raghavendrajain

from flask import Flask, render_template, g, redirect, url_for
from flask_oidc import OpenIDConnect
from okta import UsersClient, UserGroupsClient
import requests
from oauth2client.client import OAuth2Credentials
import json

app = Flask(__name__)

app.config.update({

raghavendrajain

import pandas as pd
import os
df = pd.read_csv('Flight-1-export.csv')
df["label"] = df["label"].str.lower()
groups = df.groupby(['image', "xmin", "ymin", "xmax", "ymax"]).groups
group_values = list(groups.values())
grouped_indices = list(map(lambda x: x.to_list(), group_values))
for index in grouped_indices:
    df.loc[index[0], "labels"] = ",".join([df.loc[idx, "label"] for idx in index])
    

raghavendrajain

import jupyterlab_dash
import dash
import dash_html_components as html
import dash_core_components as dcc
import dash_table as dt
import pandas as pd
import pickle

from dash.dependencies import Input, Output, State

raghavendrajain

# Code snippet posted on OpenCV website. 
# Jain tested on Ubuntu 18.04. 
# For windows, follow this blog https://www.codepool.biz/web-camera-recorder-oepncv-flask.html
import numpy as np
import cv2
 
cap = cv2.VideoCapture(0)
 
# Define the codec and create VideoWriter object
fourcc = cv2.VideoWriter_fourcc(*'XVID')

raghavendrajain

raghavendrajain

Check if result_ext folder exists inside the folder. If not make the folder
Read the original file
Unlock the file in all cases, even if it is unlocked. It is fairly inexpensive operation.
Split the files. Each page is separated into a temporary file.
Read from each of the split file into a dataframe and then delete that file.
If the page has table then read it from the dataframe and extract the data. Camelot is used to do that.
Read all the text using Tika.
Split the text based on newline character. This will give many lists. Use regular expression to get lists that begin with 4 digits.
Concatenate all the dataframes .
Save all the concatenated dataframes into a final dataframe if the number of columns is 10.

raghavendrajain

import tika
tika.initVM()
from tika import parser
import camelot
import pandas as pd
import re

#filename = "Sample3_unconsolidated.pdf"
filename = "Sample3_consolidated.pdf"

raghavendrajain

#install camelot or something like that for using PyPDF2

from PyPDF2 import PdfFileWriter, PdfFileReader

inputpdf = PdfFileReader(open("1_extractable.pdf", "rb"))

for i in range(inputpdf.numPages):
    output = PdfFileWriter()
    output.addPage(inputpdf.getPage(i))
    with open("document-page%s.pdf" % i, "wb") as outputStream:

raghavendrajain

# install pikepdf using `pip install pikepdf`

import pikepdf

pdf = pikepdf.open('unextractable.pdf')
pdf.save('extractable.pdf')

raghavendrajain

// pull down jquery into the JavaScript console
var script = document.createElement('script');
script.src = "https://ajax.googleapis.com/ajax/libs/jquery/2.2.0/jquery.min.js";
document.getElementsByTagName('head')[0].appendChild(script);
// grab the URLs
var urls = $('.rg_di .rg_meta').map(function() { return JSON.parse($(this).text()).ou; });
// write the URls to file (one per line)
var textToSave = urls.toArray().join('\n');
var hiddenElement = document.createElement('a');
hiddenElement.href = 'data:attachment/text,' + encodeURI(textToSave);