def create_xlsx(pdf_path ,api_key):
try:
c = pdftables_api.Client(api_key)
c.xlsx(pdf_path, 'output')
except FileNotFoundError:
print("PDF Path is Invalid")
except pdftables_api.pdftables_api.APIException:
print("API Key was Invalid")
def convert_PDFtoExcel(a, b):
try:
conversion = api.Client('**********')
conversion.xlsx_multiple(a, b)
except:
print("Error - While converting Source file -" + a +
" from pdf to excel")
return b
def convert_pdf_to_excel(pdf_path):
c = pdftables_api.Client(API_KEY)
path, file = os.path.split(pdf_path)
excelfile = file.split(".")[-2]
excelfile_path = "./temp"
c.xlsx(pdf_path,excelfile_path+"/temporary")
return excelfile_path
def convert_pdf_to_excel(pdf_path):
c = pdftables_api.Client(API_KEY)
path, file = os.path.split(pdf_path)
excelfile = file.split(".")[-2]
excelfile_path = "/home/srinidhi/angular/extractor/temp"
c.xlsx(pdf_path, excelfile_path + "/temporary")
print(excelfile_path, "File Created")
return excelfile_path
def convertpdf_xml(request):
df = "./static/pdf/pdf.pdf"
filename = 'static/datascience/convertpdf/PDFdata_docx.xml'
c = pdftables_api.Client('sx112tn9r25e')
c.xml(df, filename)
download_name = "PDFdata_docx.xml"
wrapper = FileWrapper(open(filename))
response = HttpResponse(wrapper, content_type="text/xml; charset=utf-8")
response['Content-Disposition'] = "attachment; filename=%s" % download_name
return response
def convertpdf_csv(request):
df = "./static/pdf/pdf.pdf"
filename = 'static/datascience/convertpdf/PDFdata_csv.csv'
c = pdftables_api.Client('sx112tn9r25e')
c.csv(df, filename)
download_name = "PDFdata_csv.csv"
wrapper = FileWrapper(open(filename))
response = HttpResponse(wrapper, content_type='text/csv')
response['Content-Disposition'] = "attachment; filename=%s" % download_name
return response
def convert_pdfFiles_to_xlsx(src):
pdfFiles = []
path = os.path.join(src, "*.pdf")
for file in glob.glob(path):
pdfFiles.append(file)
ExcelFiles = []
print("PDF Files:", pdfFiles)
for file in pdfFiles:
c = pdftables_api.Client(my_pdftables_api_key)
#c.xlsx(file, file[0:len(file)-4]+'.xlsx')
ExcelFiles.append(file[0:len(file) - 4] + '.xlsx')
return ExcelFiles
def convertToCSV(key, inputFolder, outputFolder):
# Convert PDF to CSV with API
try:
import pdftables_api
# Make a list of all PDF files in input folder
paths = glob.glob(inputFolder + '/*.pdf')
print("CSVs count:", len(paths))
if len(paths) == 0:
print('Empty or wrong input folder')
return
for path in paths:
# Name is output folder plus name of file minus last 4 characters '.pdf'
name = outputFolder + path[len(inputFolder):-4]
c = pdftables_api.Client(key)
c.csv(path, name)
print(name)
except Exception as e:
print(e)
import pdftables_api
import os
dir = raw_input("Insert folder path: ")
for entry in os.listdir(dir):
if entry.endswith(".pdf"):
a = os.path.join(dir, entry)
b = os.path.join(dir, entry)
d = b.split(".pdf")[0]
c = pdftables_api.Client('5d8bp4bt79zt')
c.xlsx(a, d + ".xlsx")
print '"'+ entry +'"' , "Converted Successfully"
continue
else:
continue
print "Done!"
import pdftables_api
c = pdftables_api.Client('ctslevg3totv')
for i in range(4,20):
if (i<10):
string='0'+str(i)
else:
string=str(i)
c.xlsx('district'+string+'.pdf', 'output'+string+'.xlsx')
def pdfToExcel(d):
c = pdftables_api.Client('wa9l2jbtqv2t')
c.csv('"E:/4-1/Final Project/pdf/"+ d + ".pdf"',
'"E:/4-1/Final Project/csv/"+ d + ".csv"')
#Not sure why the package can't be used in pycharm but it works in IDLE
import pdftables_api
c = pdftables_api.Client('my_personal_API_code')
import os
os.chdir('/Users/jzalmano/Documents/') #FOLDER_PATH_GOES_HERE
#Change 'output' to be any name you want the excel spreadsheet to be named
#Change PDF_NAME_GOES_HERE to be whatever the name of the pdf is
c.xlsx('PDF_NAME_GOES_HERE.pdf', 'output')
import pdftables_api
c = pdftables_api.Client('e3j22hhxx0ic')
for i in range(1, 5):
if (i < 10):
string = '0' + str(i)
else:
string = str(i)
c.xlsx('district' + string + '.pdf', 'output' + string + '.xlsx')
"""
import os
import sys
base_path = tmp_global_obj["basepath"]
cur_path = base_path + 'modules' + os.sep + 'PDF2XLSX' + os.sep + 'libs' + os.sep
sys.path.append(cur_path)
import requests
import random
import pdftables_api
"""
Obtengo el modulo que fueron invocados
"""
module = GetParams("module")
if module == "pdftables":
pdf_file = GetParams("pdf")
path = GetParams("path")
api_key = GetParams("apikey")
if not path.endswith(".xlsx"):
path += ".xlsx"
try:
c = pdftables_api.Client(api_key)
c.xlsx(pdf_file, path)
except Exception as e:
PrintException()
raise e
import pdftables_api
c = pdftables_api.Client('emrssrlm10zx')
for i in range(1, 46):
if (i < 10):
string = '0' + str(i)
else:
string = str(i)
c.xlsx('district' + string + '.pdf', 'output' + string + '.xlsx')
import pdftables_api
c = pdftables_api.Client('ywjdw1ch1az9')
for i in range(22, 26):
if (i < 10):
string = '0' + str(i)
else:
string = str(i)
c.xlsx('district' + string + '.pdf', 'output' + string + '.xlsx')
import os
import pdftables_api
client = pdftables_api.Client('14tn2liiiei7')
for num, file in enumerate(os.listdir()):
if file.endswith('pdf'):
client.csv(file, 'fromsas_{}'.format(num))
else:
raise("There are no pdf files.")
import pdftables_api
c = pdftables_api.Client('2f8d5j4y33tv')
for i in range(9, 18):
if (i < 10):
string = '0' + str(i)
else:
string = str(i)
c.xlsx('district' + string + '.pdf', 'output' + string + '.xlsx')
import pandas as pd
import pdftables_api
import os
if not os.path.exists('test'):
os.makedirs('test')
if not os.path.exists('excel'):
os.makedirs('excel')
from parser_pdf import download_pdf
print("Файлы в формате pdf можете найти в папке test")
print("Файлы в формате xlsx можете найти в папке excel")
absdwdirname = os.path.abspath('test')
with open("settings.txt", 'r') as file:
f = file.read().split("\n")
key = f[0]
if key == '': key = '00xa7kk2eja9'
print("ключ", key)
c = pdftables_api.Client(key)
dfs = pd.read_excel('inn.xlsx')
for i in dfs['ИНН'].tolist():
if len(str(i)) == 12 or len(str(i)) == 10:
download_pdf(i)
print("Завершено скачивание pdf файлов...Начинаем преобразование в xlsx")
for filename in os.listdir(absdwdirname):
c.xlsx(os.path.join(absdwdirname, filename),
os.path.join('excel', filename[:len(filename) - 4]))
print("Процесс закончен!")
import pdftables_api
c = pdftables_api.Client('bfgu7mbg51q8')
for i in range(17,28):
if (i<10):
string='0'+str(i)
else:
string=str(i)
c.xlsx('district'+string+'.pdf', 'output'+string+'.xlsx')
#Code is for conversion of pdf file to excel file
import pdftables_api #importing module given by pdftables
import os
#Enter the path of the folder where all pdf file are stored
a=raw_input("Enter the path of the folder")
try:
c = pdftables_api.Client('zmll391gneyq')
file_path = a+"\\"
for file in os.listdir(file_path):
#If statement to find all the file in the folder with .pdf format
if file.endswith(".pdf"):
c.xlsx(os.path.join(file_path,file), file+'.xlsx')
#Except handling just to prevent any error in try statement regarding intalling gitbash or apikey
except Exception:
try:
c = pdftables_api.Client('mu5pqlmbcxzh')
file_path = a+"\\"
for file in os.listdir(file_path):
if file.endswith(".pdf"):
c.xlsx(os.path.join(file_path, file), file + '.xlsx')
except Exception:
try:
c = pdftables_api.Client('rk8wn6n8l98b')
file_path = a+"\\"
for file in os.listdir(file_path):
if file.endswith(".pdf"):
c.xlsx(os.path.join(file_path, file), file + '.xlsx')
except Exception:
try:
c = pdftables_api.Client('vchmq35pbbjy')
file_path = a+"\\"
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import time
import sys
sys.path.insert(0, 'libs')
import pdftables_api
import xlrd
import xlwt
c = pdftables_api.Client('fc9wow7u2a9c')
def crear_xlsx(banco):
c.xlsx(banco + '.pdf', 'xlsx/' + banco + '_output.xlsx')
def generar_banaci(banco):
try:
a = formatear_banaci(banco)
return a
except:
None
def formatear_banaci(banco):
try:
book = xlrd.open_workbook('xlsx/' + banco + '_output.xlsx')
sheet = book.sheet_by_index(2)
var = {}
for col in range(1, 10):
ind = limpiar_banaci(sheet.cell_value(1, col)).lower()
import pdftables_api
c = pdftables_api.Client('eqnu7qshno1h')
for i in range(3, 38):
if (i < 10):
string = '0' + str(i)
else:
string = str(i)
c.xlsx('district' + string + '.pdf', 'output' + string + '.xlsx')
import pdftables_api
c = pdftables_api.Client('rm20ic2hu1j1')
for i in range(1, 9):
if (i < 10):
string = '0' + str(i)
else:
string = str(i)
c.xlsx('district' + string + '.pdf', 'output' + string + '.xlsx')
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Thu Feb 20 04:53:02 2020
@author: snowden
"""
import pdftables_api
c.csv('/home/snowden/Downloads/1034-DEPENSES-2016.pdf',
'pgt-depenses-2016.csv')
#replace c.xlsx with c.csv to convert to CSV
#replace c.xlsx with c.xml to convert to XML
#replace c.xlsx with c.html to convert to HTML
i = 0
listOfPDF = ['', '']
for file in listOfPDF:
i += 1
c = pdftables_api.Client('83ile2qas3u3')
c.csv((file, 'file-{}').format(i))
import urllib.request
import pdftables_api
#fetching the pdf from the nsu site
pdf_path = "http://www.northsouth.edu/newassets/images/5-240.AcademicCalendarSpring%202021.pdf"
def download_file(download_url, filename):
response = urllib.request.urlopen(download_url)
file = open(filename + ".pdf", 'wb')
file.write(response.read())
file.close()
#Coverter Api that Converts the given Pdf into Xlxs
download_file(pdf_path, "Test")
c = pdftables_api.Client('9v1fb38u4aah')
c.xlsx('Test.pdf', 'output')
#replace c.xlsx with c.csv to convert to CSV
# Configuring google standard csv events.
#Google Calender Api imprt converted csv file.
import pdftables_api, requests
import os
# https://pdftables.com/pdf-to-excel-api
API_KEY = os.getenv('API_KEY')
convertor = pdftables_api.Client(API_KEY)
def remaining_conversions():
req = requests.get(f'https://pdftables.com/api/remaining?key={API_KEY}')
return f'{int(req.text)} pages available to convert'
def make_same_fileName(file_name):
splited_path = file_name.split('/')
primar_name = splited_path[-1]
splited_primar = primar_name.split('.')
if 'pdf' not in splited_primar:
raise ValueError("file extension must be pdf")
return splited_primar[0] + '.xlsx'
def convert_pdf_to_xlsl(pdf_path, xlsx_path):
name = make_same_fileName(pdf_path)
final_path = xlsx_path + name
convertor.xlsx(pdf_path, final_path)
print(f'Done. For this api_key remains {remaining_conversions()}')
return name
import pdftables_api
import os
c = pdftables_api.Client('API_KEYS')
file_path = "D:/RnE/xmltable/"
for file in os.listdir(file_path):
if file.endswith(".pdf"):
c.xml(os.path.join(file_path,file), file+'.xml')
import sys
# print(sys.argv[1])
import os
import pdftables_api #IMPORTANT LIBRARY
import time
print("Started Computer Vision To Analyaze PDF Files")
time.sleep(2)
dirs = os.listdir()
for file in dirs:
if (file.endswith('.pdf')):
print("Analyzing : ", file)
c = pdftables_api.Client('hksh1ytt3b6o') # MY API SECRET KEY
print("Generating Excel For : ", file)
time.sleep(2)
c.xlsx(file, file + '.xlsx') # FOR EXCEL
print("Generating XML For DataScience Enthusiasts : ", file)
time.sleep(2)
c.xml(file, file + '.xml') # FOR XML
# c.csv('main.pdf','output.csv') //IF YOU WANT CSV FILE UNCOMMENT THIS
# c.html('main.pdf','output.html') //IF YOU WANT HTML GILE UNCOMMENT THIS
os.system('mkdir files')
os.system("mv *.xlsx ./files/ && mv *.xml ./files/")
print("Making Final Zip File ")
time.sleep(3)
os.system("cd ./files && powershell Compress-Archive * final.zip")
print("Zip FIle Created With Name : final.zip")
print("[1]- To Open Zip File \n ")
print("[2]- To Email Zip File \n ")
option = int(
input("Please Choose An Option Given Above [Enter Integer Only] : \n"))
import pdftables_api
c = pdftables_api.Client('62cjalkbkgj6')
c.csv('pdf3-pages-5-6.pdf', 'output')
#replace c.xlsx with c.csv to convert to CSV
#replace c.xlsx with c.xml to convert to XML
#replace c.xlsx with c.html to convert to HTML