I want to convert PDF file into CSV. For which I am using Tabula-py. However the output CSV is containing column names not its contents. Please guide tell me what am I missing and how can I save the data frame into a CSV file so that the entire data will be retrieved in the CSV file.
#!/usr/bin/env python3
import tabula
import pandas as pd
import csv
pdf_file='document-page1.pdf'
column_names=['Product','Batch No','Machin No','Time','Date','Drum/Bag No','Tare Wt.kg','Gross Wt.kg',
'Net Wt.kg','Blender','Remarks','Operator']
# Page 1 processing
df1 = tabula.read_pdf(pdf_file, pages=1,area=(95,20, 800, 840),columns=[93,180,220,252,310,315,333,367,
410,450,480,520]
,pandas_options={'header': None}) #(top,left,bottom,right)
df1[0]=df1[0].drop(columns=5)
df1[0].columns=column_names
#df1[0].head(2)
df1[0].to_csv('result.csv')
