ZZZ Digital Lab

Back to PDF tables to sheets

before/extract.py

"""DELIBERATELY BROKEN SYNTHETIC BASELINE. Never use for a client."""
import csv
from pathlib import Path
import pdfplumber
def extract_bad(pdf_path,output):
 with pdfplumber.open(pdf_path) as doc: text=doc.pages[0].extract_text() or ''
 rows=[line.replace('O','0').split() for line in text.splitlines() if line[:1].isdigit()]
 with Path(output).open('w',newline='',encoding='utf-8') as f: csv.writer(f).writerows(rows)
 return rows