b2bcenter-parser/main.py

import pathlib
import time
import re
from typing import Self

from selenium.webdriver import Keys
from selenium.webdriver.common.by import By
from  webdriver_manager.chrome import ChromeDriverManager
from selenium import webdriver
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import NoSuchElementException, TimeoutException


class Parser:
    keyword = "Велесстрой"
    url = "https://www.b2b-center.ru/market"

    _driver: webdriver.Chrome
    _options: webdriver.ChromeOptions = webdriver.ChromeOptions()
    _service: webdriver.ChromeService

    def __init__(self):
        prefs = {"download.default_directory": str(pathlib.Path('./downloads').absolute())};
        self._options.add_experimental_option("prefs", prefs)
        self._options.add_argument("--disable-extensions")
        self._options.add_argument("--disable-gpu")
        self._options.add_argument("--headless=new")
        self._service = webdriver.ChromeService(executable_path=ChromeDriverManager().install())

    def __enter__(self) -> Self:
        self._driver = webdriver.Chrome(service=self._service, options=self._options)
        return self

    def __exit__(self, exc_type, exc_val, exc_tb):
        print("Gracefully shutting down...")
        self._driver.close()

    def find_elem(self, by: str, value: str):
        try:
            return WebDriverWait(self._driver, 10).until(EC.presence_of_element_located((by, value)))
        except TimeoutException:
            raise NoSuchElementException("Element not found")

    def login(self):
        self._driver.get(self.url)

        time.sleep(3)
        # Open login modal
        element = self.find_elem(By.ID, "auth_ajax_modal_trigger")
        element.click()

        login_control = self.find_elem(By.ID, "login_control")
        password_control = self.find_elem(By.ID, "password_control")

        login_control.click()
        login_control.clear()
        login_control.send_keys("jde2015")

        password_control.click()
        password_control.clear()
        password_control.send_keys("Bel8#Ans3")
        time.sleep(5)
        password_control.send_keys(Keys.RETURN)

    def search(self):
        time.sleep(5)
        self._driver.get(self.url + f'/?f_keyword={self.keyword}')
        time.sleep(10)
        table = self.find_elem(By.CSS_SELECTOR, ".search-results > tbody")
        links = table.find_elements(By.CSS_SELECTOR, "tr > td:nth-child(1) > a")
        for link in links:
            href = link.get_attribute("href")
            description = link.find_element(By.CSS_SELECTOR, 'div').text

            # Check LTL
            if len(re.findall(r"[Ll][Tt][Ll]", description)) != 0:
                self.accept_documentation(href)
                break

    def accept_documentation(self, url: str):
        time.sleep(3)
        self._driver.get(url)

        # Скачать документацию
        try:
            download_documentation_button = self.find_elem(By.CSS_SELECTOR, '#auction_info_td > table > tbody > tr:nth-child(4) table input[type=submit]')
            time.sleep(1)
            download_documentation_button.click()
            self.download_documentation()

        except NoSuchElementException:
            self.download_documentation()

    def download_documentation(self):
        time.sleep(5)
        documentation_block = self.find_elem(By.CSS_SELECTOR, '#download_documentation')
        docs = documentation_block.find_elements(By.CSS_SELECTOR, 'a')
        for doc in docs:
            href = doc.get_attribute('href')
            if not href.endswith('.xlsx'):
                continue
            self._driver.get(href)
            time.sleep(3)


if __name__ == "__main__":
    with Parser() as parser:
        parser.login()
        parser.search()