# 🕷️ ScrapeGraphAI: You Only Scrape Once
[](https://pepy.tech/project/scrapegraphai)
[](https://github.com/pylint-dev/pylint)
[](https://github.com/VinciGit00/Scrapegraph-ai/actions/workflows/pylint.yml)
[](https://github.com/VinciGit00/Scrapegraph-ai/actions/workflows/codeql.yml)
[](https://opensource.org/licenses/MIT)
[](https://discord.gg/gkxQDAjfeX)
ScrapeGraphAI is a *web scraping* python library that uses LLM and direct graph logic to create scraping pipelines for websites and local documents (XML, HTML, JSON, etc.).
Just say which information you want to extract and the library will do it for you!
<p align="center">
<img src="https://raw.githubusercontent.com/VinciGit00/Scrapegraph-ai/main/docs/assets/scrapegraphai_logo.png" alt="Scrapegraph-ai Logo" style="width: 50%;">
</p>
## 🚀 Quick install
The reference page for Scrapegraph-ai is available on the official page of pypy: [pypi](https://pypi.org/project/scrapegraphai/).
```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:
[](https://scrapegraph-ai-demo.streamlit.app/)
Try it directly on the web using Google Colab:
[](https://colab.research.google.com/drive/1sEZBonBMGP44CtO6GQTwAlL0BGJXjtfd?usp=sharing)
## 📖 Documentation
The documentation for ScrapeGraphAI can be found [here](https://scrapegraph-ai.readthedocs.io/en/latest/).
Check out also the Docusaurus [here](https://scrapegraph-doc.onrender.com/).
## 💻 Usage
There are three main scraping pipelines that can be used to extract information from a website (or local file):
- `SmartScraperGraph`: single-page scraper that only needs a user prompt and an input source;
- `SearchGraph`: multi-page scraper that extracts information from the top n search results of a search engine;
- `SpeechGraph`: single-page scraper that extracts information from a website and generates an audio file.
It is possible to use different LLM through APIs, such as **OpenAI**, **Groq**, **Azure** and **Gemini**, or local models using **Ollama**.
### Case 1: SmartScraper using Local Models
Remember to have [Ollama](https://ollama.com/) installed and download the models using the **ollama pull** command.
```python
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
},
"embeddings": {
"model": "ollama/nomic-embed-text",
"base_url": "http://localhost:11434", # set Ollama URL
},
"verbose": True,
}
smart_scraper_graph = SmartScraperGraph(
prompt="List me all the projects with their descriptions",
# 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)
```
The output will be a list of projects with their descriptions like the following:
```python
{'projects': [{'title': 'Rotary Pendulum RL', 'description': 'Open Source project aimed at controlling a real life rotary pendulum using RL algorithms'}, {'title': 'DQN Implementation from scratch', 'description': 'Developed a Deep Q-Network algorithm to train a simple and double pendulum'}, ...]}
```
### Case 2: SearchGraph using Mixed Models
We use **Groq** for the LLM and **Ollama** for the embeddings.
```python
from scrapegraphai.graphs import SearchGraph
# Define the configuration for the graph
graph_config = {
"llm": {
"model": "groq/gemma-7b-it",
"api_key": "GROQ_API_KEY",
"temperature": 0
},
"embeddings": {
"model": "ollama/nomic-embed-text",
"base_url": "http://localhost:11434", # set ollama URL arbitrarily
},
"max_results": 5,
}
# Create the SearchGraph instance
search_graph = SearchGraph(
prompt="List me all the traditional recipes from Chioggia",
config=graph_config
)
# Run the graph
result = search_graph.run()
print(result)
```
The output will be a list of recipes like the following:
```python
{'recipes': [{'name': 'Sarde in Saòre'}, {'name': 'Bigoli in salsa'}, {'name': 'Seppie in umido'}, {'name': 'Moleche frite'}, {'name': 'Risotto alla pescatora'}, {'name': 'Broeto'}, {'name': 'Bibarasse in Cassopipa'}, {'name': 'Risi e bisi'}, {'name': 'Smegiassa Ciosota'}]}
```
### Case 3: SpeechGraph using OpenAI
You just need to pass the OpenAI API key and the model name.
```python
from scrapegraphai.graphs import SpeechGraph
graph_config = {
"llm": {
"api_key": "OPENAI_API_KEY",
"model": "gpt-3.5-turbo",
},
"tts_model": {
"api_key": "OPENAI_API_KEY",
"model": "tts-1",
"voice": "alloy"
},
"output_path": "audio_summary.mp3",
}
# ************************************************
# Create the SpeechGraph instance and run it
# ************************************************
speech_graph = SpeechGraph(
prompt="Make a detailed audio summary of the projects.",
source="https://perinim.github.io/projects/",
config=graph_config,
)
result = speech_graph.run()
print(result)
```
The output will be an audio file with the summary of the projects on the page.
## 🤝 Contributing
Feel free to contribute and join our Discord server to discuss with us improvements and give us suggestions!
Please see the [contributing guidelines](https://github.com/VinciGit00/Scrapegraph-ai/blob/main/CONTRIBUTING.md).
[](https://discord.gg/gkxQDAjfeX)
[](https://www.linkedin.com/company/scrapegraphai/)
[](https://twitter.com/scrapegraphai)
## 📈 Roadmap
Check out the project roadmap [here](https://github.com/VinciGit00/Scrapegraph-ai/blob/main/docs/README.md)! 🚀
Wanna visualize the roadmap in a more interactive way? Check out the [markmap](https://markmap.js.org/repl) visualization by copy pasting the markdown content in the editor!
## ❤️ Contributors
[](https://github.com/VinciGit00/Scrapegraph-ai/graphs/contributors)
## Sponsors
<p align="center">
<a href="https://serpapi.com?utm_source=scrapegraphai"><img src="https://raw.githubusercontent.com/VinciGit00/Scrapegraph-ai/main/docs/assets/serp_api_logo.png" alt="SerpAPI" style="width: 10%;"></a>
</p>
## 🎓 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
<p align="center">
<img src="https://raw.githubusercontent.com/VinciGit00/Scrapegraph-ai/main/docs/assets/logo_authors.png" alt="Authors_logos">
</p>
| | Contact Info |
|--------------------|----------------------|
| Marco Vinciguerra | [](https://www.linkedin.com/in/marco-vinciguerra-7ba365242/) |
| Marco Perini | [](https://www.linkedin.com/in/perinim/) |
| Lorenzo Padoan | [](https://www.linkedin.com/in/lorenzo-padoan-4521a2154/) |
## 📜 License
ScrapeGraphAI is licensed under the MIT License. See the [LICENSE](https://github.com/VinciGit00/Scrapegraph-ai/blob/main/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.
Raw data
{
"_id": null,
"home_page": null,
"name": "scrapegraphai",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.9",
"maintainer_email": null,
"keywords": "ai, artificial intelligence, gpt, graph, langchain, machine learning, natural language processing, nlp, openai, rag, scrapegraph, scrapegraphai, scraping, web scraping, web scraping library, web scraping tool, webscraping",
"author": null,
"author_email": "Marco Vinciguerra <mvincig11@gmail.com>, Marco Perini <perinim.98@gmail.com>, Lorenzo Padoan <lorenzo.padoan977@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/00/20/6985fb89a1e65851d5a91c1aee7a29038d1c5a4f7155d73ea0e09ab7c9c5/scrapegraphai-1.2.4.tar.gz",
"platform": null,
"description": "\n# \ud83d\udd77\ufe0f ScrapeGraphAI: You Only Scrape Once\n[](https://pepy.tech/project/scrapegraphai)\n[](https://github.com/pylint-dev/pylint)\n[](https://github.com/VinciGit00/Scrapegraph-ai/actions/workflows/pylint.yml)\n[](https://github.com/VinciGit00/Scrapegraph-ai/actions/workflows/codeql.yml)\n[](https://opensource.org/licenses/MIT)\n[](https://discord.gg/gkxQDAjfeX)\n\nScrapeGraphAI is a *web scraping* python library that uses LLM and direct graph logic to create scraping pipelines for websites and local documents (XML, HTML, JSON, etc.).\n\nJust say which information you want to extract and the library will do it for you!\n\n<p align=\"center\">\n <img src=\"https://raw.githubusercontent.com/VinciGit00/Scrapegraph-ai/main/docs/assets/scrapegraphai_logo.png\" alt=\"Scrapegraph-ai Logo\" style=\"width: 50%;\">\n</p>\n\n## \ud83d\ude80 Quick install\n\nThe reference page for Scrapegraph-ai is available on the official page of pypy: [pypi](https://pypi.org/project/scrapegraphai/).\n\n```bash\npip install scrapegraphai\n```\nyou will also need to install Playwright for javascript-based scraping:\n```bash\nplaywright install\n```\n\n**Note**: it is recommended to install the library in a virtual environment to avoid conflicts with other libraries \ud83d\udc31\n\n## \ud83d\udd0d Demo\nOfficial streamlit demo:\n\n[](https://scrapegraph-ai-demo.streamlit.app/)\n\nTry it directly on the web using Google Colab:\n\n[](https://colab.research.google.com/drive/1sEZBonBMGP44CtO6GQTwAlL0BGJXjtfd?usp=sharing)\n\n## \ud83d\udcd6 Documentation\n\nThe documentation for ScrapeGraphAI can be found [here](https://scrapegraph-ai.readthedocs.io/en/latest/).\n\nCheck out also the Docusaurus [here](https://scrapegraph-doc.onrender.com/).\n\n## \ud83d\udcbb Usage\nThere are three main scraping pipelines that can be used to extract information from a website (or local file):\n- `SmartScraperGraph`: single-page scraper that only needs a user prompt and an input source;\n- `SearchGraph`: multi-page scraper that extracts information from the top n search results of a search engine;\n- `SpeechGraph`: single-page scraper that extracts information from a website and generates an audio file.\n\nIt is possible to use different LLM through APIs, such as **OpenAI**, **Groq**, **Azure** and **Gemini**, or local models using **Ollama**.\n\n### Case 1: SmartScraper using Local Models\n\nRemember to have [Ollama](https://ollama.com/) installed and download the models using the **ollama pull** command.\n\n```python\nfrom scrapegraphai.graphs import SmartScraperGraph\n\ngraph_config = {\n \"llm\": {\n \"model\": \"ollama/mistral\",\n \"temperature\": 0,\n \"format\": \"json\", # Ollama needs the format to be specified explicitly\n \"base_url\": \"http://localhost:11434\", # set Ollama URL\n },\n \"embeddings\": {\n \"model\": \"ollama/nomic-embed-text\",\n \"base_url\": \"http://localhost:11434\", # set Ollama URL\n },\n \"verbose\": True,\n}\n\nsmart_scraper_graph = SmartScraperGraph(\n prompt=\"List me all the projects with their descriptions\",\n # also accepts a string with the already downloaded HTML code\n source=\"https://perinim.github.io/projects\",\n config=graph_config\n)\n\nresult = smart_scraper_graph.run()\nprint(result)\n\n```\n\nThe output will be a list of projects with their descriptions like the following:\n\n```python\n{'projects': [{'title': 'Rotary Pendulum RL', 'description': 'Open Source project aimed at controlling a real life rotary pendulum using RL algorithms'}, {'title': 'DQN Implementation from scratch', 'description': 'Developed a Deep Q-Network algorithm to train a simple and double pendulum'}, ...]}\n```\n\n### Case 2: SearchGraph using Mixed Models\n\nWe use **Groq** for the LLM and **Ollama** for the embeddings.\n\n```python\nfrom scrapegraphai.graphs import SearchGraph\n\n# Define the configuration for the graph\ngraph_config = {\n \"llm\": {\n \"model\": \"groq/gemma-7b-it\",\n \"api_key\": \"GROQ_API_KEY\",\n \"temperature\": 0\n },\n \"embeddings\": {\n \"model\": \"ollama/nomic-embed-text\",\n \"base_url\": \"http://localhost:11434\", # set ollama URL arbitrarily\n },\n \"max_results\": 5,\n}\n\n# Create the SearchGraph instance\nsearch_graph = SearchGraph(\n prompt=\"List me all the traditional recipes from Chioggia\",\n config=graph_config\n)\n\n# Run the graph\nresult = search_graph.run()\nprint(result)\n```\n\nThe output will be a list of recipes like the following:\n\n```python\n{'recipes': [{'name': 'Sarde in Sa\u00f2re'}, {'name': 'Bigoli in salsa'}, {'name': 'Seppie in umido'}, {'name': 'Moleche frite'}, {'name': 'Risotto alla pescatora'}, {'name': 'Broeto'}, {'name': 'Bibarasse in Cassopipa'}, {'name': 'Risi e bisi'}, {'name': 'Smegiassa Ciosota'}]}\n```\n### Case 3: SpeechGraph using OpenAI\n\nYou just need to pass the OpenAI API key and the model name.\n\n```python\nfrom scrapegraphai.graphs import SpeechGraph\n\ngraph_config = {\n \"llm\": {\n \"api_key\": \"OPENAI_API_KEY\",\n \"model\": \"gpt-3.5-turbo\",\n },\n \"tts_model\": {\n \"api_key\": \"OPENAI_API_KEY\",\n \"model\": \"tts-1\",\n \"voice\": \"alloy\"\n },\n \"output_path\": \"audio_summary.mp3\",\n}\n\n# ************************************************\n# Create the SpeechGraph instance and run it\n# ************************************************\n\nspeech_graph = SpeechGraph(\n prompt=\"Make a detailed audio summary of the projects.\",\n source=\"https://perinim.github.io/projects/\",\n config=graph_config,\n)\n\nresult = speech_graph.run()\nprint(result)\n\n```\n\nThe output will be an audio file with the summary of the projects on the page.\n\n## \ud83e\udd1d Contributing\n\nFeel free to contribute and join our Discord server to discuss with us improvements and give us suggestions!\n\nPlease see the [contributing guidelines](https://github.com/VinciGit00/Scrapegraph-ai/blob/main/CONTRIBUTING.md).\n\n[](https://discord.gg/gkxQDAjfeX)\n[](https://www.linkedin.com/company/scrapegraphai/)\n[](https://twitter.com/scrapegraphai)\n\n## \ud83d\udcc8 Roadmap\nCheck out the project roadmap [here](https://github.com/VinciGit00/Scrapegraph-ai/blob/main/docs/README.md)! \ud83d\ude80\n\nWanna visualize the roadmap in a more interactive way? Check out the [markmap](https://markmap.js.org/repl) visualization by copy pasting the markdown content in the editor!\n\n## \u2764\ufe0f Contributors\n[](https://github.com/VinciGit00/Scrapegraph-ai/graphs/contributors)\n## Sponsors\n<p align=\"center\">\n <a href=\"https://serpapi.com?utm_source=scrapegraphai\"><img src=\"https://raw.githubusercontent.com/VinciGit00/Scrapegraph-ai/main/docs/assets/serp_api_logo.png\" alt=\"SerpAPI\" style=\"width: 10%;\"></a>\n</p>\n\n## \ud83c\udf93 Citations\nIf you have used our library for research purposes please quote us with the following reference:\n```text\n @misc{scrapegraph-ai,\n author = {Marco Perini, Lorenzo Padoan, Marco Vinciguerra},\n title = {Scrapegraph-ai},\n year = {2024},\n url = {https://github.com/VinciGit00/Scrapegraph-ai},\n note = {A Python library for scraping leveraging large language models}\n }\n```\n\n## Authors\n\n<p align=\"center\">\n <img src=\"https://raw.githubusercontent.com/VinciGit00/Scrapegraph-ai/main/docs/assets/logo_authors.png\" alt=\"Authors_logos\">\n</p>\n\n| | Contact Info |\n|--------------------|----------------------|\n| Marco Vinciguerra | [](https://www.linkedin.com/in/marco-vinciguerra-7ba365242/) |\n| Marco Perini | [](https://www.linkedin.com/in/perinim/) |\n| Lorenzo Padoan | [](https://www.linkedin.com/in/lorenzo-padoan-4521a2154/) |\n\n## \ud83d\udcdc License\n\nScrapeGraphAI is licensed under the MIT License. See the [LICENSE](https://github.com/VinciGit00/Scrapegraph-ai/blob/main/LICENSE) file for more information.\n\n## Acknowledgements\n\n- We would like to thank all the contributors to the project and the open-source community for their support.\n- ScrapeGraphAI is meant to be used for data exploration and research purposes only. We are not responsible for any misuse of the library.\n",
"bugtrack_url": null,
"license": null,
"summary": "A web scraping library based on LangChain which uses LLM and direct graph logic to create scraping pipelines.",
"version": "1.2.4",
"project_urls": null,
"split_keywords": [
"ai",
" artificial intelligence",
" gpt",
" graph",
" langchain",
" machine learning",
" natural language processing",
" nlp",
" openai",
" rag",
" scrapegraph",
" scrapegraphai",
" scraping",
" web scraping",
" web scraping library",
" web scraping tool",
" webscraping"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "756e52283e5aa836535a1443fbc011e9c8f30697032a0df7a4a5a615148e2785",
"md5": "cc731ecaabbd3d535e02dbd142351041",
"sha256": "c8be64fd2f54cfb3072f75adfb7f83ba43eb83090a11083d6e45dc7e77a7387e"
},
"downloads": -1,
"filename": "scrapegraphai-1.2.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "cc731ecaabbd3d535e02dbd142351041",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.9",
"size": 84270,
"upload_time": "2024-05-17T08:38:42",
"upload_time_iso_8601": "2024-05-17T08:38:42.343962Z",
"url": "https://files.pythonhosted.org/packages/75/6e/52283e5aa836535a1443fbc011e9c8f30697032a0df7a4a5a615148e2785/scrapegraphai-1.2.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "00206985fb89a1e65851d5a91c1aee7a29038d1c5a4f7155d73ea0e09ab7c9c5",
"md5": "f86fb709537688ee8c4a587edf6903b2",
"sha256": "3be26ae65abf86e6833f63f7256d38e3129f8852cd73062e97ff89f13f9abedf"
},
"downloads": -1,
"filename": "scrapegraphai-1.2.4.tar.gz",
"has_sig": false,
"md5_digest": "f86fb709537688ee8c4a587edf6903b2",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9",
"size": 2716285,
"upload_time": "2024-05-17T08:38:44",
"upload_time_iso_8601": "2024-05-17T08:38:44.977184Z",
"url": "https://files.pythonhosted.org/packages/00/20/6985fb89a1e65851d5a91c1aee7a29038d1c5a4f7155d73ea0e09ab7c9c5/scrapegraphai-1.2.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-05-17 08:38:44",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "scrapegraphai"
}
JSON