def readTablePdf(fileName="demoData.pdf"):
try:
i = 7
while not i == 0:
print(
"\n 1: Print DataFrame\n 2: Print JSON\n 3: Print Single Table\n 4: Print Multiple Tables "
)
print(
" 5: Save to JSON File\n 6: Save to CSV File\n 7: Tabula Info\n 0: EXIT"
)
i = int(input("Choose one of the options from above: "))
if i == 1:
df = tabula.read_pdf(
fileName
) # Simply reads pdf and returns in DataFrame format
print("DATA: \n", df)
elif i == 2:
df = tabula.read_pdf(fileName, output_format="json"
) # Reads and returns data in Json format
print("JSON DATA: \n", df)
elif i == 3:
df = tabula.read_pdf(
fileName
) # Returns first occurence of table - we can even specify page numbers to retreive table from
print("SINGLE TABLE DATA: \n", df)
elif i == 4:
df = tabula.read_pdf(fileName,
multiple_tables=True,
pages="all") # Returns all tables data
print("ALL TABLES DATA: \n", df)
elif i == 5:
####### TO SAVE JSON INTO JSON FILE
output = input("ENTER OUTPUT FILE NAME")
# Reads and saves the complete file data in JSON format into an external JSON file of given name
convert_into(fileName,
output,
output_format="json",
multiple_tables=True,
pages='all')
elif i == 6:
####### TO SAVE JSON INTO CSV FILE
output = input("ENTER OUTPUT FILE NAME")
# Reads and saves the complete file data in CSV format into an external CSV file of given name
convert_into(fileName,
output,
output_format="csv",
multiple_tables=True,
pages='all')
elif i == 7:
#Tabula Information
print("TABULA INFORMATION:\n", tabula.environment_info())
else:
break
except Exception as ex:
print("Exception in opening file: ", ex)
def test_environment_info(self):
self.assertEqual(tabula.environment_info(), None)
def test_environment_info(self):
self.assertEqual(tabula.environment_info(), None)
import tabula
#check your environment via tabula-py,which shows Python, Java #version, Java version, and your OS environment.
tabula.environment_info()
#
pdf_path = "G:\Shared drives\Agrigate\Data Analytics and Data Science\Research\Industry specs and knowledge\Fresh-Food-Trade-SA-2020.pdf"
# read pdf as CSV
tabula.convert_into(
pdf_path,
"G:\Shared drives\Agrigate\Data Analytics and Data Science\Research\Industry specs and knowledge\Fresh-Food-Trade-SA-2020.csv",
pages="all",
output_format="csv",
stream=True)
# # runtime: python37
# handlers:
# - url: /.*
# secure: always
# script: auto
from flask import Flask, render_template, request
import requests
from bs4 import BeautifulSoup
import re
import pandas as pd
from pandas import DataFrame
import tabula
test = tabula.environment_info()
print("TEST")
print(test)
import pygsheets
client = pygsheets.authorize(service_file="credentials.json")
sheet = client.open("COVID19_japan")
wks = sheet[0]
import pdfplumber
from io import BytesIO
import datetime
import json