# Building a Python Package to Turn Unstructured Data into Financial Insights

DevFeed: [Building a Python Package to Turn Unstructured Data into Financial Insights](<https://devfeed.tech/articles/building-a-python-package-to-turn-unstructured-data-into-financial-insights-39400.md>)

Original publisher: [Read original article](<https://blog.pranshu-raj.in/posts/building-concall-parser/>)

Author: Pranshu Raj

Published: 2025-06-23T08:50:45Z

Content type: tutorial

Language: en

Sources: [Pranshu Raj - blog on backend systems, performance and sidequests](<https://devfeed.tech/sources/pranshu-raj-blog-on-backend-systems-performance-and-sidequests.md>)

Topics: [Python](<https://devfeed.tech/topics/python.md>), [Parsing](<https://devfeed.tech/topics/parsing.md>), [pdf](<https://devfeed.tech/topics/pdf.md>), [data](<https://devfeed.tech/topics/data.md>), [Structured-data](<https://devfeed.tech/topics/structured-data.md>)

Tags: [data](<https://devfeed.tech/tags/data.md>), [parsing](<https://devfeed.tech/tags/parsing.md>), [pdf](<https://devfeed.tech/tags/pdf.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [python](<https://devfeed.tech/tags/python.md>), [structured](<https://devfeed.tech/tags/structured.md>)

## AI overview

This article explains how the authors built a Python package to extract structured information from messy earnings-call PDF transcripts. It covers PDF text extraction, cleaning and segmentation, speaker identification, categorization into sections such as management remarks and Q&A, and structured output.

## Source excerpt

How we built concall-parser to extract structured insights from messy earnings call transcripts, dealing with PDFs, text processing, and speaker identification challenges.