Das deutsche Python-Forum

Code: Alles auswählen

import datetime
import pandas as pd

from selenium import webdriver
from openpyxl import Workbook
from datetime import date
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

wb = Workbook()
ws = wb.active
tomorrow = datetime.datetime.now() + datetime.timedelta(days=1)

# Browser verbinden
driver = webdriver.Chrome('C:\webdrivers\chromedriver.exe')
driver.get("https://www.oddsportal.com/login/")

# User Login
username = driver.find_element_by_xpath('//*[@id="login-username1"]')
username.send_keys("Username")

password = driver.find_element_by_xpath('//*[@id="login-password1"]')
password.send_keys("Password")

login = driver.find_element_by_xpath('//*[@id="col-content"]/div[3]/div/form/div[3]/button/span/span')
login.click()

def iter_stripped_texts(elements, start_index=None, end_index=None):
    return (element.text.strip() for element in elements[slice(start_index, end_index)])

driver.get("https://www.oddsportal.com/matches/tennis/" + tomorrow.strftime("%Y%m%d") + "/")

match_tbl = driver.find_element_by_id("table-matches")
rows = match_tbl.find_elements_by_tag_name("tr")

urls = []

# Tabelle analysieren und Daten ermitteln
for row in rows:
    if "dark" not in row.get_attribute("class"):
        cells = row.find_elements_by_tag_name("td")
        a_tag = cells[1].find_elements_by_tag_name("a")[0]
        if "javascript:void(0);" not in a_tag.get_attribute("href"):
            urls.append(a_tag.get_attribute("href"))
        elif "javascript:void(0);" in a_tag.get_attribute("href"):
            a_tag = cells[1].find_elements_by_tag_name("a")[1]
            urls.append(a_tag.get_attribute("href"))

for url in urls:
    driver.get(url)
    #print(driver.find_element_by_css_selector("#breadcrumb > a:nth-child(4)").get_attribute('href'))
    df_sport = (WebDriverWait(driver, 10).until(EC.visibility_of_element_located((By.CSS_SELECTOR, "#breadcrumb > a:nth-child(3)"))).get_attribute('text'))
    df_country = (WebDriverWait(driver, 10).until(EC.visibility_of_element_located((By.CSS_SELECTOR, "#breadcrumb > a:nth-child(4)"))).get_attribute('text'))
    df_tournament = (WebDriverWait(driver, 10).until(EC.visibility_of_element_located((By.CSS_SELECTOR, "#breadcrumb > a:nth-child(5)"))).get_attribute('text'))
    df_players = driver.find_element_by_tag_name("h1").text

    for row in driver.find_elements_by_css_selector("#odds-data-table > div:nth-child(1) > table > tbody > tr"):        
        if not "wool" in row.get_attribute("class"):
            cells = row.find_elements_by_tag_name("td")
            df_bookie = cells[0].text.replace("\n", "").strip()
            df_home_odd = cells[1].text.replace("\n", "").strip()
            df_away_odd = cells[2].text.replace("\n", "").strip()
            df_payout = cells[3].text.replace("\n", "").strip()
    
            print(df_sport , df_country , df_tournament , df_players , df_bookie , df_home_odd , df_away_odd , df_payout)
            ws.append([df_sport , df_country , df_tournament , df_players , df_bookie , df_home_odd , df_away_odd , df_payout])
                    
wb.save("F:\Testdatei\Tennis-" + tomorrow.strftime("%Y%m%d") + ".xlsx")
driver.close()