PyTSHD: A Python Implementation for Topic Segmentation Based on Heading Detection

How to Use

from pytshd import TSHD
example_text = "..."
segments = TSHD.segment(
	example_text, 
	cue_filename = "resume"
)

PyTSHD supports many file extensions as well, including: text documents (txt), HTML documents (html), Word Documents (docx), and PDF documents (pdf).

from pytshd import TSHD
example_text = "..."
segments = TSHD.segment(
	example_text, 
	cue_filename = "resume"
)

Additionally, PyTSHD can fetch HTML content from URL using the extension url.

from pytshd import TSHD
example_url = "https://www.google.com"
segments = TSHD.segment(
	example_text, 
	cue_filename = "resume"
)

References

Tannous, M. E., Ramadan, W. H., & Rajab, M. A. (2023). TSHD: Topic Segmentation Based on Headings Detection (Case Study: Resumes). Advances in Human-Computer Interaction, 2023, 1–12. https://doi.org/10.1155/2023/6044007