PyPI page
Author:
Marco Vinciguerra
Summary:
A web scraping library based on LangChain which uses LLM and direct graph logic to create scraping pipelines.
Latest version:
2.3.1
Required dependencies:
async-timeout
|
beautifulsoup4
|
ddgs
|
free-proxy
|
html2text
|
jsonschema
|
langchain
|
langchain-aws
|
langchain-classic
|
langchain-community
|
langchain-mistralai
|
langchain-ollama
|
langchain-openai
|
minify-html
|
playwright
|
pydantic
|
python-dotenv
|
scrapegraph-py
|
semchunk
|
simpleeval
|
tiktoken
|
tqdm
|
undetected-playwright
Optional dependencies:
burr
|
ipywidgets
|
langchain-nvidia-ai-endpoints
|
matplotlib
|
pillow
|
surya-ocr
Downloads last day:
808
Downloads last week:
6,491
Downloads last month:
32,537
7-day smoothing