mirror of
https://github.com/VinciGit00/Scrapegraph-ai.git
synced 2026-06-12 21:01:54 +08:00
99 lines
3.2 KiB
Python
99 lines
3.2 KiB
Python
"""
|
|
XMLScraperGraph Module
|
|
"""
|
|
|
|
from typing import Optional, Type
|
|
|
|
from pydantic import BaseModel
|
|
|
|
from ..nodes import FetchNode, GenerateAnswerNode
|
|
from .abstract_graph import AbstractGraph
|
|
from .base_graph import BaseGraph
|
|
|
|
|
|
class XMLScraperGraph(AbstractGraph):
|
|
"""
|
|
XMLScraperGraph is a scraping pipeline that extracts information from XML files using a natural
|
|
language model to interpret and answer prompts.
|
|
|
|
Attributes:
|
|
prompt (str): The prompt for the graph.
|
|
source (str): The source of the graph.
|
|
config (dict): Configuration parameters for the graph.
|
|
schema (BaseModel): The schema for the graph output.
|
|
llm_model: An instance of a language model client, configured for generating answers.
|
|
embedder_model: An instance of an embedding model client,
|
|
configured for generating embeddings.
|
|
verbose (bool): A flag indicating whether to show print statements during execution.
|
|
headless (bool): A flag indicating whether to run the graph in headless mode.
|
|
model_token (int): The token limit for the language model.
|
|
|
|
Args:
|
|
prompt (str): The prompt for the graph.
|
|
source (str): The source of the graph.
|
|
config (dict): Configuration parameters for the graph.
|
|
schema (BaseModel): The schema for the graph output.
|
|
|
|
Example:
|
|
>>> xml_scraper = XMLScraperGraph(
|
|
... "List me all the attractions in Chioggia.",
|
|
... "data/chioggia.xml",
|
|
... {"llm": {"model": "openai/gpt-3.5-turbo"}}
|
|
... )
|
|
>>> result = xml_scraper.run()
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
prompt: str,
|
|
source: str,
|
|
config: dict,
|
|
schema: Optional[Type[BaseModel]] = None,
|
|
):
|
|
super().__init__(prompt, config, source, schema)
|
|
|
|
self.input_key = "xml" if source.endswith("xml") else "xml_dir"
|
|
|
|
def _create_graph(self) -> BaseGraph:
|
|
"""
|
|
Creates the graph of nodes representing the workflow for web scraping.
|
|
|
|
Returns:
|
|
BaseGraph: A graph instance representing the web scraping workflow.
|
|
"""
|
|
|
|
fetch_node = FetchNode(input="xml | xml_dir", output=["doc"])
|
|
|
|
generate_answer_node = GenerateAnswerNode(
|
|
input="user_prompt & (relevant_chunks | doc)",
|
|
output=["answer"],
|
|
node_config={
|
|
"llm_model": self.llm_model,
|
|
"additional_info": self.config.get("additional_info"),
|
|
"schema": self.schema,
|
|
},
|
|
)
|
|
|
|
return BaseGraph(
|
|
nodes=[
|
|
fetch_node,
|
|
generate_answer_node,
|
|
],
|
|
edges=[(fetch_node, generate_answer_node)],
|
|
entry_point=fetch_node,
|
|
graph_name=self.__class__.__name__,
|
|
)
|
|
|
|
def run(self) -> str:
|
|
"""
|
|
Executes the web scraping process and returns the answer to the prompt.
|
|
|
|
Returns:
|
|
str: The answer to the prompt.
|
|
"""
|
|
|
|
inputs = {"user_prompt": self.prompt, self.input_key: self.source}
|
|
self.final_state, self.execution_info = self.graph.execute(inputs)
|
|
|
|
return self.final_state.get("answer", "No answer found.")
|