"""
This script splices the original text of a webpage with that of a designated translation language.
It uses google translate, a list of translate codes is available here: https://ctrlq.org/code/19899-google-translate-languages


The function takes 2 arguments, language_splicer(link, language). Destination language defaults to Spanish if 
not specified.

"""


import time, bs4, os, requests, webbrowser, sys
from googletrans import Translator


os.chdir('C:\\Users\\Rory\\Documents\\Python\\Spanish_splicer')

def language_splicer(link, language='es'):
    start = time.time()
    print('started')

    res = requests.get(link)
    try:
        res.raise_for_status()
    except:
        print('Failed to get page')
        sys.exit()
    
    
    soup = bs4.BeautifulSoup(res.content, 'html.parser')
    a = str(soup)
    print('page obtained')
    
    h1 = soup.find_all('h1')
    h2 = soup.find_all('h2')
    h3 = soup.find_all('h3')
    h4 = soup.find_all('h4')
    h5 = soup.find_all('h5')
    p = soup.find_all('p')
    textOriginal = h1 + h2 + h3 + h4 + h5 + p
    print("len of textOriginal: " + str(len(textOriginal)))
    print("Predicted time to complete: " + str(0.3888*len(textOriginal))+ "-" + str(0.5259*len(textOriginal))+" s")
    
    JustText = []
    for i in textOriginal:
        JustText.append(str(i.get_text()))
    
    translator = Translator()
    newLanguageText = []
    
#    print("len of JustText: " + str(len(JustText)))
#    AllText = " || ".join(JustText)
#    print(AllText)

#    AllTrans = translator.translate(AllText, dest=language).text
#    newLanguageText = AllTrans.split(" || ")
#    print(newLanguageText)
#    print("len of newLanguageText: " + str(len(newLanguageText)))
        

    for i in range(0, len(JustText)):
        try:
            new = translator.translate(str(JustText[i]), dest=language).text
        except:
            new = 'Translation unavailable.'
        newLanguageText.append(new)
    
    Spliced = []
    for i in range(0, len(JustText)):
        original = str(textOriginal[i])
        splice = original[:-5] + ' || ' + newLanguageText[i] + original[-5:]
        Spliced.append(splice)
    
    print("len of Spliced: " + str(len(Spliced)))
    for i in range(0, len(Spliced)):
        a = a.replace(str(textOriginal[i]), Spliced[i])
    
    file = open('page.html', 'w', encoding="utf-8")
    file.write(a)
    file.close()
    
    webbrowser.open('page.html')
    end = time.time()
    print('Time elapsed: ' + str(end-start)+' s')
    print('finished')



# Run the script

language_splicer('https://www.bbc.co.uk/news/uk-england-london-48011838', 'es')

# And the same one in Japanese

language_splicer('https://www.bbc.co.uk/news/uk-england-london-48011838', 'ja')