Install Latest ImageMagick to support PNG, JPG convertions

 #These are the steps required in order to Install ImageMagick with JPG, PNG and TIFF delegates.

sudo apt-get update 

#Install Build-Essential in order to configure and make the final Install

sudo apt-get install build-essential 

#libjpg62-dev required in order to work with basic JPG files

sudo apt-get install -y libjpeg62-dev 

#libtiff-dev is required in order to work with TIFF file format

sudo apt-get install -y libtiff-dev 

#libpng-dev required in order to work with basic PNG files

sudo apt-get install -y libpng-dev

#Download ImageMagick

wget https://www.imagemagick.org/download/ImageMagick.tar.gz 

#Untar Imagemagick

tar xvzf ImageMagick.tar.gz 

#Access the working directory

cd ImageMagick-[version_number] 

#Configure and make sure to disable the "shared" option

./configure --disable-shared

#Make

sudo make

#Install

sudo make install

#Final Check

sudo make check

Python - Image to Pdf

1. Install img2pdf

> pip/pip3 install img2pdf

2. img2pdfown.py

# importing necessary libraries

import img2pdf

from PIL import Image

import os

  

# CLI  img2pdf *jpg -o output_all_pngs.pdf

'''

img_path = "image1.jpg";

pdf_path = "output.pdf";

image = Image.open(img_path);

pdf_bytes = img2pdf.convert(image.filename);

file = open(pdf_path, "wb");

file.write(pdf_bytes);

image.close();

file.close();

'''

# convert all files ending in .jpg inside a directory

dirname = "dump/images/"

imgs = []

#dpix = dpiy = 300;

#layout_fun = img2pdf.get_fixed_dpi_layout_fun((dpix, dpiy))

for fname in os.listdir(dirname):

    if not fname.endswith(".jpg"):

        continue

    path = os.path.join(dirname, fname)

    if os.path.isdir(path):

        continue

    imgs.append(path)

    print ("\n" + path);

with open("dump/output.pdf", "wb") as f:

    #f.write(img2pdf.convert(imgs, layout_fun=layout_fun));

    f.write(img2pdf.convert(imgs));

  

'''    

imgs = ['dump/images/page_1.jpg', 'dump/images/page_2.jpg', 'dump/images/page_10.jpg']

with open("dump/output1.pdf", "wb") as f:

    f.write(img2pdf.convert(imgs))

# specify paper size (A4)

a4inpt = (img2pdf.mm_to_pt(210), img2pdf.mm_to_pt(297))

layout_fun = img2pdf.get_layout_fun(a4inpt)

with open("name.pdf", "wb") as f:

    f.write(img2pdf.convert('test.jpg', layout_fun=layout_fun))

# use a fixed dpi of 300 instead of reading it from the image

dpix = dpiy = 300;

layout_fun = img2pdf.get_fixed_dpi_layout_fun((dpix, dpiy))

with open("name.pdf", "wb") as f:

    f.write(img2pdf.convert('test.jpg', layout_fun=layout_fun))

# create a PDF/A-1b compliant document by passing an ICC profile

with open("name.pdf", "wb") as f:

    f.write(img2pdf.convert('test.jpg', pdfa="/usr/share/color/icc/sRGB.icc"))    

'''

    

Pytesseract Read a image and labeled or Rename as filename

pytesseract_image.py

import cv2
import os
import pytesseract
try:
    from PIL import Image
except ImportError:
    import Image

pytesseract.pytesseract.tesseract_cmd = 'C:/Program Files/Tesseract-OCR/tesseract.exe'

#for x in range (1,1000): 
#    img_cv = cv2.imread(r'D:/Temp/Captcha/program/'+ str(x) + '.png')

folderpath = "D:/Temp/Captcha/program/"
for filename in os.listdir(folderpath):   
    img_cv = cv2.imread(r'D:/Temp/Captcha/program/'+ filename )
    # By default OpenCV stores images in BGR format and since pytesseract assumes RGB format,
    # we need to convert from BGR to RGB format/mode:
    img_rgb = cv2.cvtColor(img_cv, cv2.COLOR_BGR2RGB)
    imagetext = pytesseract.image_to_string(img_rgb)
    print (imagetext)
    # OR
    #img_rgb = Image.frombytes('RGB', img_cv.shape[:2], img_cv, 'raw', 'BGR', 0, 0)
    #imagetext = pytesseract.image_to_string(img_rgb)
    #print (imagetext)
    src =folderpath+ filename
    dst =folderpath+ imagetext + ".png"
    os.rename(src, dst)


NOTE:
save filenmae other than pytesseract.py - Note: to avoid pytesseract.image_to_string not found error

AttributeError: module 'pytesseract' has no attribute 'image_to_string'

may be your python file name itself "pytesseract,py"

kindly rename it to new name like pytes_ex.py.


--Enjoy

JSoup - HTML Parser for image audio video attributes

SAMPLE

package com.jsoup;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.safety.Whitelist;
import org.jsoup.select.Elements;

public class HtmlParser
{
public static String html = "<html><head><title>Sample Title</title></head>"
         + "<body>"
         + "<p>Sample Content1</p>"              
         + "<img name='pic1' id='picid1' src='test.jpg' />"  
         + "<p>Sample Content2</p>"
         + "<p>Sample Content3</p>"
         + "<img name='pic2' id='picid2' src='test2.jpg' />"
         + "<video width='320' height='240' controls>"
        + "<source id='1' src='movie.mp4' type='video/mp4'>"
        + " <source  id='2' src='movie.ogg' type='video/ogg'>"
        + "<Br/>Your browser does not support the video tag."
        + "</video>"
        + "<audio controls>"
        + "<source id='1' src='horse.ogg' type='audio/ogg'>"
        + "<source id='2' src='horse.mp3' type='audio/mpeg'>"
        + "<Br/>Your browser does not support the audio tag."
        + "</audio>"
        + "<p><a href='http://example.com/'" + " onclick='checkData()'>Link</a></p>"
         +"</body></html>";


/*output
Initial HTML: <p><a href='http://example.com/' onclick='checkData()'>Link</a></p>
Cleaned HTML: <p><a href="http://example.com/" rel="nofollow">Link</a></p>*/
public static void safeGuardHtmlSanitize ()
{
System.out.println ( "Initial HTML: " + html );
String safeHtml = Jsoup.clean ( html, Whitelist.basic () );
System.out.println ( "Cleaned HTML: " + safeHtml );
}

public static void main ( String [] args )
{

Document document = Jsoup.parse ( html );
// img with src ending .png
Elements imgs = document.select ( "img" );
for ( Element img : imgs )
{
System.out.println ( "Name: " + img.attr ( "name" ) + " id: " + img.id () + " src: " + img.attr ( "src" ) );
//to replace the value existing
img.attr ( "src", "replacedImage.jpg" ) ;
}
System.out.println ( "\n\n" );

Elements videos = document.select ( "video" );
Elements videoSrc = videos.select ( "source" );
for ( Element vSrc : videoSrc )
{
System.out.println ( " id: " + vSrc.id () + " src: " + vSrc.attr ( "src" ) + " type: " + vSrc.attr ( "type" ));
}
System.out.println ( "\n\n" );

Elements audios = document.select ( "audio" );
Elements audioSrc = audios.select ( "source" );
for ( Element aSrc : audioSrc )
{
System.out.println ( " id: " + aSrc.id () + " src: " + aSrc.attr ( "src" ) + " type: " + aSrc.attr ( "type" ));
}
System.out.println ( "\n\n" );

safeGuardHtmlSanitize();
}
}

OUTPUT

Name: pic1 id: picid1 src: test.jpg
Name: pic2 id: picid2 src: test2.jpg



 id: 1 src: movie.mp4 type: video/mp4
 id: 2 src: movie.ogg type: video/ogg



 id: 1 src: horse.ogg type: audio/ogg
 id: 2 src: horse.mp3 type: audio/mpeg



Initial HTML: Sample Content1
Sample Content2
Sample Content3
Link
Cleaned HTML: Sample Title
Sample Content1
Sample Content2
Sample Content3


Your browser does not support the video tag.

Your browser does not support the audio tag.
Link