Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/smyja/blackmaria
Python package for webscraping in Natural language
https://github.com/smyja/blackmaria
gpt-3 nlp openai python webscraping
Last synced: about 1 month ago
JSON representation
Python package for webscraping in Natural language
- Host: GitHub
- URL: https://github.com/smyja/blackmaria
- Owner: smyja
- License: mit
- Created: 2023-03-26T11:33:53.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2023-10-28T14:19:50.000Z (11 months ago)
- Last Synced: 2024-07-24T11:53:22.955Z (about 2 months ago)
- Topics: gpt-3, nlp, openai, python, webscraping
- Language: Python
- Homepage:
- Size: 110 KB
- Stars: 152
- Watchers: 6
- Forks: 11
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- Funding: .github/FUNDING.yml
- License: LICENSE
Awesome Lists containing this project
README
## Black Maria
### Getting Started
#### Prerequisites
- [Python 3.6+](https://www.python.org/downloads/)
#### Installation
- export `OPEN_AI_KEY` to your environment variables
- `pip install blackmaria`
### What is Black Maria?
Black Maria is a Python library for web scraping any webpage using natural language.
### How to use Black Maria?
Black Maria uses [guardrails](https://github.com/ShreyaR/guardrails). Guardrails are a set of instructions that tell the LLM what the output should look like.
```python
from blackmaria import maria
url="https://yellowjackets.fandom.com/wiki/F_Sharp"
spec=("""
Query string here.
@xml_prefix_prompt
{output_schema}
@json_suffix_prompt_v2_wo_none
""")
query="provide details about the movie,summary,cast,cast.starring,cast.guest_starring,cast.co-starring"
query_response=maria.night_crawler(url=url,spec=spec,query=query)
print(query_response)
```
### Output
```json
{
"movie": {
"summary": "As the teens get their bearings among the wreckage, Misty finds hell on earth quite becoming. In the present: revenge, sex homework and the policeman formerly known as Goth.",
"cast": {
"starring": [
"Lottie Matthews",
"Vanessa Palmer",
"Misty Quigley",
"Shauna Sadecki",
"Natalie Scatorccio",
"Taissa Turner"
],
"guest_starring": [
"Akilah",
"Laura Lee",
"Mari",
"Adam Martin",
"Javi Martinez",
"Travis Martinez",
"Jessica Roberts",
"Jeff Sadecki",
"Ben Scott",
"Jackie Taylor"
],
"co-starring": ["Kevyn Tan", "Simone"]
}
}
}
```