Yan Lyesin yanlesin
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from poppler import load_from_file, PageRenderer | |
| import pandas as pd | |
| import polars as pl | |
| import numpy as np | |
| pdf_document = load_from_file("/Users/yanlyesin/Downloads/13flist2024q3.pdf") | |
| df_from_pdf = pd.DataFrame(columns=['text', 'page', 'cusip', 'issuer_name', 'issuer_description', 'status', 'text_length']) | |
| for page in range(2, pdf_document.pages): | |
| text_from_pdf = pdf_document.create_page(page).text().split("\n") | |
| df_text = pd.DataFrame({'text': text_from_pdf, 'page': [page] * len(text_from_pdf)}) |