selenium_print.py

import time
from selenium import webdriver
from selenium.webdriver.firefox.options import Options
from PIL import Image
import cv2
options = Options()
options.headless = True

driver = webdriver.Firefox(
    executable_path=r"C:\Users\sasid\Downloads\geckodriver.exe", options=options)
URL = 'http://properties.inspecthoa.com/3080-21st-St-Long-Island-City-NY-11102'
final_list = []
driver.maximize_window()
driver.get(URL)


def get_concat_v(im1, im2):
    dst = Image.new('RGB', (im1.width, im1.height + im2.height))
    dst.paste(im1, (0, 0))
    dst.paste(im2, (0, im1.height))
    return dst


def standardize(pil_img, logo=None):
    border = 50

    paste_x = border
    paste_y = border
    logo_x = 3170
    logo_y = 2380

    img_width, img_height = pil_img.size

    width, height = 3508 - border*2, 2480 - border*2

    wpercent = (width/float(img_width))
    img_height = int((float(img_height)*float(wpercent)))
    img_width = width

    if img_height > height:
        hpercent = float(height/float(img_height))
        img_width = int((float(img_width)*float(hpercent)))

        img_height = height

    paste_x = border + int(float(width - img_width)/2)
    paste_y = border  # + int(float(height - img_height)/2)

    pil_img = pil_img.resize((img_width, img_height),  resample=Image.LANCZOS)
    result = Image.new(pil_img.mode, (width + border*2,
                                      height + border*2), (255, 255, 255, 255))

    result.paste(pil_img, (paste_x, paste_y))
    if logo is not None:
        result.paste(logo, (logo_x, logo_y))

    return result


def get_images(link):
    pdf_file_name = link.strip('/').split('/')[-1]+".pdf"
    ihoa_summary = driver.find_element_by_xpath(
        '/html/body/div/main/div[1]/section/div/div[1]').screenshot_as_png
    final_list.append(ihoa_summary)
    time.sleep(5)
    # click finances
    driver.find_element_by_xpath(
        '/html/body/div/main/div[1]/section/div/div[3]/div[1]/div[1]/button/span[1]').click()
    time.sleep(5)
    finances_summary = driver.find_element_by_xpath(
        '/html/body/div/main/div[1]/section/div/div[3]/div[3]/section/div').screenshot_as_png
    final_list.append(finances_summary)
    # fees click
    driver.find_element_by_xpath(
        '/html/body/div/main/div[1]/section/div/div[3]/div[2]/div/div[2]/button').click()
    time.sleep(5)
    fee_one = driver.find_element_by_xpath(
        '//*[@id="root"]/main/div[1]/section/div/div[3]/div[3]/section/div/div[1]').screenshot_as_png
    final_list.append(fee_one)
    fee_two = driver.find_element_by_xpath(
        '//*[@id="root"]/main/div[1]/section/div/div[3]/div[3]/section/div/div[2]/div').screenshot_as_png
    final_list.append(fee_two)
    # expences click
    driver.find_element_by_xpath(
        '/html/body/div/main/div[1]/section/div/div[3]/div[2]/div/div[3]/button').click()
    time.sleep(5)
    exp_1 = driver.find_element_by_xpath(
        '//*[@id="root"]/main/div[1]/section/div/div[3]/div[3]/section/div/div[1]').screenshot_as_png
    final_list.append(exp_1)
    exp_2 = driver.find_element_by_xpath(
        '//*[@id="root"]/main/div[1]/section/div/div[3]/div[3]/section/div/div[2]').screenshot_as_png
    final_list.append(exp_2)
    # reserver click
    driver.find_element_by_xpath(
        '/html/body/div/main/div[1]/section/div/div[3]/div[2]/div/div[4]/button').click()
    time.sleep(5)
    res_1 = driver.find_element_by_xpath(
        '//*[@id="root"]/main/div[1]/section/div/div[3]/div[3]/section/div/div[1]').screenshot_as_png
    final_list.append(res_1)
    res_2 = driver.find_element_by_xpath(
        '//*[@id="root"]/main/div[1]/section/div/div[3]/div[3]/section/div/div[2]').screenshot_as_png
    final_list.append(res_2)

    # bylaws_click
    driver.find_element_by_xpath(
        '/html/body/div/main/div[1]/section/div/div[3]/div[1]/div[2]/button').click()
    time.sleep(5)
    driver.find_element_by_xpath(
        '//*[@id="root"]/main/div[1]/section/div/div[3]/div[2]/div/div[2]/button').click()
    time.sleep(5)
    must_know = driver.find_element_by_xpath(
        '//*[@id="root"]/main/div[1]/section/div/div[3]/div[3]/section/div').screenshot_as_png
    final_list.append(must_know)
    driver.find_element_by_xpath(
        '//*[@id="root"]/main/div[1]/section/div/div[3]/div[2]/div/div[3]/button').click()
    time.sleep(5)
    good_to_know = driver.find_element_by_xpath(
        '//*[@id="root"]/main/div[1]/section/div/div[3]/div[3]/section/div/div').screenshot_as_png
    final_list.append(good_to_know)
    # operations
    driver.find_element_by_xpath(
        '/html/body/div/main/div[1]/section/div/div[3]/div[1]/div[3]/button').click()
    time.sleep(5)
    driver.find_element_by_xpath(
        '/html/body/div/main/div[1]/section/div/div[3]/div[2]/div/div/button').click()
    time.sleep(5)
    operations = driver.find_element_by_xpath(
        '/html/body/div/main/div[1]/section/div/div[3]/div[3]/section/div/div')
    total_height = operations.size['height']+1000
    driver.set_window_size(1920, total_height)
    time.sleep(2)
    driver.save_screenshot('operations_screenshot.png')
    img_one = cv2.imread('operations_screenshot.png')
    print(img_one.shape)
    height_one = img_one.shape[0]
    width_one = img_one.shape[1]

    # Cut the image in half
    height_cutoff = height_one // 2 - 50
    print(height_cutoff)

    s1 = img_one[:height_cutoff, :]
    s2 = img_one[height_cutoff:, :]

    #cv2.imwrite("top_part.png", s1)
    cv2.imwrite("operations_half.png", s2)

    # financing
    driver.find_element_by_xpath(
        '/html/body/div/main/div[1]/section/div/div[3]/div[1]/div[4]/button').click()
    time.sleep(5)
    operations = driver.find_element_by_xpath(
        '/html/body/div/main/div[1]/section/div/div[3]')
    total_height = operations.size['height']+700
    driver.set_window_size(1920, total_height)
    time.sleep(2)
    driver.save_screenshot('financing_screenshot.png')
    # Read the image
    img = cv2.imread('financing_screenshot.png')
    # print(img.shape)
    height = img.shape[0]
    #width = img.shape[1]

    # Cut the image in half
    height_cutoff = (height // 2) - 75
    # print(height_cutoff)

    s1 = img[:height_cutoff, :]
    s2 = img[height_cutoff:, :]

    #cv2.imwrite("top_part.png", s1)
    cv2.imwrite("financing_half.png", s2)

    count = 0
    for i in final_list:
        filename = '{}.png'.format(count)
        count += 1
        with open(filename, 'wb') as f:
            f.write(i)

    im_list = []
    widt = Image.open('1.png').width
    one = Image.open('0.png')
    one = one.resize((widt, one.height))
    one.save('0.png')

    logo = Image.open('hoa_logo.png')
    for i in range(0, count):
        im = Image.open(str(i)+'.png').convert('RGB')
        if i > 7:
            im_list.append(standardize(im, logo))
        else:
            im_list.append(im)
    oper_img = Image.open('operations_half.png').convert('RGB')
    fin_img = Image.open('financing_half.png').convert('RGB')
    im_list.append(standardize(oper_img, logo))
    im_list.append(standardize(fin_img, logo))
    im1 = standardize(get_concat_v(im_list[0], im_list[1]), logo)
    im2 = standardize(get_concat_v(im_list[2], im_list[3]), logo)
    im3 = standardize(get_concat_v(im_list[4], im_list[5]), logo)
    im4 = standardize(get_concat_v(im_list[6], im_list[7]), logo)
    listtwo = [im1, im2, im3, im4]
    listtwo.extend(im_list[8:])

    im1.save("tmp/"+pdf_file_name, "PDF", resolution=150, quality=70,
             optimize=True, save_all=True, append_images=listtwo[1:])

    print('Image saved at tmp/{}'.format(pdf_file_name))


get_images(URL)