Как спарсить данные с одинаковым классом и id?

Question

Всем добрый день. Подскажите, как спарсить данные (прикрепил скриншот) с этого сайта: https://www.flashscore.ru/match/llD7mNQ3/#odds-comparison;over-under;full-time

Есть код, который прокручивает страницу и берет её html, но не знаю как можно взять эти данные? Класс и id у всех одинаковый, подобраться к ним не могу. Подскажите, как можно это спарсить? Заранее спасибо.

Код:

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


def main(sec_wait):
    driver = webdriver.Chrome()
    wait = WebDriverWait(driver, sec_wait)

    driver.get("https://www.flashscore.ru/match/llD7mNQ3/#odds-comparison;over-under;full-time")

    driver.execute_script("window.scrollTo(0, 700);")
    data = wait_to_find_id(driver, wait, "odds_ou_2.5", ".")

    html2 = driver.page_source
    soup2 = BeautifulSoup(html2, 'lxml')
    # print(html2)

    tochka_kef_first = soup2.find_all('table', id='odds_ou_2.5')
    print(tochka_kef_first)


def wait_to_find_id(driver, wait, id_, text_to_find=""):
    try:
        element = wait.until(
            EC.text_to_be_present_in_element((By.ID, id_), text_to_find)
        )
        return driver.find_element_by_id(id_).text
    except TimeoutException:
        driver.quit()
        raise Exception(f"Element not found after {wait._timeout} sec of waiting")
    except Exception as e:
        driver.quit()
        raise e


if __name__ == "__main__":
    main(10)

Как спарсить эти данные? (P.S. Именно тотал 2.5)

на выходе просто иметь 4 числа: 1.78 | 1.79 | 2.15 | 2.14

Answer 1

вот решение:

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


def wait_to_find_by(driver, wait, value=None, find="", by=By.ID, text=True):
    """Finds an element by By object and an expectation for
    checking if the given text is present in the specified element.
    If no match was found within the specified time, an Exception is raised.

    inputs:
        driver - instance of the selenium.webdriver.some_class.
        wait - instance of the selenium.webdriver.support.ui.WebDriverWait.
        value[None] - The By object of the element to be found.
        find[""] - the text that must be present in the element.
        by[By.ID] - selenium.webdriver.common.by.By object.
        text[True] - if False, then returns the element itself, otherwise - element.text.
    """
    try:
        element = wait.until(
            EC.text_to_be_present_in_element((by, value), find)
        )
        element = driver.find_element(by=by, value=value)
        if text:
            return element.text
        return element
    except TimeoutException:
        driver.quit()
        raise Exception(f"Element not found after {wait._timeout} sec of waiting")
    except Exception as e:
        driver.quit()
        raise e


def main(sec_wait):
    driver = webdriver.Chrome()
    wait = WebDriverWait(driver, sec_wait)

    driver.get("https://www.flashscore.ru/match/llD7mNQ3/"\
        "#odds-comparison;over-under;full-time")

    wait_to_find_by(driver, wait, "odds_ou_2.5")

    soup = BeautifulSoup(driver.page_source, 'lxml')
    total_25 = (soup.find("table", id="odds_ou_2.5")
        .find_all("tr", class_=["odd", "even"]))


    data = []
    for bookmaker in total_25:
        link = bookmaker.find("a", class_="elink").get("href")
        if link.find("453") == -1:
           continue
        data.append([
            bookmaker.find("span", class_=["up"]),
            bookmaker.find("span", class_=["down"])
        ])

    if len(data) != 1:
        raise Exception("there is no needable bookmaker")
    else:
        element_up, element_down = data[0]

    data_up = re.split(r"\[.+\]", element_up.get("eu"))
    data_down = re.split(r"\[.+\]", element_down.get("eu"))

    print("up:", " >> ".join(data_up))
    print("down:", " >> ".join(data_down))


if __name__ == "__main__":
    main(10)

БЛОГ НА HUSL

Как спарсить данные с одинаковым классом и id?

Ответы (1 шт):