Python Projects & Free Books

pip install PyPDF2

import PyPDF2

# https://t.me/pythonfreebootcamp

pdf_file = 'sample.pdf'
with open(pdf_file, 'rb') as file:
    reader = PyPDF2.PdfFileReader(file)
    text = ''
    for page_num in range(reader.numPages):
        page = reader.getPage(page_num)
        text += page.extractText()

print(text)

import pytesseract as t
from PIL import Image
img = Image.open("photo.jpg")
text = t.image_to_string(img)
print(text)

# Create two lists
names = ["John", "Mary", "Bob"]
ages = [30, 25, 40]

# Iterate over both lists using zip()
for name, age in zip(names, ages):
    print(f"{name} is {age} years old.")

boy={"ram":70,"Sundar":80}

girl={"riya":80,"Sonali":70}

student=boy | girl

print(student)

import requests
from bs4 import BeautifulSoup as BSP

def split_url(url):
    return url.split('&')[0]

def get_image_urls(search_query):
    url = f"https://cn.bing.com/images/search?q={search_query}&first=1&cw=1177&ch=678"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3"
    }
    rss = requests.get(url, headers=headers)
    soup = BSP(rss.content, "html.parser")

    all_img = []
    for img in soup.find_all('img'):
        img_url = img.get('src2')
        if img_url and img_url.startswith('https://tse2.mm.bing.net/'):
            img_url = split_url(img_url)
            all_img.append(img_url)

    return all_img

print(get_image_urls("cat"))

['https://tse2.mm.bing.net/th?q=Cat+Portrait', ...']

import requests
from bs4 import BeautifulSoup as BSP

def get_image_urls(search_query):
    url = f"https://www.google.com/search?q={search_query}&tbm=isch"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3"
    }
    rss = requests.get(url, headers=headers)
    soup = BSP(rss.content, "html.parser")

    all_img = []
    for img in soup.find_all('img'):
        src = img['src']
        if not src.endswith("gif"):
            all_img.append(src)

    return all_img

print(get_image_urls("boy"))