#PDF Herunterladen
wget https://niigata-gte.com/pdf/shop-list.pdf -O data.pdf

apt install python3-tk ghostscript
pip install camelot-py[cv]

camelot -p all -o data.csv -f csv -strip '\n' -split lattice -scale 40 data.pdf

import camelot
import pandas as pd

tables = camelot.read_pdf(
    "data.pdf", pages="all", split_text=True, strip_text="\n", line_scale=40
)

df = pd.concat(
    [
        table.df.iloc[1:].set_axis(
            ["Händlercode", "Genre", "Speichername", "Adresse", "Telefonnummer", "Mitnahme", "Lieferung"], axis=1
        )
        for table in tables
    ]
)

df.to_csv("niigata.csv", encoding="utf_8_sig")

Recommended Posts