translating text using data frame from google trans not translating

Hi Tuhin

 

Have a look at the code that is now inserted its the same i  posted today and im stil experiencing the same issue. Please test this code again on your side and share the compiled output. I might be doing something wrong here. 

 

// latest code with URL link included but still experience same result no change at all.

from google_trans import Translator
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions
import pandas as pd
import urllib.request as urllib2
import time

chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--headless')
chrome_options.add_argument("window-size=1920,1080")
driver = webdriver.Chrome(options=chrome_options)
url = "https://www.classcentral.com/collection/top-free-online-courses"
driver.get(url)

try:
    while True:
        # wait until button is clickable
        WebDriverWait(driver, 1).until(
                expected_conditions.element_to_be_clickable((By.XPATH, "//button[@data-name='LOAD_MORE']"))
            ).click()
        time.sleep(0.5)
except Exception as e:
    pass

all_courses = driver.find_element(by=By.CLASS_NAME, value='catalog-grid__results')
courses = all_courses.find_elements(by=By.CSS_SELECTOR, value='[class="color-charcoal course-name"]')

#google translating languages
translator = Translator()

df = pd.DataFrame([[course.text, course.get_attribute('href')] for course in courses],
                    columns=['Title (eng)', 'Link'])

df['Title (hin)'] = df['Title (eng)'].apply(lambda x: translator.translate(x, dest='hi').text)

print(df)

Yes, I think the error is because you are passing an empty string as an argument to the get_attribute method. To fix this, you need to pass the attribute name as the argument. In this case, it should be href. Try the code below:

from google_trans import Translator
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions
import pandas as pd
import urllib.request as urllib2
import time

chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--headless')
chrome_options.add_argument("window-size=1920,1080")
driver = webdriver.Chrome(options=chrome_options)
url = "./....classcentral.com/collection/top-free-online-courses"  # replace with actual URL
driver.get(url)

try:
    while True:
        WebDriverWait(driver, 1).until(
            expected_conditions.element_to_be_clickable((By.XPATH, "//button[@data-name='LOAD_MORE']"))
        ).click()
        time.sleep(0.5)
except Exception as e:
    pass

all_courses = driver.find_element(by=By.CLASS_NAME, value='catalog-grid__results')
courses = all_courses.find_elements(by=By.CSS_SELECTOR, value='[class="color-charcoal course-name"]')

df = pd.DataFrame([[course.text, course.get_attribute('href')] for course in courses],
                  columns=['Title (eng)', 'Link'])

# Create a translator object
translator = Translator()

# Translate each course title to Hindi
df['Title (hin)'] = df['Title (eng)'].apply(lambda x: translator.translate(x, dest='hi').text)

print(df)

Make sure to replace the url variable with the actual URL of the page you want to scrape.
 

Hi Tuhin

Do you mind sharing your output here as a solution, because what you mentioned now here tried and this compiles this screen code below. I have all the necessary libraries used from the program but i kept getting this exception all the time. What is best option to fix this problem...?

Traceback (most recent call last):
  File "C:\Users\Zux\PycharmProjects\ClassCentral\main.py", line 37, in 
    df['Title (hin)'] = df['Title (eng)'].apply(lambda x: translator.translate(x, dest='hi').text)
                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Zux\PycharmProjects\ClassCentral\ClassCentral\Lib\site-packages\pandas\core\series.py", line 4771, in apply
    return SeriesApply(self, func, convert_dtype, args, kwargs).apply()



from google_trans import Translator
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions
import pandas as pd
import urllib.request as urllib2
import time

chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--headless')
chrome_options.add_argument("window-size=1920,1080")
driver = webdriver.Chrome(options=chrome_options)
url = "https://www.classcentral.com/collection/top-free-online-courses"
driver.get(url)

#google translating languages
translator = Translator()

try:
    while True:
        # wait until button is clickable
        WebDriverWait(driver, 1).until(
                expected_conditions.element_to_be_clickable((By.XPATH, "//button[@data-name='LOAD_MORE']"))
            ).click()
        time.sleep(0.5)
except Exception as e:
    pass

all_courses = driver.find_element(by=By.CLASS_NAME, value='catalog-grid__results')
courses = all_courses.find_elements(by=By.CSS_SELECTOR, value='[class="color-charcoal course-name"]')

df = pd.DataFrame([[course.text, course.get_attribute('href')] for course in courses],
                    columns=['Title (eng)', 'Link'])

df['Title (hin)'] = df['Title (eng)'].apply(lambda x: translator.translate(x, dest='hi').text)

print(df)

Hello,

See the updated code snippet,I have modified it and it should translate the course titles correctly:

from google_trans import Translator
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions
import pandas as pd
import urllib.request as urllib2
import time

chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--headless')
chrome_options.add_argument("window-size=1920,1080")
driver = webdriver.Chrome(options=chrome_options)
url = "./....classcentral.com/collection/top-free-online-courses"//i cant put url links dont have enough reputation
driver.get(url)

try:
    while True:
        WebDriverWait(driver, 1).until(
            expected_conditions.element_to_be_clickable((By.XPATH, "//button[@data-name='LOAD_MORE']"))
        ).click()
        time.sleep(0.5)
except Exception as e:
    pass

all_courses = driver.find_element(by=By.CLASS_NAME, value='catalog-grid__results')
courses = all_courses.find_elements(by=By.CSS_SELECTOR, value='[class="color-charcoal course-name"]')

df = pd.DataFrame([[course.text, course.get_attribute('')] for course in courses],
                  columns=['Title (eng)', 'Link'])

# Create a translator object
translator = Translator()

# Translate each course title to Hindi
df['Title (hin)'] = df['Title (eng)'].apply(lambda x: translator.translate(x, dest='hi').text)

print(df)

This should create a new column in the DataFrame called Title (hin) that contains the Hindi translation of the course titles.