Comments (2)
randomwalker
commented on May 26, 2024
You can get a best of both worlds approach in the following way:
-
Obtain a sample of URLs for the website (I assume this is straightforward)
-
Cluster the URLs based on purely URL features
-
Build the classifier at the cluster level rather than individual URLs. This will work for most websites
-
For the ones where you are not sure, crawl 5-10 pages from each plausible product page cluster, and use the content features.
I'd like to repeat my point that I think this problem is easier than you're making it out to be :) If you send me a dataset of URLs I'd be happy to take a crack at it.
from dark-patterns.
aruneshmathur
commented on May 26, 2024
That's a neat idea. I suggested a more structured approach, where we manually label a set of URLs from each website first, but clustering reduces that effort.
Some additional URL features to consider:
- length of URL path
- number of directory levels in the URL path
If content features are required, I suggest peeking at the <head> tag first. Many pages follow the Facebook Open Graph protocol, which embeds valuable information.
from dark-patterns.
Related Issues (20)
- Move product attribute code to Javascript HOT 1
- Store number of buttons, imgs, links inside each segment HOT 1
- Store details of the longest text node of each segment HOT 1
- Handle cases where computed style is null HOT 4
- Integrate segmentation into mutation summary event flow HOT 2
- Rate limit/throttle segmentation and element snapshots HOT 1
- Add unique IDs to elements HOT 1
- Handling body elements with 0 width and height
- Build a clustering dashboard HOT 1
- Incorrect background-color value HOT 3
- Link segments to phases HOT 2
- Evaluate the accuracy of shopping website detection HOT 2
- Evaluate accuracy of checkout crawler HOT 1
- Limit product attribute selection HOT 1
- Clustering preprocessing
- Related Work section HOT 1
- Introduction section
- Methods section HOT 1
- Clean up the analysis notebooks
- usage: cluster_browser_http.py [-h] clusters_pickle cluster_id_column cluster_browser_http.py: error: the following arguments are required: clusters_pickle, cluster_id_column
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 dark-patterns.