你可以使用更好的Python代码来使用Google进行翻译:
来源:https://neculaifantanaru.com/en/python-code-text-google-translate-website-translation-beautifulsoup-new.html
from bs4 import BeautifulSoup
from bs4.formatter import HTMLFormatter
import requests
import sys
import os
class UnsortedAttributes(HTMLFormatter):
def attributes(self, tag):
for k, v in tag.attrs.items():
yield k, v
files_from_folder = r"c:\Folder2"
use_translate_folder = True
destination_language = 'vi'
extension_file = ".html"
directory = os.fsencode(files_from_folder)
def translate(text, target_language):
url = "https://translate.google.com/translate_a/single"
headers = {
"Host": "translate.google.com",
"Accept": "*/*",
"Cookie": "",
"User-Agent": "GoogleTranslate/5.9.59004 (iPhone; iOS 10.2; ja; iPhone9,1)",
"Accept-Language": "fr",
"Accept-Encoding": "gzip, deflate",
"Connection": "keep-alive",
}
sentence = text
params = {
"client": "it",
"dt": ["t", "rmt", "bd", "rms", "qca", "ss", "md", "ld", "ex"],
"otf": "2",
"dj": "1",
"q": sentence,
"hl": "ja",
"ie": "UTF-8",
"oe": "UTF-8",
"sl": "en",
"tl": target_language,
}
res = requests.get(
url=url,
headers=headers,
params=params,
)
res = res.json()
paragraph = ''
for i in range(0, len(res["sentences"])):
paragraph += res["sentences"][i]["trans"]
return paragraph
def recursively_translate(node):
for x in range(len(node.contents)):
if isinstance(node.contents[x], str):
if node.contents[x].strip() != '':
try:
node.contents[x].replaceWith(translate(text=node.contents[x], target_language=destination_language))
except:
pass
elif node.contents[x] != None:
recursively_translate(node.contents[x])
for file in os.listdir(directory):
filename = os.fsdecode(file)
print(filename)
if filename == 'y_key_e479323ce281e459.html' or filename == 'directory.html':
continue
if filename.endswith(extension_file):
with open(os.path.join(files_from_folder, filename), encoding='utf-8') as html:
soup = BeautifulSoup('<pre>' + html.read() + '</pre>', 'html.parser')
for title in soup.findAll('title'):
recursively_translate(title)
for meta in soup.findAll('meta', {'name':'description'}):
try:
meta['content'] = translate(text=meta['content'], target_language=destination_language)
except:
pass
for h1 in soup.findAll('h1', {'itemprop':'name'}, class_='den_articol'):
begin_comment = str(soup).index('<!-- ARTICOL START -->')
end_comment = str(soup).index('<!-- ARTICOL FINAL -->')
if begin_comment < str(soup).index(str(h1)) < end_comment:
recursively_translate(h1)
for p in soup.findAll('p', class_='text_obisnuit'):
begin_comment = str(soup).index('<!-- ARTICOL START -->')
end_comment = str(soup).index('<!-- ARTICOL FINAL -->')
if begin_comment < str(soup).index(str(p)) < end_comment:
recursively_translate(p)
for p in soup.findAll('p', class_='text_obisnuit2'):
begin_comment = str(soup).index('<!-- ARTICOL START -->')
end_comment = str(soup).index('<!-- ARTICOL FINAL -->')
if begin_comment < str(soup).index(str(p)) < end_comment:
recursively_translate(p)
for span in soup.findAll('span', class_='text_obisnuit2'):
begin_comment = str(soup).index('<!-- ARTICOL START -->')
end_comment = str(soup).index('<!-- ARTICOL FINAL -->')
if begin_comment < str(soup).index(str(span)) < end_comment:
recursively_translate(span)
for li in soup.findAll('li', class_='text_obisnuit'):
begin_comment = str(soup).index('<!-- ARTICOL START -->')
end_comment = str(soup).index('<!-- ARTICOL FINAL -->')
if begin_comment < str(soup).index(str(li)) < end_comment:
recursively_translate(li)
for a in soup.findAll('a', class_='linkMare'):
begin_comment = str(soup).index('<!-- ARTICOL START -->')
end_comment = str(soup).index('<!-- ARTICOL FINAL -->')
if begin_comment < str(soup).index(str(a)) < end_comment:
recursively_translate(a)
for h4 in soup.findAll('h4', class_='text_obisnuit2'):
begin_comment = str(soup).index('<!-- ARTICOL START -->')
end_comment = str(soup).index('<!-- ARTICOL FINAL -->')
if begin_comment < str(soup).index(str(h4)) < end_comment:
recursively_translate(h4)
for h5 in soup.findAll('h5', class_='text_obisnuit2'):
begin_comment = str(soup).index('<!-- ARTICOL START -->')
end_comment = str(soup).index('<!-- ARTICOL FINAL -->')
if begin_comment < str(soup).index(str(h5)) < end_comment:
recursively_translate(h5)
for h1 in soup.findAll('h1', {'itemprop':'name'}, class_='den_webinar'):
begin_comment = str(soup).index('<!-- ARTICOL START -->')
end_comment = str(soup).index('<!-- ARTICOL FINAL -->')
if begin_comment < str(soup).index(str(h1)) < end_comment:
recursively_translate(h1)
print(f'{filename} translated')
soup = soup.encode(formatter=UnsortedAttributes()).decode('utf-8')
new_filename = f'{filename.split(".")[0]}_{destination_language}.html'
if use_translate_folder:
try:
with open(os.path.join(files_from_folder+r'\translated', new_filename), 'w', encoding='utf-8') as new_html:
new_html.write(soup[5:-6])
except:
os.mkdir(files_from_folder+r'\translated')
with open(os.path.join(files_from_folder+r'\translated', new_filename), 'w', encoding='utf-8') as new_html:
new_html.write(soup[5:-6])
else:
with open(os.path.join(files_from_folder, new_filename), 'w', encoding='utf-8') as html:
html.write(soup[5:-6])