chore: import upstream snapshot with attribution
CodeQL / Analyze (python) (push) Failing after 0s
Release / Build (push) Failing after 1s
Test Suite / Unit Tests (push) Failing after 0s
Release / Release (push) Has been cancelled

This commit is contained in:
wehub-resource-sync
2026-07-13 12:18:10 +08:00
commit fbfefa28d3
384 changed files with 46941 additions and 0 deletions
@@ -0,0 +1,57 @@
"""
Basic example of scraping pipeline using ScriptCreatorGraph
"""
import os
from dotenv import load_dotenv
from scrapegraphai.graphs import ScriptCreatorMultiGraph
from scrapegraphai.utils import prettify_exec_info
load_dotenv()
# ************************************************
# Define the configuration for the graph
# ************************************************
openai_key = os.getenv("OPENAI_APIKEY")
graph_config = {
"llm": {
"api_key": openai_key,
"model": "openai/gpt-4o",
},
"library": "beautifulsoup",
"verbose": True,
}
# ************************************************
# Create the ScriptCreatorGraph instance and run it
# ************************************************
urls = [
"https://schultzbergagency.com/emil-raste-karlsen/",
"https://schultzbergagency.com/johanna-hedberg/",
]
# ************************************************
# Create the ScriptCreatorGraph instance and run it
# ************************************************
script_creator_graph = ScriptCreatorMultiGraph(
prompt="Find information about actors",
# also accepts a string with the already downloaded HTML code
source=urls,
config=graph_config,
)
result = script_creator_graph.run()
print(result)
# ************************************************
# Get graph execution info
# ************************************************
graph_exec_info = script_creator_graph.get_execution_info()
print(prettify_exec_info(graph_exec_info))
@@ -0,0 +1,49 @@
"""
Basic example of scraping pipeline using SmartScraper
"""
import json
import os
from dotenv import load_dotenv
from scrapegraphai.graphs import ScriptCreatorGraph
from scrapegraphai.utils import prettify_exec_info
load_dotenv()
# ************************************************
# Define the configuration for the graph
# ************************************************
graph_config = {
"llm": {
"api_key": os.getenv("OPENAI_API_KEY"),
"model": "openai/gpt-4o",
},
"library": "beautifulsoup",
"verbose": True,
"headless": False,
}
# ************************************************
# Create the SmartScraperGraph instance and run it
# ************************************************
smart_scraper_graph = ScriptCreatorGraph(
prompt="List me all the news with their description.",
# also accepts a string with the already downloaded HTML code
source="https://perinim.github.io/projects",
config=graph_config,
)
result = smart_scraper_graph.run()
print(json.dumps(result, indent=4))
# ************************************************
# Get graph execution info
# ************************************************
graph_exec_info = smart_scraper_graph.get_execution_info()
print(prettify_exec_info(graph_exec_info))
@@ -0,0 +1,62 @@
"""
Basic example of scraping pipeline using ScriptCreatorGraph
"""
import os
from typing import List
from dotenv import load_dotenv
from pydantic import BaseModel, Field
from scrapegraphai.graphs import ScriptCreatorGraph
from scrapegraphai.utils import prettify_exec_info
load_dotenv()
# ************************************************
# Define the schema for the graph
# ************************************************
class Project(BaseModel):
title: str = Field(description="The title of the project")
description: str = Field(description="The description of the project")
class Projects(BaseModel):
projects: List[Project]
# ************************************************
# Define the configuration for the graph
# ************************************************
openai_key = os.getenv("OPENAI_APIKEY")
graph_config = {
"llm": {"api_key": openai_key, "model": "openai/gpt-4o"},
"library": "beautifulsoup",
"verbose": True,
}
# ************************************************
# Create the ScriptCreatorGraph instance and run it
# ************************************************
script_creator_graph = ScriptCreatorGraph(
prompt="List me all the projects with their description.",
# also accepts a string with the already downloaded HTML code
source="https://perinim.github.io/projects",
config=graph_config,
schema=Projects,
)
result = script_creator_graph.run()
print(result)
# ************************************************
# Get graph execution info
# ************************************************
graph_exec_info = script_creator_graph.get_execution_info()
print(prettify_exec_info(graph_exec_info))