().__init__(node_name, "conditional_node")
+        self.key_name = key_name
+        if len(next_nodes) != 2:
+            raise ValueError("next_nodes must contain exactly two elements.")
+        self.next_nodes = next_nodes
+
+    def execute(self, state: dict) -> str:
+        """
+        Checks if the specified key is present in the state and decides the next node accordingly.
+
+        Args:
+            state (dict): The current state of the graph.
+
+        Returns:
+            str: The name of the next node to execute based on the presence of the key.
+        """
+
+        if self.key_name in state.get("keys", {}) and len(state["keys"][self.key_name]) > 0:
+            return self.next_nodes[0].node_name
+        return self.next_nodes[1].node_name

scrapegraphai/nodes/fetch_html_node.py

@@ -0,0 +1,67 @@
+""" 
+Module for fetching the HTML node
+"""
+
+from langchain_community.document_loaders import AsyncHtmlLoader
+from .base_node import BaseNode
+
+
+class FetchHTMLNode(BaseNode):
+    """
+    A node responsible for fetching the HTML content of a specified URL and updating
+    the graph's state with this content. It uses the AsyncHtmlLoader for asynchronous
+    document loading.
+
+    This node acts as a starting point in many scraping workflows, preparing the state
+    with the necessary HTML content for further processing by subsequent nodes in the graph.
+
+    Attributes:
+        node_name (str): The unique identifier name for the node.
+        node_type (str): The type of the node, defaulting to "node". This categorization
+                         helps in determining the node's role and behavior within the graph.
+                         The "node" type is used for standard operational nodes.
+
+    Args:
+        node_name (str): The unique identifier name for the node. This name is used to
+                         reference the node within the graph.
+        node_type (str, optional): The type of the node, limited to "node" or
+                                   "conditional_node". Defaults to "node".
+
+    Methods:
+        execute(state): Fetches the HTML content for the URL specified in the state and
+                        updates the state with this content under the 'document' key.
+                        The 'url' key must be present in the state for the operation
+                        to succeed.
+    """
+
+    def __init__(self, node_name: str, node_type: str = "node"):
+        """
+        Initializes the FetchHTMLNode with a node name and node type.
+        """
+        super().__init__(node_name, node_type)
+
+    def execute(self, state: dict) -> dict:
+        """
+        Executes the node's logic to fetch HTML content from a specified URL and
+        update the state with this content.
+
+        Args:
+            state (dict): The current state of the graph, expected to contain a 'url' key.
+
+        Returns:
+            dict: The updated state with a new 'document' key containing the fetched HTML content.
+
+        Raises:
+            KeyError: If the 'url' key is not found in the state, indicating that the
+                      necessary information to perform the operation is missing.
+        """
+        try:
+            url = state["keys"]["url"]
+        except KeyError as e:
+            print(f"Error: {e} not found in state.")
+            raise
+        loader = AsyncHtmlLoader(url)
+        document = loader.load()
+        state["keys"]["document"] = document
+
+        return state

scrapegraphai/nodes/generate_answer_node.py

@@ -0,0 +1,100 @@
+"""
+Module for generating the answer node
+"""
+from langchain_core.output_parsers import JsonOutputParser
+from langchain.prompts import PromptTemplate
+from .base_node import BaseNode
+
+
+class GenerateAnswerNode(BaseNode):
+    """
+    A node that generates an answer using a language model (LLM) based on the user's input
+    and the content extracted from a webpage. It constructs a prompt from the user's input
+    and the scraped content, feeds it to the LLM, and parses the LLM's response to produce
+    an answer.
+
+    Attributes:
+        llm (ChatOpenAI): An instance of a language model client, configured for generating answers.
+        node_name (str): The unique identifier name for the node, defaulting 
+        to "GenerateAnswerNode".
+        node_type (str): The type of the node, set to "node" indicating a 
+        standard operational node.
+
+    Args:
+        llm: An instance of the language model client (e.g., ChatOpenAI) used 
+        for generating answers.
+        node_name (str, optional): The unique identifier name for the node. 
+        Defaults to "GenerateAnswerNode".
+
+    Methods:
+        execute(state): Processes the input and document from the state to generate an answer,
+                        updating the state with the generated answer under the 'answer' key.
+    """
+
+    def __init__(self, llm, node_name: str = "GenerateAnswerNode"):
+        """
+        Initializes the GenerateAnswerNode with a language model client and a node name.
+        """
+        super().__init__(node_name, "node")
+        self.llm = llm
+
+    def execute(self, state: dict) -> dict:
+        """
+        Generates an answer by constructing a prompt from the user's input and the scraped
+        content, querying the language model, and parsing its response.
+
+        The method updates the state with the generated answer under the 'answer' key.
+
+        Args:
+            state (dict): The current state of the graph, expected to contain 'user_input',
+                          and optionally 'parsed_document' or 'relevant_chunks' within 'keys'.
+
+        Returns:
+            dict: The updated state with the 'answer' key containing the generated answer.
+
+        Raises:
+            KeyError: If 'user_input' or 'document' is not found in the state, indicating
+                      that the necessary information for generating an answer is missing.
+        """
+
+        print("---GENERATE ANSWER---")
+        try:
+            user_input = state["keys"]["user_input"]
+            document = state["keys"]["document"]
+        except KeyError as e:
+            print(f"Error: {e} not found in state.")
+            raise
+
+        parsed_document = state["keys"].get("parsed_document", None)
+        relevant_chunks = state["keys"].get("relevant_chunks", None)
+
+        if relevant_chunks:
+            context = relevant_chunks
+        elif parsed_document:
+            context = parsed_document
+        else:
+            context = document
+
+        output_parser = JsonOutputParser()
+        format_instructions = output_parser.get_format_instructions()
+
+        template = """You are a website scraper and you have just scraped the
+        following content from a website.
+         You are now asked to answer a question about the content you have scraped.\n {format_instructions} \n The content is as follows: {context}
+        Question: {question}
+                """
+
+        schema_prompt = PromptTemplate(
+            template=template,
+            input_variables=["context", "question"],
+            partial_variables={"format_instructions": format_instructions},
+        )
+
+        # Chain
+        schema_chain = schema_prompt | self.llm | output_parser
+        answer = schema_chain.invoke(
+            {"context": context, "question": user_input})
+
+        # Update the state with the generated answer
+        state["keys"].update({"answer": answer})
+        return state

scrapegraphai/nodes/get_probable_tags_node.py

@@ -0,0 +1,88 @@
+"""
+Module for proobable tags
+"""
+from langchain.output_parsers import CommaSeparatedListOutputParser
+from langchain.prompts import PromptTemplate
+from .base_node import BaseNode
+
+
+class GetProbableTagsNode(BaseNode):
+    """
+    A node that utilizes a language model to identify probable HTML tags within a document that 
+    are likely to contain the information relevant to a user's query. This node generates a prompt
+    describing the task, submits it to the language model, and processes the output to produce a 
+    list of probable tags.
+
+    Attributes:
+        llm: An instance of a language model client, configured for generating tag predictions.
+        node_name (str): The unique identifier name for the node,
+        defaulting to "GetProbableTagsNode".
+        node_type (str): The type of the node, set to "node" indicating a standard operational node.
+
+    Args:
+        llm: An instance of the language model client (e.g., ChatOpenAI) used for tag predictions.
+        node_name (str, optional): The unique identifier name for the node. 
+        Defaults to "GetProbableTagsNode".
+
+    Methods:
+        execute(state): Processes the user's input and the URL from the state to generate a list of 
+                        probable HTML tags, updating the state with these tags under the 'tags' key.
+    """
+
+    def __init__(self, llm, node_name: str = "GetProbableTagsNode"):
+        """
+        Initializes the GetProbableTagsNode with a language model client and a node name.
+        """
+        super().__init__(node_name, "node")
+        self.llm = llm
+
+    def execute(self, state: dict):
+        """
+        Generates a list of probable HTML tags based on the user's input and updates the state 
+        with this list. The method constructs a prompt for the language model, submits it, and 
+        parses the output to identify probable tags.
+
+        Args:
+            state (dict): The current state of the graph, expected to contain 'user_input', 'url',
+                          and optionally 'document' within 'keys'.
+
+        Returns:
+            dict: The updated state with the 'tags' key containing a list of probable HTML tags.
+
+        Raises:
+            KeyError: If 'user_input' or 'url' is not found in the state, indicating that the
+                      necessary information for generating tag predictions is missing.
+        """
+
+        print("---GET PROBABLE TAGS---")
+        try:
+            user_input = state["keys"]["user_input"]
+            url = state["keys"]["url"]
+        except KeyError as e:
+            print(f"Error: {e} not found in state.")
+            raise
+
+        output_parser = CommaSeparatedListOutputParser()
+        format_instructions = output_parser.get_format_instructions()
+
+        template = """You are a website scraper that knows all the types of html tags.
+         You are now asked to list all the html tags where you think you can find the information of the asked question.\n 
+         {format_instructions} \n  The webpage is: {webpage} \n The asked question is the following: {question}
+        """
+
+        tag_prompt = PromptTemplate(
+            template=template,
+            input_variables=["question"],
+            partial_variables={
+                "format_instructions": format_instructions, "webpage": url},
+        )
+
+        # Execute the chain to get probable tags
+        tag_answer = tag_prompt | self.llm | output_parser
+        probable_tags = tag_answer.invoke({"question": user_input})
+
+        print("Possible tags: ", *probable_tags)
+
+        # Update the nested 'keys' dictionary with probable tags
+        state["keys"].update({"tags": probable_tags})
+        return state

scrapegraphai/nodes/parse_html_node.py

@@ -0,0 +1,74 @@
+"""
+Module for parsing the HTML node
+"""
+from langchain_community.document_transformers import BeautifulSoupTransformer
+from .base_node import BaseNode
+
+
+class ParseHTMLNode(BaseNode):
+    """
+    A node responsible for parsing HTML content from a document using specified tags. 
+    It uses BeautifulSoupTransformer for parsing, providing flexibility in extracting
+    specific parts of an HTML document based on the tags provided in the state.
+
+    This node enhances the scraping workflow by allowing for targeted extraction of 
+    content, thereby optimizing the processing of large HTML documents.
+
+    Attributes:
+        node_name (str): The unique identifier name for the node, defaulting to "ParseHTMLNode".
+        node_type (str): The type of the node, set to "node" indicating a standard operational node.
+
+    Args:
+        node_name (str, optional): The unique identifier name for the node. 
+        Defaults to "ParseHTMLNode".
+
+    Methods:
+        execute(state): Parses the HTML document contained within the state using 
+        the specified tags, if provided, and updates the state with the parsed content.
+    """
+
+    def __init__(self, node_name="ParseHTMLNode"):
+        """
+        Initializes the ParseHTMLNode with a node name.
+        """
+        super().__init__(node_name, "node")
+
+    def execute(self, state):
+        """
+        Executes the node's logic to parse the HTML document based on specified tags. 
+        If tags are provided in the state, the document is parsed accordingly; otherwise, 
+        the document remains unchanged. The method updates the state with either the original 
+        or parsed document under the 'parsed_document' key.
+
+        Args:
+            state (dict): The current state of the graph, expected to contain 
+            'document' within 'keys', and optionally 'tags' for targeted parsing.
+
+        Returns:
+            dict: The updated state with the 'parsed_document' key containing the parsed content,
+                  if tags were provided, or the original document otherwise.
+
+        Raises:
+            KeyError: If 'document' is not found in the state, indicating that the necessary 
+                      information for parsing is missing.
+        """
+
+        print("---PARSE HTML DOCUMENT---")
+        try:
+            document = state["keys"]["document"]
+        except KeyError as e:
+            print(f"Error: {e} not found in state.")
+            raise
+
+        tags = state["keys"].get("tags", None)
+
+        if not tags:
+            print("No specific tags provided; returning document as is.")
+            return state
+
+        bs_transformer = BeautifulSoupTransformer()
+        parsed_document = bs_transformer.transform_documents(
+            document, tags_to_extract=tags)
+        print("Document parsed with specified tags.")
+        state["keys"].update({"parsed_document": parsed_document})
+        return state

scrapegraphai/utils/convert_to_csv.py

@@ -0,0 +1,36 @@
+"""
+Module that given a filename and a position saves the file in the csv format
+"""
+import os
+import pandas as pd
+
+
+def convert_to_csv(data: dict, filename: str, position: str):
+    """
+    Convert data to JSON format and save it to a file.
+
+    Args:
+        data (dict): Data to save.
+        filename (str): Name of the file to save without .csv extension.
+        position (str): Directory where the file should be saved.
+
+    Raises:
+        ValueError: If filename contains '.csv'.
+        FileNotFoundError: If the specified directory does not exist.
+        PermissionError: If the program does not have permission to write to the directory.
+    """
+    if ".csv" in filename:
+        raise ValueError("The filename should not contain '.csv'")
+
+    try:
+        os.makedirs(position, exist_ok=True)
+        pd.DataFrame.from_dict(data, orient='index').to_csv(
+            os.path.join(position, f"{filename}.csv"), index=False)
+    except FileNotFoundError as fnfe:
+        raise FileNotFoundError(
+            f"The specified directory '{position}' does not exist.") from fnfe
+    except PermissionError as pe:
+        raise PermissionError(
+            f"You don't have permission to write to '{position}'.") from pe
+    except Exception as e:
+        raise e

scrapegraphai/utils/convert_to_json.py

@@ -0,0 +1,36 @@
+"""
+Module that given a filename and a position saves the file in the json format
+"""
+import json
+import os
+
+
+def convert_to_json(data: dict, filename: str, position: str):
+    """
+    Convert data to CSV format and save it to a file.
+
+    Args:
+        data (dict): Data to save.
+        filename (str): Name of the file to save without .json extension.
+        position (str): Directory where the file should be saved.
+
+    Raises:
+        ValueError: If filename contains '.json'.
+        FileNotFoundError: If the specified directory does not exist.
+        PermissionError: If the program does not have permission to write to the directory.
+    """
+    if ".json" in filename:
+        raise ValueError("The filename should not contain '.json'")
+
+    try:
+        os.makedirs(position, exist_ok=True)
+        with open(os.path.join(position, f"{filename}.json"), "w", encoding="utf-8") as f:
+            f.write(json.dumps(data))
+    except FileNotFoundError as fnfe:
+        raise FileNotFoundError(
+            f"The specified directory '{position}' does not exist.") from fnfe
+    except PermissionError as pe:
+        raise PermissionError(
+            f"You don't have permission to write to '{position}'.") from pe
+    except Exception as e:
+        raise e

scrapegraphai/utils/getter.py

@@ -0,0 +1,18 @@
+"""
+Module for retrieving content from a URL
+"""
+from langchain_community.document_loaders import AsyncHtmlLoader
+
+
+def _get_function(link: str) -> str:
+    """
+    It sends a GET request to the specified link with optional headers.
+
+    Args:
+        link (str): The URL to send the GET request to.
+
+    Returns:
+        str: The content of the response as a string.
+    """
+    loader = AsyncHtmlLoader(link)
+    return str(loader.load())

scrapegraphai/utils/remover.py

@@ -0,0 +1,40 @@
+"""
+Module for removing the unused html tags
+"""
+
+
+def remover(file: str, only_body: bool = False) -> str:
+    """
+    This function elaborates the HTML file and remove all the not necessary tag
+
+    Parameters:
+        file (str): the file to parse
+
+    Returns:
+        str: the parsed file
+    """
+
+    res = ""
+
+    if only_body:
+        is_body = True
+    else:
+        is_body = False
+
+    for elem in file.splitlines():
+        if "<title>" in elem:
+            res = res + elem
+
+        if "<body>" in elem:
+            is_body = True
+
+        if "</body>" in elem:
+            break
+
+        if "<script>" in elem:
+            continue
+
+        if is_body:
+            res = res + elem
+
+    return res.replace("\\n", "")

scrapegraphai/utils/token_calculator.py

@@ -0,0 +1,31 @@
+""" 
+Module for truncatinh in chunks the messages
+"""
+from typing import List
+import tiktoken
+from .info.dictionaries import models_tokens
+
+
+def truncate_text_tokens(text: str, model: str, encoding_name: str) -> List[str]:
+    """
+    It creates a list of strings to create max dimension tokenizable elements
+
+    Args:
+        text (str): The input text to be truncated into tokenizable elements.
+        model (str): The name of the language model to be used.
+        encoding_name (str): The name of the encoding to be used (default: EMBEDDING_ENCODING).
+
+    Returns:
+        List[str]: A list of tokenizable elements created from the input text.
+    """
+
+    encoding = tiktoken.get_encoding(encoding_name)
+    max_tokens = models_tokens[model] - 500
+    encoded_text = encoding.encode(text)
+
+    chunks = [encoded_text[i:i + max_tokens]
+              for i in range(0, len(encoded_text), max_tokens)]
+
+    result = [encoding.decode(chunk) for chunk in chunks]
+
+    return result

scrapegraphai-0.0.1.dist-info/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.dist-info/METADATA

@@ -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.dist-info/RECORD

@@ -0,0 +1,21 @@
+scrapegraphai/__init__.py,sha256=tdcyvY2aV8oK3-PzGgX5GN_ZtTA3Eg7EKWf-Rsv_8N0,57
+scrapegraphai/graphs/__init__.py,sha256=YABWf6FCiDmGt__zr-oyJzJYkpBMr3oSWxIbSan9MKk,129
+scrapegraphai/graphs/base_graph.py,sha256=9xIH04Xfgnn88cpCcO1ltrSwsGN_OOVnWpD7G6v16pA,3117
+scrapegraphai/graphs/smart_scraper_graph.py,sha256=GQhntpolTwQn5ydBYJbtKbCm5wHtVxB0dEePh-ZVZIQ,4358
+scrapegraphai/info/dictionaries.py,sha256=p17RcmLht6FjzGps3sBD7-ROQQ5UhmHhY50MbLSr69g,1216
+scrapegraphai/nodes/__init__.py,sha256=awtwOn83YSlK5ZGiw0LplYPJAO3tUNSIi4UCdbkOn2k,292
+scrapegraphai/nodes/base_node.py,sha256=rdVCCno-0Rp7t5TUqt8usRjyp_xeIeywxLmzBP7ggjo,2732
+scrapegraphai/nodes/conditional_node.py,sha256=dnGSHm9SzJkOisCs9a80fTBPS8_rFG_UT4RVy9M4A0s,3006
+scrapegraphai/nodes/fetch_html_node.py,sha256=8lhG25E9_KOmdR07HzBJUeApy1PcmPzXKWytkpx2v-A,2698
+scrapegraphai/nodes/generate_answer_node.py,sha256=_aCkakZlO3kr6aETlb3GoCEoe8XBP21WXHv-y5U_av8,4002
+scrapegraphai/nodes/get_probable_tags_node.py,sha256=Mkm6BrDCHB-1uvAGfpctIF7dXdRP-adBRKup_g4aMVM,3775
+scrapegraphai/nodes/parse_html_node.py,sha256=dH0OXLk1G7GBdKqJp6HwFM5js6WOHPmLF_04Udgei8w,2990
+scrapegraphai/utils/convert_to_csv.py,sha256=vn1PvKW3TaZexO0OsSVWcG39ucl3y7T_rQN0BzXH8W0,1307
+scrapegraphai/utils/convert_to_json.py,sha256=o2M1yTdGyHfimKKY2mNSa05wqEb6g1YsfdFzqDm_QRA,1304
+scrapegraphai/utils/getter.py,sha256=yufZ-jkPvGMpJKpKfLHyxX4osqcMzSRDhiaqA9tgqwY,459
+scrapegraphai/utils/remover.py,sha256=FYjYciow-tMRHIvLV_3ebgCjCF2qwVJeWb2On6GCjqc,770
+scrapegraphai/utils/token_calculator.py,sha256=Yep-MJ7nYsWZGWhrPn2aSJuH-KPB5NAP3y9XyhTIJOw,1016
+scrapegraphai-0.0.1.dist-info/LICENSE,sha256=0e0T0fhnrfvsU9jAvrmSPCXQPFG3uxnb0T4az_WUz5s,11138
+scrapegraphai-0.0.1.dist-info/METADATA,sha256=s3qwNz8g8NUq1bSmWoTgjr1p37Bbc2wzexdaGYMEV48,4914
+scrapegraphai-0.0.1.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
+scrapegraphai-0.0.1.dist-info/RECORD,,

scrapegraphai-0.0.1.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: poetry-core 1.8.1
+Root-Is-Purelib: true
+Tag: py3-none-any