chore: import upstream snapshot with attribution
This commit is contained in:
@@ -0,0 +1,11 @@
|
||||
# OpenAI API Configuration
|
||||
OPENAI_API_KEY=your-openai-api-key-here
|
||||
|
||||
# Optional Configurations
|
||||
MAX_TOKENS=4000
|
||||
MODEL_NAME=gpt-4-1106-preview
|
||||
TEMPERATURE=0.7
|
||||
|
||||
# CSV Scraper Settings
|
||||
CSV_DELIMITER=,
|
||||
MAX_ROWS=1000
|
||||
@@ -0,0 +1,30 @@
|
||||
# CSV Scraper Graph Example
|
||||
|
||||
This example demonstrates how to use Scrapegraph-ai to extract data from web sources and save it in CSV format.
|
||||
|
||||
## Features
|
||||
|
||||
- Table data extraction
|
||||
- CSV formatting
|
||||
- Data cleaning
|
||||
- Structured output
|
||||
|
||||
## Setup
|
||||
|
||||
1. Install required dependencies
|
||||
2. Copy `.env.example` to `.env`
|
||||
3. Configure your API keys in the `.env` file
|
||||
|
||||
## Usage
|
||||
|
||||
```python
|
||||
from scrapegraphai.graphs import CsvScraperGraph
|
||||
|
||||
graph = CsvScraperGraph()
|
||||
csv_data = graph.scrape("https://example.com/table")
|
||||
```
|
||||
|
||||
## Environment Variables
|
||||
|
||||
Required environment variables:
|
||||
- `OPENAI_API_KEY`: Your OpenAI API key
|
||||
@@ -0,0 +1,59 @@
|
||||
"""
|
||||
Basic example of scraping pipeline using CSVScraperMultiGraph from CSV documents
|
||||
"""
|
||||
|
||||
import os
|
||||
|
||||
from scrapegraphai.graphs import CSVScraperMultiGraph
|
||||
from scrapegraphai.utils import prettify_exec_info
|
||||
|
||||
# ************************************************
|
||||
# Read the CSV file
|
||||
# ************************************************
|
||||
|
||||
FILE_NAME = "inputs/username.csv"
|
||||
curr_dir = os.path.dirname(os.path.realpath(__file__))
|
||||
file_path = os.path.join(curr_dir, FILE_NAME)
|
||||
|
||||
with open(file_path, "r") as file:
|
||||
text = file.read()
|
||||
|
||||
# ************************************************
|
||||
# Define the configuration for the graph
|
||||
# ************************************************
|
||||
|
||||
graph_config = {
|
||||
"llm": {
|
||||
"model": "ollama/llama3",
|
||||
"temperature": 0,
|
||||
"format": "json", # Ollama needs the format to be specified explicitly
|
||||
# "model_tokens": 2000, # set context length arbitrarily
|
||||
"base_url": "http://localhost:11434",
|
||||
},
|
||||
"embeddings": {
|
||||
"model": "ollama/nomic-embed-text",
|
||||
"temperature": 0,
|
||||
"base_url": "http://localhost:11434",
|
||||
},
|
||||
"verbose": True,
|
||||
}
|
||||
|
||||
# ************************************************
|
||||
# Create the CSVScraperMultiGraph instance and run it
|
||||
# ************************************************
|
||||
|
||||
csv_scraper_graph = CSVScraperMultiGraph(
|
||||
prompt="List me all the last names",
|
||||
source=[str(text), str(text)],
|
||||
config=graph_config,
|
||||
)
|
||||
|
||||
result = csv_scraper_graph.run()
|
||||
print(result)
|
||||
|
||||
# ************************************************
|
||||
# Get graph execution info
|
||||
# ************************************************
|
||||
|
||||
graph_exec_info = csv_scraper_graph.get_execution_info()
|
||||
print(prettify_exec_info(graph_exec_info))
|
||||
@@ -0,0 +1,59 @@
|
||||
"""
|
||||
Basic example of scraping pipeline using CSVScraperGraph from CSV documents
|
||||
"""
|
||||
|
||||
import os
|
||||
|
||||
from scrapegraphai.graphs import CSVScraperGraph
|
||||
from scrapegraphai.utils import prettify_exec_info
|
||||
|
||||
# ************************************************
|
||||
# Read the CSV file
|
||||
# ************************************************
|
||||
|
||||
FILE_NAME = "inputs/username.csv"
|
||||
curr_dir = os.path.dirname(os.path.realpath(__file__))
|
||||
file_path = os.path.join(curr_dir, FILE_NAME)
|
||||
|
||||
with open(file_path, "r") as file:
|
||||
text = file.read()
|
||||
|
||||
# ************************************************
|
||||
# Define the configuration for the graph
|
||||
# ************************************************
|
||||
|
||||
graph_config = {
|
||||
"llm": {
|
||||
"model": "ollama/llama3",
|
||||
"temperature": 0,
|
||||
"format": "json", # Ollama needs the format to be specified explicitly
|
||||
# "model_tokens": 2000, # set context length arbitrarily
|
||||
"base_url": "http://localhost:11434",
|
||||
},
|
||||
"embeddings": {
|
||||
"model": "ollama/nomic-embed-text",
|
||||
"temperature": 0,
|
||||
"base_url": "http://localhost:11434",
|
||||
},
|
||||
"verbose": True,
|
||||
}
|
||||
|
||||
# ************************************************
|
||||
# Create the CSVScraperGraph instance and run it
|
||||
# ************************************************
|
||||
|
||||
csv_scraper_graph = CSVScraperGraph(
|
||||
prompt="List me all the last names",
|
||||
source=str(text), # Pass the content of the file, not the file object
|
||||
config=graph_config,
|
||||
)
|
||||
|
||||
result = csv_scraper_graph.run()
|
||||
print(result)
|
||||
|
||||
# ************************************************
|
||||
# Get graph execution info
|
||||
# ************************************************
|
||||
|
||||
graph_exec_info = csv_scraper_graph.get_execution_info()
|
||||
print(prettify_exec_info(graph_exec_info))
|
||||
@@ -0,0 +1,6 @@
|
||||
Username; Identifier;First name;Last name
|
||||
booker12;9012;Rachel;Booker
|
||||
grey07;2070;Laura;Grey
|
||||
johnson81;4081;Craig;Johnson
|
||||
jenkins46;9346;Mary;Jenkins
|
||||
smith79;5079;Jamie;Smith
|
||||
|
@@ -0,0 +1,54 @@
|
||||
"""
|
||||
Basic example of scraping pipeline using CSVScraperMultiGraph from CSV documents
|
||||
"""
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
|
||||
from scrapegraphai.graphs import CSVScraperMultiGraph
|
||||
from scrapegraphai.utils import prettify_exec_info
|
||||
|
||||
load_dotenv()
|
||||
# ************************************************
|
||||
# Read the CSV file
|
||||
# ************************************************
|
||||
|
||||
FILE_NAME = "inputs/username.csv"
|
||||
curr_dir = os.path.dirname(os.path.realpath(__file__))
|
||||
file_path = os.path.join(curr_dir, FILE_NAME)
|
||||
|
||||
with open(file_path, "r") as file:
|
||||
text = file.read()
|
||||
|
||||
# ************************************************
|
||||
# Define the configuration for the graph
|
||||
# ************************************************
|
||||
openai_key = os.getenv("OPENAI_APIKEY")
|
||||
|
||||
graph_config = {
|
||||
"llm": {
|
||||
"api_key": openai_key,
|
||||
"model": "openai/gpt-4o",
|
||||
},
|
||||
}
|
||||
|
||||
# ************************************************
|
||||
# Create the CSVScraperMultiGraph instance and run it
|
||||
# ************************************************
|
||||
|
||||
csv_scraper_graph = CSVScraperMultiGraph(
|
||||
prompt="List me all the last names",
|
||||
source=[str(text), str(text)],
|
||||
config=graph_config,
|
||||
)
|
||||
|
||||
result = csv_scraper_graph.run()
|
||||
print(result)
|
||||
|
||||
# ************************************************
|
||||
# Get graph execution info
|
||||
# ************************************************
|
||||
|
||||
graph_exec_info = csv_scraper_graph.get_execution_info()
|
||||
print(prettify_exec_info(graph_exec_info))
|
||||
@@ -0,0 +1,56 @@
|
||||
"""
|
||||
Basic example of scraping pipeline using CSVScraperGraph from CSV documents
|
||||
"""
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
|
||||
from scrapegraphai.graphs import CSVScraperGraph
|
||||
from scrapegraphai.utils import prettify_exec_info
|
||||
|
||||
load_dotenv()
|
||||
|
||||
# ************************************************
|
||||
# Read the CSV file
|
||||
# ************************************************
|
||||
|
||||
FILE_NAME = "inputs/username.csv"
|
||||
curr_dir = os.path.dirname(os.path.realpath(__file__))
|
||||
file_path = os.path.join(curr_dir, FILE_NAME)
|
||||
|
||||
with open(file_path, "r") as file:
|
||||
text = file.read()
|
||||
|
||||
# ************************************************
|
||||
# Define the configuration for the graph
|
||||
# ************************************************
|
||||
|
||||
openai_key = os.getenv("OPENAI_APIKEY")
|
||||
|
||||
graph_config = {
|
||||
"llm": {
|
||||
"api_key": openai_key,
|
||||
"model": "openai/gpt-4o",
|
||||
},
|
||||
}
|
||||
|
||||
# ************************************************
|
||||
# Create the CSVScraperGraph instance and run it
|
||||
# ************************************************
|
||||
|
||||
csv_scraper_graph = CSVScraperGraph(
|
||||
prompt="List me all the last names",
|
||||
source=str(text), # Pass the content of the file, not the file object
|
||||
config=graph_config,
|
||||
)
|
||||
|
||||
result = csv_scraper_graph.run()
|
||||
print(result)
|
||||
|
||||
# ************************************************
|
||||
# Get graph execution info
|
||||
# ************************************************
|
||||
|
||||
graph_exec_info = csv_scraper_graph.get_execution_info()
|
||||
print(prettify_exec_info(graph_exec_info))
|
||||
@@ -0,0 +1,6 @@
|
||||
Username; Identifier;First name;Last name
|
||||
booker12;9012;Rachel;Booker
|
||||
grey07;2070;Laura;Grey
|
||||
johnson81;4081;Craig;Johnson
|
||||
jenkins46;9346;Mary;Jenkins
|
||||
smith79;5079;Jamie;Smith
|
||||
|
Reference in New Issue
Block a user