fix: formatting

ScrapeGraphAI · Dec 11, 2024 · d1b2104 · d1b2104
1 parent bae92b0
commit d1b2104
Show file tree

Hide file tree

Showing 14 changed files with 14 additions and 38 deletions.
diff --git a/scrapegraphai/graphs/base_graph.py b/scrapegraphai/graphs/base_graph.py
@@ -56,13 +56,11 @@ def __init__(self, nodes: list, edges: list, entry_point: str,
         self.callback_manager = CustomLLMCallbackManager()
 
         if nodes[0].node_name != entry_point.node_name:
-            # raise a warning if the entry point is not the first node in the list
             warnings.warn(
                 "Careful! The entry point node is different from the first node in the graph.")
 
         self._set_conditional_node_edges()
 
-        # Burr configuration
         self.use_burr = use_burr
         self.burr_config = burr_config or {}
 
@@ -91,7 +89,8 @@ def _set_conditional_node_edges(self):
             if node.node_type == 'conditional_node':
                 outgoing_edges = [(from_node, to_node) for from_node, to_node in self.raw_edges if from_node.node_name == node.node_name]
                 if len(outgoing_edges) != 2:
-                    raise ValueError(f"ConditionalNode '{node.node_name}' must have exactly two outgoing edges.")
+                    raise ValueError(f"""ConditionalNode '{node.node_name}'
+                                     must have exactly two outgoing edges.""")
                 node.true_node_name = outgoing_edges[0][1].node_name
                 try:
                     node.false_node_name = outgoing_edges[1][1].node_name
@@ -151,14 +150,14 @@ def _get_schema(self, current_node):
         """Extracts schema information from the node configuration."""
         if not hasattr(current_node, "node_config"):
             return None
-            
+
         if not isinstance(current_node.node_config, dict):
             return None
-            
+
         schema_config = current_node.node_config.get("schema")
         if not schema_config or isinstance(schema_config, dict):
             return None
-            
+
         try:
             return schema_config.schema()
         except Exception:
@@ -167,7 +166,7 @@ def _get_schema(self, current_node):
     def _execute_node(self, current_node, state, llm_model, llm_model_name):
         """Executes a single node and returns execution information."""
         curr_time = time.time()
-        
+
         with self.callback_manager.exclusive_get_callback(llm_model, llm_model_name) as cb:
             result = current_node.execute(state)
             node_exec_time = time.time() - curr_time
@@ -197,17 +196,17 @@ def _get_next_node(self, current_node, result):
             raise ValueError(
                 f"Conditional Node returned a node name '{result}' that does not exist in the graph"
             )
-        
+
         return self.edges.get(current_node.node_name)
 
     def _execute_standard(self, initial_state: dict) -> Tuple[dict, list]:
         """
-        Executes the graph by traversing nodes starting from the entry point using the standard method.
+        Executes the graph by traversing nodes
+        starting from the entry point using the standard method.
         """
         current_node_name = self.entry_point
         state = initial_state
-
-        # Tracking variables
+
         total_exec_time = 0.0
         exec_info = []
         cb_total = {
@@ -230,16 +229,13 @@ def _execute_standard(self, initial_state: dict) -> Tuple[dict, list]:
 
         while current_node_name:
             current_node = self._get_node_by_name(current_node_name)
-
-            # Update source information if needed
+
             if source_type is None:
                 source_type, source, prompt = self._update_source_info(current_node, state)
-
-            # Get model information if needed
+
             if llm_model is None:
                 llm_model, llm_model_name, embedder_model = self._get_model_info(current_node)
-
-            # Get schema if needed
+
             if schema is None:
                 schema = self._get_schema(current_node)
 
@@ -273,7 +269,6 @@ def _execute_standard(self, initial_state: dict) -> Tuple[dict, list]:
                 )
                 raise e
 
-        # Add total results to execution info
         exec_info.append({
             "node_name": "TOTAL RESULT",
             "total_tokens": cb_total["total_tokens"],
@@ -284,7 +279,6 @@ def _execute_standard(self, initial_state: dict) -> Tuple[dict, list]:
             "exec_time": total_exec_time,
         })
 
-        # Log final execution results
         graph_execution_time = time.time() - start_time
         response = state.get("answer", None) if source_type == "url" else None
         content = state.get("parsed_doc", None) if response is not None else None
@@ -343,4 +337,3 @@ def append_node(self, node):
         self.raw_edges.append((last_node, node))
         self.nodes.append(node)
         self.edges = self._create_edges({e for e in self.raw_edges})
-
diff --git a/scrapegraphai/graphs/code_generator_graph.py b/scrapegraphai/graphs/code_generator_graph.py
@@ -17,7 +17,6 @@
     GenerateCodeNode,
 )
 
-
 class CodeGeneratorGraph(AbstractGraph):
     """
     CodeGeneratorGraph is a script generator pipeline that generates

diff --git a/scrapegraphai/graphs/csv_scraper_graph.py b/scrapegraphai/graphs/csv_scraper_graph.py
@@ -59,7 +59,7 @@ def _create_graph(self):
         """
         Creates the graph of nodes representing the workflow for web scraping.
         """
-    
+
         fetch_node = FetchNode(
             input="csv | csv_dir",
             output=["doc"],

diff --git a/scrapegraphai/graphs/depth_search_graph.py b/scrapegraphai/graphs/depth_search_graph.py
@@ -15,7 +15,6 @@
     GenerateAnswerNodeKLevel,
 )
 
-
 class DepthSearchGraph(AbstractGraph):
     """
     CodeGeneratorGraph is a script generator pipeline that generates

diff --git a/scrapegraphai/graphs/document_scraper_graph.py b/scrapegraphai/graphs/document_scraper_graph.py
@@ -9,7 +9,6 @@
 from .abstract_graph import AbstractGraph
 from ..nodes import FetchNode, ParseNode, GenerateAnswerNode
 
-
 class DocumentScraperGraph(AbstractGraph):
     """
     DocumentScraperGraph is a scraping pipeline that automates the process of

diff --git a/scrapegraphai/graphs/omni_scraper_graph.py b/scrapegraphai/graphs/omni_scraper_graph.py
@@ -9,7 +9,6 @@
 from ..nodes import FetchNode, ParseNode, ImageToTextNode, GenerateAnswerOmniNode
 from ..models import OpenAIImageToText
 
-
 class OmniScraperGraph(AbstractGraph):
     """
     OmniScraper is a scraping pipeline that automates the process of

diff --git a/scrapegraphai/graphs/script_creator_graph.py b/scrapegraphai/graphs/script_creator_graph.py
@@ -1,14 +1,12 @@
 """
 ScriptCreatorGraph Module
 """
-
 from typing import Optional
 from pydantic import BaseModel
 from .base_graph import BaseGraph
 from .abstract_graph import AbstractGraph
 from ..nodes import FetchNode, ParseNode, GenerateScraperNode
 
-
 class ScriptCreatorGraph(AbstractGraph):
     """
     ScriptCreatorGraph defines a scraping pipeline for generating web scraping scripts.

diff --git a/scrapegraphai/graphs/search_graph.py b/scrapegraphai/graphs/search_graph.py
@@ -1,7 +1,6 @@
 """
 SearchGraph Module
 """
-
 from copy import deepcopy
 from typing import Optional, List
 from pydantic import BaseModel

diff --git a/scrapegraphai/graphs/search_link_graph.py b/scrapegraphai/graphs/search_link_graph.py
@@ -1,15 +1,13 @@
 """
 SearchLinkGraph Module
 """
-
 from typing import Optional
 import logging
 from pydantic import BaseModel
 from .base_graph import BaseGraph
 from .abstract_graph import AbstractGraph
 from ..nodes import FetchNode, SearchLinkNode, SearchLinksWithContext
 
-
 class SearchLinkGraph(AbstractGraph):
     """
     SearchLinkGraph is a scraping pipeline that automates the process of

diff --git a/scrapegraphai/graphs/smart_scraper_graph.py b/scrapegraphai/graphs/smart_scraper_graph.py
@@ -1,7 +1,6 @@
 """
 SmartScraperGraph Module
 """
-
 from typing import Optional
 from pydantic import BaseModel
 from scrapegraph_py import Client

diff --git a/scrapegraphai/graphs/smart_scraper_lite_graph.py b/scrapegraphai/graphs/smart_scraper_lite_graph.py
@@ -1,7 +1,6 @@
 """
 SmartScraperGraph Module
 """
-
 from typing import Optional
 from pydantic import BaseModel
 from .base_graph import BaseGraph
@@ -11,7 +10,6 @@
     ParseNode,
 )
 
-
 class SmartScraperLiteGraph(AbstractGraph):
     """
     SmartScraperLiteGraph is a scraping pipeline that automates the process of

diff --git a/scrapegraphai/graphs/speech_graph.py b/scrapegraphai/graphs/speech_graph.py
@@ -1,7 +1,6 @@
 """
 SpeechGraph Module
 """
-
 from typing import Optional
 from pydantic import BaseModel
 from .base_graph import BaseGraph
@@ -15,7 +14,6 @@
 from ..utils.save_audio_from_bytes import save_audio_from_bytes
 from ..models import OpenAITextToSpeech
 
-
 class SpeechGraph(AbstractGraph):
     """
     SpeechyGraph is a scraping pipeline that scrapes the web, provide an answer

diff --git a/scrapegraphai/nodes/fetch_node.py b/scrapegraphai/nodes/fetch_node.py
@@ -1,7 +1,6 @@
 """
 FetchNode Module
 """
-
 import json
 from typing import List, Optional
 from langchain_openai import ChatOpenAI, AzureChatOpenAI
@@ -15,7 +14,6 @@
 from ..utils.logging import get_logger
 from .base_node import BaseNode
 
-
 class FetchNode(BaseNode):
     """
     A node responsible for fetching the HTML content of a specified URL and updating

diff --git a/scrapegraphai/nodes/fetch_node_level_k.py b/scrapegraphai/nodes/fetch_node_level_k.py
@@ -1,7 +1,6 @@
 """
 fetch_node_level_k module
 """
-
 from typing import List, Optional
 from urllib.parse import urljoin
 from langchain_core.documents import Document
-Original file line number
+Diff line change
@@ Expand Up / @@ -17,7 +17,6 @@ @@
         GenerateCodeNode,
     )
     class CodeGeneratorGraph(AbstractGraph):
         """
         CodeGeneratorGraph is a script generator pipeline that generates
@@ Expand Down @@