Retrieve Image as a BLOB from MySQL Table using Python

 # Import the required modules
import mysql.connector
import base64
from PIL import Image
import io

# For security reasons, never expose your password
#password = open('password','r').readline()

# Create a connection
mydb = mysql.connector.connect(
host="host",
user="suriyaparithy",
password="suriyaparithy",
database="database" # Name of the database
)

# Create a cursor object
cursor = mydb.cursor()

# Prepare the query
query = 'SELECT PICTURE FROM PROFILE WHERE ID=100'

# Execute the query to get the file
cursor.execute(query)
data = cursor.fetchall()

# The returned data will be a list of list
image = data[0][0]

# Decode the string
binary_data = base64.b64decode(image)

# Convert the bytes into a PIL image
image = Image.open(io.BytesIO(binary_data))

# Display the image
image.show()

👋 Hi, I'm Suriya — QA Engineer with 4+ years of experience in manual, API & automation testing.

📬 Contact Me | LinkedIn | GitHub

📌 Follow for: Real-Time Test Cases, Bug Reports, Selenium Frameworks.

Image File stored as a BLOB in MySQL Table using Python

 # Import the required modules
import mysql.connector
import base64
from PIL import Image
import io

# Create a connection
mydb = mysql.connector.connect(
host="localhost",
user="suriyaparithy",
password="suriyaparithy",
database="database" # Name of the database
)

# Create a cursor object
cursor = mydb.cursor()

# Open a file in binary mode
file = open('chemical.PNG','rb').read()

# We must encode the file to get base64 string
file = base64.b64encode(file)

# Sample data to be inserted
args = ('100', 'Sample Name', file)

# Prepare a query
query = 'INSERT INTO PROFILE VALUES(%s, %s, %s)'

# Execute the query and commit the database.
cursor.execute(query,args)
mydb.commit()

👋 Hi, I'm Suriya — QA Engineer with 4+ years of experience in manual, API & automation testing.

📬 Contact Me | LinkedIn | GitHub

📌 Follow for: Real-Time Test Cases, Bug Reports, Selenium Frameworks.

Extract text from a single image using Python

#Extract text from a single image using Python
from PIL import Image
from pytesseract import pytesseract

#Define path to tessaract.exe
path_to_tesseract = r'C:\Program Files\Tesseract-OCR\tesseract.exe'

#Define path to image
path_to_image = 'chemical.PNG'

#Point tessaract_cmd to tessaract.exe
pytesseract.tesseract_cmd = path_to_tesseract

#Open image with PIL
img = Image.open(path_to_image)

#Extract text from image
text = pytesseract.image_to_string(img)
print(text)

👋 Hi, I'm Suriya — QA Engineer with 4+ years of experience in manual, API & automation testing.

📬 Contact Me | LinkedIn | GitHub

📌 Follow for: Real-Time Test Cases, Bug Reports, Selenium Frameworks.

Extract only images from PDF using Python

 # How to Extract Images from PDF in Python
import fitz # PyMuPDF
import io
from PIL import Image

# file path you want to extract images from
file = "byju.pdf"

# open the file
pdf_file = fitz.open(file)

# iterate over PDF pages
for page_index in range(len(pdf_file)):

    # get the page itself
    page = pdf_file[page_index]
    image_list = page.get_images()

    # printing number of images found in this page
    if image_list:
        print(f"[+] Found a total of {len(image_list)} images in page {page_index}")
    else:
        print("[!] No images found on page", page_index)
    for image_index, img in enumerate(page.get_images(), start=1):

        # get the XREF of the image
        xref = img[0]

        # extract the image bytes
        base_image = pdf_file.extract_image(xref)
        image_bytes = base_image["image"]

        # get the image extension
        image_ext = base_image["ext"]

        # load it to PIL
        image = Image.open(io.BytesIO(image_bytes))

        # save it to local disk
        image.save(open(f"image{page_index+1}_{image_index}.{image_ext}", "wb"))

👋 Hi, I'm Suriya — QA Engineer with 4+ years of experience in manual, API & automation testing.

📬 Contact Me | LinkedIn | GitHub

📌 Follow for: Real-Time Test Cases, Bug Reports, Selenium Frameworks.

Extract text and image from PDF files in python

# Module Imports
import os
from PIL import Image
import pytesseract
from pdf2image import convert_from_path

# Define Paths
poppler_path = r'C:\Program Files\poppler-0.68.0\poppler-0.68.0\bin'
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract'
pdf_path = "chemistry.pdf"

# Save PDF pages to images
images = convert_from_path(pdf_path=pdf_path, poppler_path=poppler_path)
for count, img in enumerate(images):
    img_name = f"page_{count}.png"  
    img.save(img_name, "png")

# Extract Text
png_files = [f for f in os.listdir(".") if f.endswith(".png")]
for png_file in png_files:
    extracted_text = pytesseract.image_to_string(Image.open(png_file))
    print(extracted_text)

Reference - https://www.gcptutorials.com/post/python-extract-text-from-pdf-files 

👋 Hi, I'm Suriya — QA Engineer with 4+ years of experience in manual, API & automation testing.

📬 Contact Me | LinkedIn | GitHub

📌 Follow for: Real-Time Test Cases, Bug Reports, Selenium Frameworks.