extract.py

from selenium import webdriver
from selenium.common.exceptions import WebDriverException
from PIL import Image
from io import BytesIO

import time

from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from bs4 import BeautifulSoup

def take_webdata(url):
    options = webdriver.ChromeOptions()
    options.add_argument('--headless')
    options.add_argument('--no-sandbox')
    options.add_argument('--disable-dev-shm-usage')

    try:
        wd = webdriver.Chrome(options=options)
        wd.set_window_size(1080, 720)  # Adjust the window size here
        wd.get(url)
        wd.implicitly_wait(5)
        # Get the page title
        page_title = wd.title
        screenshot = wd.get_screenshot_as_png()

    except WebDriverException as e:
        return Image.new('RGB', (1, 1)), page_title
    finally:
        if wd:
            wd.quit()

    return Image.open(BytesIO(screenshot)) , page_title


def scrape_vehicle(page_source):
    soup = BeautifulSoup(page_source, "html.parser")
    data_kendaraan = {}
    table = soup.find("table")
    for row in table.find_all("tr"):
        cells = row.find_all("td")
        if len(cells) >= 3:
            key = cells[0].get_text(strip=True).lower().replace(".", "").replace(" ", "_")
            value = cells[2].get_text(strip=True)
            data_kendaraan[key] = value
    
    rincians = []
    rincian_div = soup.find("div", id="det_pkb")
    if rincian_div:
        rows = rincian_div.find_all("div", class_="row")
        for row in rows[1:]:  # baris pertama adalah header
            cols = row.find_all("p")
            if len(cols) >= 3:
                rincian = {
                    "pokok": cols[0].get_text(strip=True),
                    "denda": cols[1].get_text(strip=True),
                    "total": cols[2].get_text(strip=True),
                }
                rincian["jenis"] = cols[3].get_text(strip=True) if len(cols) > 3 else ""
                rincian["jenis"] = rincian["jenis"].upper()
                rincian = {k: v for k, v in rincian.items() if v}
                if rincian:
                    rincians.append(rincian)

    return data_kendaraan, rincians


def get_vehicle_info(plate_number: str):
    # Configure headless Chrome
    options = webdriver.ChromeOptions()
    options.add_argument("--headless")
    options.add_argument("--disable-gpu")
    options.add_argument("--no-sandbox")

    # Path to chromedriver (adjust if needed)
    driver = webdriver.Chrome(options=options)

    try:    
        driver.get("https://www.jambisamsat.net/infopkb.html")
        time.sleep(1)

        WebDriverWait(driver, 10).until(
            EC.presence_of_element_located((By.ID, "no_polisi"))
        )

        input_field = driver.find_element(By.ID, "no_polisi")
        input_field.clear()
        input_field.send_keys(plate_number)

        submit_button = driver.find_element(By.CSS_SELECTOR, 'button.btn.btn-primary[type="submit"]')
        submit_button.click()

        # Wait for the new page to load
        WebDriverWait(driver, 10).until(
            EC.url_contains("infopkb.php")
        )

        driver.implicitly_wait(3)
        
        scroll_height = driver.execute_script("return document.body.scrollHeight")
        driver.set_window_size(1920, scroll_height + 200)  # force full-page height
        time.sleep(1)

        data_kendaraan, rincian = scrape_vehicle(driver.page_source)

        print(data_kendaraan, rincian)

        page_title = driver.title
        screenshot = driver.get_screenshot_as_png()

        return Image.open(BytesIO(screenshot)) , page_title

    except WebDriverException as e:
        return Image.new('RGB', (1, 1)), page_title

    finally:
        driver.quit()