Why, when I add time.sleep (2), I get my desired result, but if I add, wait until the specific xpath gives less results?
Output using time.sleep (2) (also desirable):
Adelaide Utd
Tottenham
Dundee Fc
...
Quantity: 145 names
Delete time.sleep
Adelaide Utd
Tottenham
Dundee Fc
...
Quantity: 119 names
I added:
clickMe = wait(driver, 13).until(EC.element_to_be_clickable((By.CSS_SELECTOR, ("#page-container > div:nth-child(4) > div > div.ubet-sports-section-page > div > div:nth-child(2) > div > div > div:nth-child(1) > div > div > div.page-title-new > h1"))))
Since this element is present on all pages.
Seems to be much smaller. How can I get around this problem?
Script:
import csv
import os
from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support.ui import WebDriverWait as wait
driver = webdriver.Chrome()
driver.set_window_size(1024, 600)
driver.maximize_window()
driver.get('https://ubet.com/sports/soccer')
clickMe = WebDriverWait(driver, 10).until(EC.element_to_be_clickable((By.XPATH, ('//select[./option="Soccer"]/option'))))
options = driver.find_elements_by_xpath('//select[./option="Soccer"]/option')
indexes = [index for index in range(len(options))]
for index in indexes:
try:
try:
zz = wait(driver, 10).until(
EC.element_to_be_clickable((By.XPATH, '(//select/optgroup/option)[%s]' % str(index + 1))))
zz.click()
except StaleElementReferenceException:
pass
from selenium.webdriver.support.ui import WebDriverWait
def find(driver):
pass
from selenium.common.exceptions import StaleElementReferenceException, NoSuchElementException
import time
clickMe = wait(driver, 10).until(EC.element_to_be_clickable((By.CSS_SELECTOR, ("#page-container > div:nth-child(4) > div > div.ubet-sports-section-page > div > div:nth-child(2) > div > div > div:nth-child(1) > div > div > div.page-title-new > h1"))))
langs0 = driver.find_elements_by_css_selector(
"div > div > div > div > div > div > div > div > div.row.collapse > div > div > div:nth-child(2) > div > div > div > div > div > div.row.small-collapse.medium-collapse > div:nth-child(1) > div > div > div > div.lbl-offer > span")
langs0_text = []
for lang in langs0:
try:
langs0_text.append(lang.text)
except StaleElementReferenceException:
pass
directory = 'C:\\A.csv'
with open(directory, 'a', newline='', encoding="utf-8") as outfile:
writer = csv.writer(outfile)
for row in zip(langs0_text):
writer.writerow(row)
except StaleElementReferenceException:
pass
If you cannot access the page, you will need vpn.
Updating ...
This item may be loading in front of others. Therefore, if we changed it to datascraped (not all pages have data that needs to be cleared).
Add
to try:
clickMe = wait(driver, 13).until(EC.element_to_be_clickable((By.CSS_SELECTOR, ("div > div > div > div > div > div > div > div > div.row.collapse > div > div > div:nth-child(2) > div > div > div > div > div > div.row.small-collapse.medium-collapse > div:nth-child(3) > div > div > div > div.lbl-offer > span"))))
except TimeoutException as ex:
pass
The same question is still present.
Manual steps:
Scrape:
div > div > div > div > div > div > div > div > div.row.collapse > div > div > div:nth-child(2) > div > div > div > div > div > div.row.small-collapse.medium-collapse > div:nth-child(1) > div > div > div > div.lbl-offer > span
Loop repeat.