aliexpress-one-price-parser/aliexpress-one-price-parser.py

#!/usr/bin/python3

import warnings
warnings.filterwarnings("ignore", message="python-telegram-bot is using upstream urllib3")

import time
import sys
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By
from bs4 import BeautifulSoup
from telegram import Bot, InputMediaPhoto
from collections import defaultdict

# Telegram Bot Token and Chat ID
TELEGRAM_BOT_TOKEN = ""
TELEGRAM_CHAT_ID = ""

# Function to ensure URLs start with "https://"
def format_url(url):
    if url.startswith("//"):
        return f"https:{url}"
    elif not url.startswith(("http://", "https://")):
        return f"https://{url}"
    return url

# Function to scroll the page a fixed number of times
def scroll_page(driver, scroll_pause_time=5):  # Increased wait time
    for _ in range(50):
        driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
        time.sleep(scroll_pause_time)

# Function to save fully rendered HTML to a file for debugging
def save_rendered_html(driver, filename="debug.html"):
    rendered_html = driver.execute_script("return document.documentElement.outerHTML;")
    with open(filename, "w", encoding="utf-8") as file:
        file.write(rendered_html)
    print(f"Fully rendered HTML saved to {filename}")

# Function to search for the word in the `alt` attribute and group `data-src` by `alt` text
def search_word_in_alt_tags(driver, word):
    rendered_html = driver.execute_script("return document.documentElement.outerHTML;")
    save_rendered_html(driver)

    soup = BeautifulSoup(rendered_html, 'html.parser')
    alt_to_data_src = defaultdict(list)

    img_tags = soup.find_all('img', alt=True)
    for img in img_tags:
        alt_text = img.get('alt', '').lower()
        if word.lower() in alt_text:
            data_src = img.get('data-src')
            if data_src:
                data_src = format_url(data_src)
                alt_to_data_src[alt_text].append(data_src)

    return alt_to_data_src

# Function to send media group to Telegram (limit to 10 photos)
def send_to_telegram(alt_text, data_src_list):
    bot = Bot(token=TELEGRAM_BOT_TOKEN)
    data_src_list = data_src_list[:10]

    media_group = []
    for index, data_src in enumerate(data_src_list):
        media = InputMediaPhoto(media=data_src, caption=alt_text if index == 0 else "")
        media_group.append(media)

    bot.send_media_group(chat_id=TELEGRAM_CHAT_ID, media=media_group)
    print(f"Sent {len(media_group)} image(s) with alt text: '{alt_text}'")

# Main function
def main(url, word):
    # Set up Chrome options for headless mode
    chrome_options = Options()
    chrome_options.add_argument("--headless")
    chrome_options.add_argument("--disable-gpu")
    chrome_options.add_argument("--no-sandbox")
    chrome_options.add_argument("--disable-dev-shm-usage")
    chrome_options.add_argument("--user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36")
    chrome_options.add_argument("--disable-blink-features=AutomationControlled")
    chrome_options.add_experimental_option("excludeSwitches", ["enable-automation"])
    chrome_options.add_experimental_option("useAutomationExtension", False)

    # Set up the WebDriver with headless options
    driver = webdriver.Chrome(options=chrome_options)

    try:
        driver.get(url)
        scroll_page(driver)

        alt_to_data_src = search_word_in_alt_tags(driver, word)
        if alt_to_data_src:
            print(f"Found {len(alt_to_data_src)} unique alt text(s) containing the word '{word}'.")
            for alt_text, data_src_list in alt_to_data_src.items():
                send_to_telegram(alt_text, data_src_list)
        else:
            print(f"The word '{word}' was not found in any alt attributes after scrolling 50 pages.")

    finally:
        driver.quit()

if __name__ == "__main__":
    if len(sys.argv) != 3:
        print("Usage: python script.py <url> <word_to_search>")
        sys.exit(1)

    url = sys.argv[1]
    word_to_search = sys.argv[2]

    if not url.startswith(("http://", "https://")):
        url = "https://" + url

    main(url, word_to_search)