Python scraper based on AI
ScrapeGraphAI is a web scraping python library which uses LLM and direct graph logic to create scraping pipelines for websites, documents and XML files. Just say which information you want to extract and the library will do it for you!
The reference page for Scrapegraph-ai is avaible on the official page of pypy: pypi.
pip install scrapegraphai
Official streamlit demo:
Try it directly on the web using Google Colab:
Follow the procedure on the following link to setup your OpenAI API key: link.
The documentation for ScrapeGraphAI can be found here.
Check out also the docusaurus documentation.
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.
Remember to download the model on Ollama separately!
from scrapegraphai.graphs import SmartScraperGraph
graph_config = {
"llm": {
"model": "ollama/mistral",
"temperature": 0,
"format": "json", # Ollama needs the format to be specified explicitly
"base_url": "http://localhost:11434", # set ollama URL arbitrarily
},
"embeddings": {
"model": "ollama/nomic-embed-text",
"temperature": 0,
"base_url": "http://localhost:11434", # set ollama URL arbitrarily
}
}
smart_scraper_graph = SmartScraperGraph(
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(result)
Note: before using the local model remeber to create the docker container!
docker-compose up -d
docker exec -it ollama ollama run stablelm-zephyr
You can use which models avaiable on Ollama or your own model instead of stablelm-zephyr
from scrapegraphai.graphs import SmartScraperGraph
graph_config = {
"llm": {
"model": "ollama/mistral",
"temperature": 0,
"format": "json", # Ollama needs the format to be specified explicitly
# "model_tokens": 2000, # set context length arbitrarily
},
}
smart_scraper_graph = SmartScraperGraph(
prompt="List me all the news with their description.",
# also accepts a string with the already downloaded HTML code
source="https://www.wired.com",
config=graph_config
)
result = smart_scraper_graph.run()
print(result)
from scrapegraphai.graphs import SmartScraperGraph
OPENAI_API_KEY = "YOUR_API_KEY"
graph_config = {
"llm": {
"api_key": OPENAI_API_KEY,
"model": "gpt-3.5-turbo",
},
}
smart_scraper_graph = SmartScraperGraph(
prompt="List me all the news with their description.",
# also accepts a string with the already downloaded HTML code
source="https://www.wired.com",
config=graph_config
)
result = smart_scraper_graph.run()
print(result)
from scrapegraphai.graphs import SmartScraperGraph
GOOGLE_APIKEY = "YOUR_API_KEY"
# Define the configuration for the graph
graph_config = {
"llm": {
"api_key": GOOGLE_APIKEY,
"model": "gemini-pro",
},
}
# Create the SmartScraperGraph instance
smart_scraper_graph = SmartScraperGraph(
prompt="List me all the quotes, authors and tags ",
source="http://quotes.toscrape.com", # also accepts a string with the already downloaded HTML code as string format
config=graph_config
)
result = smart_scraper_graph.run()
print(result)
The output for alle 3 the cases will be a dictionary with the extracted information, for example:
{
'titles': [
'Rotary Pendulum RL'
],
'descriptions': [
'Open Source project aimed at controlling a real life rotary pendulum using RL algorithms'
]
}
Fell free to contribute and join our Discord server to discuss with us improvements and give us suggestions!
For more information, please see the contributing guidelines.
If you have used our library for research purposes please quote us with the following reference:
@misc{scrapegraph-ai,
author = {Marco Perini, Lorenzo Padoan, Marco Vinciguerra},
title = {Scrapegraph-ai},
year = {2024},
url = {https://github.com/VinciGit00/Scrapegraph-ai},
note = {A Python library for scraping data from graphs}
}
Contact Info | |
---|---|
Marco Vinciguerra | |
Marco Perini | |
Lorenzo Padoan |
ScrapeGraphAI is licensed under the MIT License. See the LICENSE file for more information.