Comments (1)
jamesturk
commented on May 31, 2024
The matching HTML is sent to the LLM. So if you had HTML like:
<html>
<div class="sidebar"> ... </div>
<main><a href="#">Something</a><div>Something Else</div></main>
<div class="footer"> ... </div>
</html>
And passed the selector main, all of the innerHTML of that element would get sent. (If there are multiple matches they are appended together.)
Just extracting text would tend to lose context, and some data (URL, phone numbers, etc.) might not be in the text, but instead in attributes. Further refinement of this library will likely entail figuring out how minimal the HTML sent can be without affecting results. (I'm currently working on building a test corpus of sorts, since these sorts of questions need to be answered in probabilities.)
from scrapeghost.
Related Issues (20)
- Example Data/Case Studies Needed!
- Discussion: Relicensing HOT 6
- HallucinationChecker error HOT 2
- Use guardrails for validation.
- SSL verification check
- Disable HallucinationChecker HOT 3
- Functionality to JUST update existing CSS / XPath Selectors HOT 1
- Issue with release_date formatting in tutorial HOT 2
- Extending the project for older python versions HOT 1
- Example error HOT 1
- scrapeghost.errors.TooManyTokens even though I am using auto_split_length HOT 1
- add non-JSON output option
- Better Automatic Token Reduction HOT 1
- breaking change: adjust how models are selected
- Optionally use puppeteer chromium and/or beautiful soup? HOT 2
- pagination HOT 1
- explore using new functions-mode in GPT
- JavaScript Enabling HOT 1
- Not all chunk sizes are limited by the auto_split_length parameter HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from scrapeghost.