In this video, I showed a way of content-based feature extraction by Python and content-based features which I defined in the previous video. This is the last video of feature engineering steps in the roadmap. Next video will be about dataset creation for phishing detection models.
You can convert unstructured html data to structured data via this method by BeautifulSoup module, and created a pandas data frame. Check the Github link:
https://github.com/emre-kocyigit/cont...
#machinelearning
#featureextraction
#python
#beautifulsoup
#webscraping
#phishingdetection
#endtoendmachinlearning
Timecode
0:00 Intro and steps of the feature extraction process
2:25 Define a function that opens a html file and returns its content
3:04 Define a function that creates a BeautifulSoup object
3:28 Define a function that creates a vector based on content-based features
5:03 Run functions for all html files and create a 2-dimensional list
7:04 Create a data frame by pandas
8:27 Closing and next video info