🕷️ ScrapeGraphAI: You Only Scrape Once

ScrapeGraphAI is a web scraping python library that 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!

🚀 Quick install

The reference page for Scrapegraph-ai is available on the official page of pypy: pypi.

bash pip install scrapegraphai you will also need to install Playwright for javascript-based scraping: bash playwright install

Note: it is recommended to install the library in a virtual environment to avoid conflicts with other libraries 🐱

🔍 Demo

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.

📖 Documentation

The documentation for ScrapeGraphAI can be found here.

Check out also the docusaurus documentation.

💻 Usage

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.

Case 1: Extracting information using Ollama

Remember to download the model on Ollama separately!

```python from scrapegraphai.graphs import SmartScraperGraph

graphconfig = { "llm": { "model": "ollama/mistral", "temperature": 0, "format": "json", # Ollama needs the format to be specified explicitly "baseurl": "http://localhost:11434", # set Ollama URL }, "embeddings": { "model": "ollama/nomic-embed-text", "base_url": "http://localhost:11434", # set Ollama URL } }

smartscrapergraph = SmartScraperGraph( prompt="List me all the articles", # also accepts a string with the already downloaded HTML code source="https://perinim.github.io/projects", config=graph_config )

result = smartscrapergraph.run() print(result)

```

Case 2: Extracting information using Docker

Note: before using the local model remember to create the docker container! text docker-compose up -d docker exec -it ollama ollama pull stablelm-zephyr You can use which models avaiable on Ollama or your own model instead of stablelm-zephyr ```python from scrapegraphai.graphs import SmartScraperGraph

graphconfig = { "llm": { "model": "ollama/mistral", "temperature": 0, "format": "json", # Ollama needs the format to be specified explicitly # "modeltokens": 2000, # set context length arbitrarily }, }

smartscrapergraph = SmartScraperGraph( prompt="List me all the articles", # also accepts a string with the already downloaded HTML code source="https://perinim.github.io/projects",
config=graph_config )

result = smartscrapergraph.run() print(result) ```

Case 3: Extracting information using Openai model

```python from scrapegraphai.graphs import SmartScraperGraph OPENAIAPIKEY = "YOURAPIKEY"

graphconfig = { "llm": { "apikey": OPENAIAPIKEY, "model": "gpt-3.5-turbo", }, }

smartscrapergraph = SmartScraperGraph( prompt="List me all the articles", # also accepts a string with the already downloaded HTML code source="https://perinim.github.io/projects", config=graph_config )

result = smartscrapergraph.run() print(result) ```

Case 4: Extracting information using Groq

```python from scrapegraphai.graphs import SmartScraperGraph from scrapegraphai.utils import prettifyexecinfo

groqkey = os.getenv("GROQAPIKEY")

graphconfig = { "llm": { "model": "groq/gemma-7b-it", "apikey": groqkey, "temperature": 0 }, "embeddings": { "model": "ollama/nomic-embed-text", "temperature": 0, "baseurl": "http://localhost:11434", }, "headless": False }

smartscrapergraph = SmartScraperGraph( prompt="List me all the projects with their description and the author.", source="https://perinim.github.io/projects", config=graph_config )

result = smartscrapergraph.run() print(result) ```

Case 5: Extracting information using Azure

```python from langchainopenai import AzureChatOpenAI from langchainopenai import AzureOpenAIEmbeddings

lmmodelinstance = AzureChatOpenAI( openaiapiversion=os.environ["AZUREOPENAIAPIVERSION"], azuredeployment=os.environ["AZUREOPENAICHATDEPLOYMENTNAME"] )

embeddermodelinstance = AzureOpenAIEmbeddings( azuredeployment=os.environ["AZUREOPENAIEMBEDDINGSDEPLOYMENTNAME"], openaiapiversion=os.environ["AZUREOPENAIAPIVERSION"], ) graphconfig = { "llm": {"modelinstance": llmmodelinstance}, "embeddings": {"modelinstance": embeddermodel_instance} }

smartscrapergraph = SmartScraperGraph( prompt="""List me all the events, with the following fields: companyname, eventname, eventstartdate, eventstarttime, eventenddate, eventendtime, location, eventmode, eventcategory, thirdpartyredirect, noofdays, timeinhours, hostedorattending, refreshmentstype, registrationavailable, registrationlink""", source="https://www.hmhco.com/event", config=graphconfig ) ```

Case 6: Extracting information using Gemini

```python from scrapegraphai.graphs import SmartScraperGraph GOOGLEAPIKEY = "YOURAPI_KEY"

Define the configuration for the graph

graphconfig = { "llm": { "apikey": GOOGLE_APIKEY, "model": "gemini-pro", }, }

Create the SmartScraperGraph instance

smartscrapergraph = SmartScraperGraph( prompt="List me all the articles", source="https://perinim.github.io/projects", config=graph_config )

result = smartscrapergraph.run() print(result) ```

The output for all 3 the cases will be a dictionary with the extracted information, for example:

bash { 'titles': [ 'Rotary Pendulum RL' ], 'descriptions': [ 'Open Source project aimed at controlling a real life rotary pendulum using RL algorithms' ] }

🤝 Contributing

Feel free to contribute and join our Discord server to discuss with us improvements and give us suggestions!

Please see the contributing guidelines.

📈 Roadmap

Check out the project roadmap here! 🚀

Wanna visualize the roadmap in a more interactive way? Check out the markmap visualization by copy pasting the markdown content in the editor!

❤️ Contributors

🎓 Citations

If you have used our library for research purposes please quote us with the following reference: text @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 leveraging large language models} }

Authors

| | Contact Info | |--------------------|----------------------| | Marco Vinciguerra | | | Marco Perini | | | Lorenzo Padoan | |

📜 License

ScrapeGraphAI is licensed under the MIT License. See the LICENSE file for more information.

Acknowledgements

• We would like to thank all the contributors to the project and the open-source community for their support.
• ScrapeGraphAI is meant to be used for data exploration and research purposes only. We are not responsible for any misuse of the library.