前回の内容と今回やったこと
前回の記事【Python】英文PDF（に限らないけど）をDeepLやGoogle翻訳で自動で翻訳させてテキストファイルにしてしまおう。
では翻訳結果をテキストファイルに出力しましたが、翻訳前の文章と横に並べて見比べられたら便利だと思いませんか。
まだ改善の余地はありますがHTMLで実現しました。
例に使った論文
ごちゃごちゃと盛り付けたのでコードが汚いですがご容赦ください（もとからか）。
8/7追記
HTML表示時における
・ 対応する英文or和文への、ハイライト機能・ジャンプ機能
・ ダークモード
を追加しました。また、
非ダークモード時の色合いも優しくしました。
逆翻訳（日本語 → 英語）に対応しました。
コード
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.keys import Keys
import time
import pyperclip as ppc
DRIVER_PATH = 'chromedriver.exe'
options = Options()
options.add_argument('--disable-gpu')
options.add_argument('--disable-extensions')
options.add_argument('--proxy-server="direct://"')
options.add_argument('--proxy-bypass-list=*')
options.add_argument('--start-maximized')
def parse_merge(text, n=4900, m=1, inv=False):
sentences = []
sentence = ""
for j, i in enumerate(" ".join(
text.splitlines()).split(". " if inv == False else "。")):
if i in ("", " ", "."): continue
if (len(sentence) + len(i) > n) or (j % m == 0):
sentences.append(sentence)
sentence = ""
sentence += i + ("." if inv == False else "。")
sentences.append(sentence)
return sentences
def TranslateFromClipboard(tool, write, filename, isPrint, html, title,
sentence_cnt, inv):
driver = webdriver.Chrome(executable_path=DRIVER_PATH,
chrome_options=options)
url = 'https://www.deepl.com/ja/translator' if tool == "DeepL" else f'https://translate.google.co.jp/?hl=ja&tab=TT&authuser=0#view=home&op=translate&sl=auto&tl={"en" if inv else "ja"}'
driver.get(url)
if tool == "DeepL":
textarea = driver.find_element_by_css_selector(
'.lmt__textarea.lmt__source_textarea.lmt__textarea_base_style')
elif tool == "GT":
textarea = driver.find_element_by_id('source')
en = parse_merge(ppc.paste(), m=sentence_cnt, inv=inv)
ja = []
for sentence in en:
if sentence == "":
ja.append("")
continue
cbText = ppc.paste()
ppc.copy(sentence)
textarea.send_keys(Keys.CONTROL, "v")
ppc.copy(cbText)
transtext = ""
while transtext == "":
time.sleep(1)
if tool == "DeepL":
transtext = driver.find_element_by_css_selector(
'.lmt__textarea.lmt__target_textarea.lmt__textarea_base_style'
).get_property("value")
elif tool == "GT":
try:
time.sleep(1)
transtext = driver.find_element_by_css_selector(
'.tlid-translation.translation').text
except:
pass
if isPrint: print(transtext)
ja.append(transtext)
textarea.send_keys(Keys.CONTROL, "a")
textarea.send_keys(Keys.BACKSPACE)
driver.quit()
if write:
with open(filename + ".txt", "w", encoding='UTF-8') as f:
f.write("\n".join(ja))
if html:
eng = ""
jpn = ""
for i, ej in enumerate(zip(en, ja)):
eng += f'<br><a id="e{i}" href="#j{i}" onmouseover="over(' + f"'j{i}'" + ')" onmouseout="out(' + f"'j{i}'" + f')">{ej[0]}</a><br>'
jpn += f'<br><a id="j{i}" href="#e{i}" onmouseover="over(' + f"'e{i}'" + ')" onmouseout="out(' + f"'e{i}'" + f')">{ej[1]}</a><br>'
with open(filename + ".html", "w", encoding='UTF-8') as f:
f.write(
f'<h1 align="center">{title}</h1>\n<input id="btn-mode" type="checkbox">\n<hr>\n<body>\n<div class="parent">\n<div id="en">\n{eng}\n</div>\n<div id="ja">\n{jpn}\n</div>\n</div>'
+
'<style>\n:root {\n--main-text: #452b15;\n--main-bg: #f8f1e2;\n--highlight-text: #db8e3c;\n}\n:root[theme="dark"] {\n--main-text: #b0b0b0;\n--main-bg: #121212;\n--highlight-text: #fd8787;\n}\nh1 {\ncolor: var(--main-text);\n}\ninput {\nposition: absolute;\ntop: 1%;\nright: 1%;\n}\n#en {\nwidth: 43%;\nheight: 90%;\npadding: 0 2%;\nfloat: left;\nborder-right:1px solid #ccc;\nmargin: 1%;\noverflow: auto;\n}\n#ja {\nwidth: 43%;\nheight: 90%;\npadding: 0 2%;\nfloat: right;\nmargin: 1%;\noverflow: auto;\n}\na,\na:hover,\na:visited,\na:link,\na:active {\ncolor: var(--main-text);\ntext-decoration: none;\n}\nbody {\nbackground-color: var(--main-bg);\n}\n</style>\n<script>\nvar a = document.getElementsByTagName("a");\nfunction over(e) {\ndocument.getElementById(e).style.color = getComputedStyle(document.getElementById(e)).getPropertyValue("--highlight-text");\n}\nfunction out(e) {\ndocument.getElementById(e).style.color = getComputedStyle(document.getElementById(e)).getPropertyValue("--main-text");\n}\nconst btn = document.querySelector("#btn-mode");\nbtn.addEventListener("change", () => {\nif (btn.checked == true) {\ndocument.documentElement.setAttribute("theme", "dark");\n} else {\ndocument.documentElement.setAttribute("theme", "light");\n}\nfor (var i = 0; i < a.length; i++) {\na[i].style.color = getComputedStyle(a[i]).getPropertyValue("--main-text");\n}\n});\n</script>\n</body>'
)
if __name__ == "__main__":
args = [
"DeepL", False, "translated_text.txt", True, False, "EN ↔ JP", 1, False
]
if input("1. 英語 → 日本語 2. 日本語 → 英語 ") == "2": args[7] = True
if input("1. DeepL 2.GoogleTranslate ") == "2": args[0] = "GT"
if input("翻訳結果を書き出しますか？ y/n ") == "y":
case = input("1. txt 2. HTML 3. both ")
if case == "1":
args[1] = True
format_ = ".txt"
elif case == "2":
args[4] = True
format_ = ".html"
elif case == "3":
args[1], args[4] = True, True
format_ = ".txt/.html"
filename = input(
f"出力ファイルにつける名前を入力してください（デフォルトは'translated_text{format_}'） ")
if filename:
args[2] = filename.replace(" ", "_")
if case == "2" or case == "3":
title = input("（論文の）タイトルを入力してください ")
if title:
args[5] = title
try:
args[6] = int(
input("何文ずつ翻訳しますか？（デフォルトは1文ずつ。小さいほど出力がきれいで、大きいほど早くなります。） "))
except:
pass
if input("翻訳経過をここに表示しますか？ y/n ") == "n":
args[3] = False
input("準備ができたらEnterを押してください")
TranslateFromClipboard(*args)
読みやすさはかなり上がりましたが、１文ずつ翻訳しているので全文翻訳するのにかなり時間がかかります（実行時の選択でまとめて翻訳することも出来ます）。
8/9追記
さらにひと手間かかりますが、より見やすく翻訳できる方法がありました。
PDFをWordで開いてからコピーして、以下の文章を分割する関数部分を少し変えたスクリプトで翻訳しましょう。
さすがWordと言うべきか改行をまたぐ文章等もきれいに整形してくれます。
Wordごし用微調整コード
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.keys import Keys
import time
import pyperclip as ppc
DRIVER_PATH = 'chromedriver.exe'
options = Options()
options.add_argument('--disable-gpu')
options.add_argument('--disable-extensions')
options.add_argument('--proxy-server="direct://"')
options.add_argument('--proxy-bypass-list=*')
options.add_argument('--start-maximized')
def parse_merge(text, n=4900):
sentences = []
sentence = ""
for i in text.splitlines():
if i in ("", " ", "."): continue
sentences.append(i)
return sentences
def TranslateFromClipboard(tool, write, filename, isPrint, html, title,inv):
driver = webdriver.Chrome(executable_path=DRIVER_PATH,
chrome_options=options)
url = 'https://www.deepl.com/ja/translator' if tool == "DeepL" else f'https://translate.google.co.jp/?hl=ja&tab=TT&authuser=0#view=home&op=translate&sl=auto&tl={"en" if inv else "ja"}'
driver.get(url)
if tool == "DeepL":
textarea = driver.find_element_by_css_selector(
'.lmt__textarea.lmt__source_textarea.lmt__textarea_base_style')
elif tool == "GT":
textarea = driver.find_element_by_id('source')
en = parse_merge(ppc.paste())
ja = []
for sentence in en:
if sentence == "":
ja.append("")
continue
cbText = ppc.paste()
ppc.copy(sentence)
textarea.send_keys(Keys.CONTROL, "v")
ppc.copy(cbText)
transtext = ""
while transtext == "":
time.sleep(1)
if tool == "DeepL":
transtext = driver.find_element_by_css_selector(
'.lmt__textarea.lmt__target_textarea.lmt__textarea_base_style'
).get_property("value")
elif tool == "GT":
try:
time.sleep(1)
transtext = driver.find_element_by_css_selector(
'.tlid-translation.translation').text
except:
pass
if isPrint: print(transtext)
ja.append(transtext)
textarea.send_keys(Keys.CONTROL, "a")
textarea.send_keys(Keys.BACKSPACE)
driver.quit()
if write:
with open(filename + ".txt", "w", encoding='UTF-8') as f:
f.write("\n".join(ja))
if html:
eng = ""
jpn = ""
for i, ej in enumerate(zip(en, ja)):
eng += f'<br><a id="e{i}" href="#j{i}" onmouseover="over(' + f"'j{i}'" + ')" onmouseout="out(' + f"'j{i}'" + f')">{ej[0]}</a><br>'
jpn += f'<br><a id="j{i}" href="#e{i}" onmouseover="over(' + f"'e{i}'" + ')" onmouseout="out(' + f"'e{i}'" + f')">{ej[1]}</a><br>'
with open(filename + ".html", "w", encoding='UTF-8') as f:
f.write(
f'<h1 align="center">{title}</h1>\n<input id="btn-mode" type="checkbox">\n<hr>\n<body>\n<div class="parent">\n<div id="en">\n{eng}\n</div>\n<div id="ja">\n{jpn}\n</div>\n</div>'
+
'<style>\n:root {\n--main-text: #452b15;\n--main-bg: #f8f1e2;\n--highlight-text: #db8e3c;\n}\n:root[theme="dark"] {\n--main-text: #b0b0b0;\n--main-bg: #121212;\n--highlight-text: #fd8787;\n}\nh1 {\ncolor: var(--main-text);\n}\ninput {\nposition: absolute;\ntop: 1%;\nright: 1%;\n}\n#en {\nwidth: 43%;\nheight: 90%;\npadding: 0 2%;\nfloat: left;\nborder-right:1px solid #ccc;\nmargin: 1%;\noverflow: auto;\n}\n#ja {\nwidth: 43%;\nheight: 90%;\npadding: 0 2%;\nfloat: right;\nmargin: 1%;\noverflow: auto;\n}\na,\na:hover,\na:visited,\na:link,\na:active {\ncolor: var(--main-text);\ntext-decoration: none;\n}\nbody {\nbackground-color: var(--main-bg);\n}\n</style>\n<script>\nvar a = document.getElementsByTagName("a");\nfunction over(e) {\ndocument.getElementById(e).style.color = getComputedStyle(document.getElementById(e)).getPropertyValue("--highlight-text");\n}\nfunction out(e) {\ndocument.getElementById(e).style.color = getComputedStyle(document.getElementById(e)).getPropertyValue("--main-text");\n}\nconst btn = document.querySelector("#btn-mode");\nbtn.addEventListener("change", () => {\nif (btn.checked == true) {\ndocument.documentElement.setAttribute("theme", "dark");\n} else {\ndocument.documentElement.setAttribute("theme", "light");\n}\nfor (var i = 0; i < a.length; i++) {\na[i].style.color = getComputedStyle(a[i]).getPropertyValue("--main-text");\n}\n});\n</script>\n</body>'
)
if __name__ == "__main__":
args = ["DeepL", False, "translated_text.txt", True, False, "EN ↔ JP",False]
if input("1. 英語 → 日本語 2. 日本語 → 英語 ") == "2": args[6] = True
if input("1. DeepL 2.GoogleTranslate ") == "2": args[0] = "GT"
if input("翻訳結果を書き出しますか？ y/n ") == "y":
case = input("1. txt 2. HTML 3. both ")
if case == "1":
args[1] = True
format_ = ".txt"
elif case == "2":
args[4] = True
format_ = ".html"
elif case == "3":
args[1], args[4] = True, True
format_ = ".txt/.html"
filename = input(
f"出力ファイルにつける名前を入力してください（デフォルトは'translated_text{format_}'） ")
if filename:
args[2] = filename.replace(" ", "_")
if case == "2" or case == "3":
title = input("（論文の）タイトルを入力してください ")
if title:
args[5] = title
if input("翻訳経過をここに表示しますか？ y/n ") == "n":
args[3] = False
input("準備ができたらEnterを押してください")
TranslateFromClipboard(*args)
8/11追記
Word通さずともある程度段落を分解できるようにしました。
（だいたい）段落ごとに翻訳するため、１文ずつに比べ翻訳速度もだいぶマシになりました。
文章分解強化版コード
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.keys import Keys
import time
import pyperclip as ppc
import re
import unicodedata
DRIVER_PATH = 'chromedriver.exe'
options = Options()
options.add_argument('--disable-gpu')
options.add_argument('--disable-extensions')
options.add_argument('--proxy-server="direct://"')
options.add_argument('--proxy-bypass-list=*')
options.add_argument('--start-maximized')
def len_(text):
cnt = 0
for t in text:
if unicodedata.east_asian_width(t) in "FWA":
cnt += 2
else:
cnt += 1
return cnt
def textParser(text, n=30, bracketDetect=True):
text = text.splitlines()
sentences = []
t = ""
bra_cnt = ket_cnt = bra_cnt_jp = ket_cnt_jp = 0
for i in range(len(text)):
if not bool(re.search("\S", text[i])): continue
if bracketDetect:
bra_cnt += len(re.findall("[\(（]", text[i]))
ket_cnt += len(re.findall("[\)）]", text[i]))
bra_cnt_jp += len(re.findall("[｢「『]", text[i]))
ket_cnt_jp += len(re.findall("[｣」』]", text[i]))
if i != len(text) - 1:
if bool(re.fullmatch(r"[A-Z\s]+", text[i])):
if t != "": sentences.append(t)
t = ""
sentences.append(text[i])
elif bool(
re.match(
"(\d{1,2}[\.,、．]\s?(\d{1,2}[\.,、．]*)*\s?|I{1,3}V{0,1}X{0,1}[\.,、．]|V{0,1}X{0,1}I{1,3}[\.,、．]|[・•●])+\s",
text[i])) or re.match("\d{1,2}．\w", text[i]) or (
bool(re.match("[A-Z]", text[i][0]))
and abs(len_(text[i]) - len_(text[i + 1])) > n
and len_(text[i]) < n):
if t != "": sentences.append(t)
t = ""
sentences.append(text[i])
elif (
text[i][-1] not in ("。", ".", "．") and
(abs(len_(text[i]) - len_(text[i + 1])) < n or
(len_(t + text[i]) > len_(text[i + 1]) and bool(
re.search("[。\.．]\s\d|..[。\.．]|.[。\.．]", text[i + 1][-3:])
or bool(re.match("[A-Z]", text[i + 1][:1]))))
or bool(re.match("\s?[a-z,\)]", text[i + 1]))
or bra_cnt > ket_cnt or bra_cnt_jp > ket_cnt_jp)):
t += text[i]
else:
sentences.append(t + text[i])
t = ""
else:
sentences.append(t + text[i])
return len(sentences), sentences
def TranslateFromClipboard(tool, write, filename, isPrint, html, title, inv):
driver = webdriver.Chrome(executable_path=DRIVER_PATH,
chrome_options=options)
url = 'https://www.deepl.com/ja/translator' if tool == "DeepL" else f'https://translate.google.co.jp/?hl=ja&tab=TT&authuser=0#view=home&op=translate&sl=auto&tl={"en" if inv else "ja"}'
driver.get(url)
if tool == "DeepL":
textarea = driver.find_element_by_css_selector(
'.lmt__textarea.lmt__source_textarea.lmt__textarea_base_style')
elif tool == "GT":
textarea = driver.find_element_by_id('source')
length, en = textParser(ppc.paste())
ja = []
preText = ""
for i, sentence in enumerate(en):
if sentence == "":
ja.append("")
continue
cbText = ppc.paste()
ppc.copy(sentence)
textarea.send_keys(Keys.CONTROL, "v")
ppc.copy(cbText)
transtext = ""
cnt = 0
while transtext in ("", preText):
time.sleep(1)
if tool == "DeepL":
transtext = driver.find_element_by_css_selector(
'.lmt__textarea.lmt__target_textarea.lmt__textarea_base_style'
).get_property("value")
elif tool == "GT":
try:
transtext = driver.find_element_by_css_selector(
'.tlid-translation.translation').text
except:
pass
cnt += 1
if cnt % 10 == 0: textarea.send_keys(".")
if isPrint:
print(sentence)
print(transtext)
print(f"\n{i+1}/{length} {int(100*(i+1)/length)}% done\n")
ja.append(transtext)
textarea.send_keys(Keys.CONTROL, "a")
textarea.send_keys(Keys.BACKSPACE)
preText = transtext
driver.quit()
if write:
with open(filename + ".txt", "w", encoding='UTF-8') as f:
f.write("\n".join(ja))
if html:
eng = ""
jpn = ""
for i, ej in enumerate(zip(en, ja)):
eng += f'<br><a id="e{i}" href="#j{i}" onmouseover="over(' + f"'j{i}'" + ')" onmouseout="out(' + f"'j{i}'" + f')">{ej[0]}</a><br>'
jpn += f'<br><a id="j{i}" href="#e{i}" onmouseover="over(' + f"'e{i}'" + ')" onmouseout="out(' + f"'e{i}'" + f')">{ej[1]}</a><br>'
with open(filename + ".html", "w", encoding='UTF-8') as f:
f.write(
f'<h1 align="center">{title}</h1>\n<input id="btn-mode" type="checkbox">\n<hr>\n<body>\n<div class="parent">\n<div id="en">\n{eng}\n</div>\n<div id="ja">\n{jpn}\n</div>\n</div>'
+
'<style>\n:root {\n--main-text: #452b15;\n--main-bg: #f8f1e2;\n--highlight-text: #db8e3c;\n}\n:root[theme="dark"] {\n--main-text: #b0b0b0;\n--main-bg: #121212;\n--highlight-text: #fd8787;\n}\nh1 {\ncolor: var(--main-text);\n}\ninput {\nposition: absolute;\ntop: 1%;\nright: 1%;\n}\n#en {\nwidth: 43%;\nheight: 90%;\npadding: 0 2%;\nfloat: left;\nborder-right:1px solid #ccc;\nmargin: 1%;\noverflow: auto;\n}\n#ja {\nwidth: 43%;\nheight: 90%;\npadding: 0 2%;\nfloat: right;\nmargin: 1%;\noverflow: auto;\n}\na,\na:hover,\na:visited,\na:link,\na:active {\ncolor: var(--main-text);\ntext-decoration: none;\n}\nbody {\nbackground-color: var(--main-bg);\n}\n</style>\n<script>\nvar a = document.getElementsByTagName("a");\nfunction over(e) {\ndocument.getElementById(e).style.color = getComputedStyle(document.getElementById(e)).getPropertyValue("--highlight-text");\n}\nfunction out(e) {\ndocument.getElementById(e).style.color = getComputedStyle(document.getElementById(e)).getPropertyValue("--main-text");\n}\nconst btn = document.querySelector("#btn-mode");\nbtn.addEventListener("change", () => {\nif (btn.checked == true) {\ndocument.documentElement.setAttribute("theme", "dark");\n} else {\ndocument.documentElement.setAttribute("theme", "light");\n}\nfor (var i = 0; i < a.length; i++) {\na[i].style.color = getComputedStyle(a[i]).getPropertyValue("--main-text");\n}\n});\n</script>\n</body>'
)
if __name__ == "__main__":
args = [
"DeepL", False, "translated_text.txt", True, False,
"ORIGINAL ↔ TRANSLATED", False
]
if input("1. 英語 → 日本語 2. 日本語 → 英語 ") == "2": args[6] = True
if input("1. DeepL 2.GoogleTranslate ") == "2": args[0] = "GT"
if input("翻訳結果を書き出しますか？ y/n ") == "y":
case = input("1. txt 2. HTML 3. both ")
if case == "1":
args[1] = True
format_ = ".txt"
elif case == "2":
args[4] = True
format_ = ".html"
elif case == "3":
args[1], args[4] = True, True
format_ = ".txt/.html"
filename = input(
f"出力ファイルにつける名前を入力してください（デフォルトは'translated_text{format_}'） ")
if filename:
args[2] = filename.replace(" ", "_")
if case == "2" or case == "3":
title = input("（論文の）タイトルを入力してください ")
if title:
args[5] = title
if input("翻訳経過をここに表示しますか？ y/n ") == "n":
args[3] = False
input("準備ができたらEnterを押してください")
TranslateFromClipboard(*args)
8/16追記
マルチスレッドで大量にChromeを開く力技高速化を施しました。
こちらは書き出しはHTMLのみとなっています。
またDeepLの場合、多く開きすぎると制限がかかって翻訳止まりますのでご注意ください。
(8/22追 対応する文章へのジャンプ機能を改良しました。)
マルチスレッド版コード
from selenium import webdriver
from selenium.webdriver import Chrome
import concurrent.futures
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.keys import Keys
import time
import pyperclip as ppc
import re
import unicodedata
from math import ceil
from threading import Thread, Lock
DRIVER_PATH = 'chromedriver.exe'
options = Options()
options.add_argument('--disable-gpu')
options.add_argument('--disable-extensions')
options.add_argument('--proxy-server="direct://"')
options.add_argument('--proxy-bypass-list=*')
options.add_argument('--start-maximized')
def html_gen(title, filename):
global tr
source = ""
result = ""
tr = sorted(tr, key=lambda x: x["order"])
for item in tr:
i, s, r = item.values()
source += f'<br><a id="s{i}" onclick="scroller(' + f"'s{i}', 'r{i}'" + ')" onmouseover="over(' + f"'r{i}'" + ')" onmouseout="out(' + f"'r{i}'" + f')">{s}</a><br>'
result += f'<br><a id="r{i}" onclick="scroller(' + f"'r{i}', 's{i}'" + ')" onmouseover="over(' + f"'s{i}'" + ')" onmouseout="out(' + f"'s{i}'" + f')">{r}</a><br>'
with open(filename + ".html", "w", encoding='UTF-8') as f:
f.write(
f'<h1 align="center">{title}</h1>\n<input id="btn-mode" type="checkbox">\n<hr>\n<body>\n<div class="parent">\n<div id="source">\n{source}\n</div>\n<div id="result">\n{result}\n</div>\n</div>'
+
'<style>\n:root {\n--main-text: #452b15;\n--main-bg: #f8f1e2;\n--highlight-text: #db8e3c;\n}\n:root[theme="dark"] {\n--main-text: #b0b0b0;\n--main-bg: #121212;\n--highlight-text: #fd8787;\n}\nh1 {\ncolor: var(--main-text);\n}\ninput {\nposition: absolute;\ntop: 1%;\nright: 1%;\n}\n#source {\nwidth: 43%;\nheight: 90%;\npadding: 0 2%;\nfloat: left;\nborder-right:1px solid #ccc;\nmargin: 1%;\noverflow: auto;\n}\n#result {\nwidth: 43%;\nheight: 90%;\npadding: 0 2%;\nfloat: right;\nmargin: 1%;\noverflow: auto;\n}\na,\na:hover,\na:visited,\na:link,\na:active {\ncolor: var(--main-text);\ntext-decoration: none;\n}\nbody {\nbackground-color: var(--main-bg);\n}\n</style>\n<script>\nvar a = document.getElementsByTagName("a");\nfunction over(e) {\ndocument.getElementById(e).style.color = getComputedStyle(document.getElementById(e)).getPropertyValue("--highlight-text");\n}\nfunction out(e) {\ndocument.getElementById(e).style.color = getComputedStyle(document.getElementById(e)).getPropertyValue("--main-text");\n}\nfunction scroller(s, o) {\nvar elements = document.getElementById(s);\nvar elemento = document.getElementById(o);\nvar rects = elements.getBoundingClientRect();\nvar recto = elemento.getBoundingClientRect();\nvar x = recto.left;\nvar y = recto.top - rects.top;\nelemento.parentNode.scrollBy(x, y);\n}\nconst btn = document.querySelector("#btn-mode");\nbtn.addEventListener("change", () => {\nif (btn.checked == true) {\ndocument.documentElement.setAttribute("theme", "dark");\n} else {\ndocument.documentElement.setAttribute("theme", "light");\n}\nfor (var i = 0; i < a.length; i++) {\na[i].style.color = getComputedStyle(a[i]).getPropertyValue("--main-text");\n}\n});\n</script>\n</body>'
)
def len_(text):
cnt = 0
for t in text:
if unicodedata.east_asian_width(t) in "FWA":
cnt += 2
else:
cnt += 1
return cnt
def textParser(text, n=30, bracketDetect=True):
text = text.splitlines()
sentences = []
t = ""
bra_cnt = ket_cnt = bra_cnt_jp = ket_cnt_jp = 0
for i in range(len(text)):
if not bool(re.search("\S", text[i])): continue
if bracketDetect:
bra_cnt += len(re.findall("[\(（]", text[i]))
ket_cnt += len(re.findall("[\)）]", text[i]))
bra_cnt_jp += len(re.findall("[｢「『]", text[i]))
ket_cnt_jp += len(re.findall("[｣」』]", text[i]))
if i != len(text) - 1:
if bool(re.fullmatch(r"[A-Z\s]+", text[i])):
if t != "": sentences.append(t)
t = ""
sentences.append(text[i])
elif bool(
re.match(
"(\d{1,2}[\.,、．]\s?(\d{1,2}[\.,、．]*)*\s?|I{1,3}V{0,1}X{0,1}[\.,、．]|V{0,1}X{0,1}I{1,3}[\.,、．]|[・•●])+\s",
text[i])) or re.match("\d{1,2}．\w", text[i]) or (
bool(re.match("[A-Z]", text[i][0]))
and abs(len_(text[i]) - len_(text[i + 1])) > n
and len_(text[i]) < n):
if t != "": sentences.append(t)
t = ""
sentences.append(text[i])
elif (
text[i][-1] not in ("。", ".", "．") and
(abs(len_(text[i]) - len_(text[i + 1])) < n or
(len_(t + text[i]) > len_(text[i + 1]) and bool(
re.search("[。\.．]\s\d|..[。\.．]|.[。\.．]", text[i + 1][-3:])
or bool(re.match("[A-Z]", text[i + 1][:1]))))
or bool(re.match("\s?[a-z,\)]", text[i + 1]))
or bra_cnt > ket_cnt or bra_cnt_jp > ket_cnt_jp)):
t += text[i]
else:
sentences.append(t + text[i])
t = ""
else:
sentences.append(t + text[i])
return len(sentences), sentences
def translate(driver, i, texts):
global tr
preText = ""
if tool == "DeepL":
textarea = driver.find_element_by_css_selector(
'.lmt__textarea.lmt__source_textarea.lmt__textarea_base_style')
elif tool == "GT":
textarea = driver.find_element_by_id('source')
for j, t in enumerate(texts):
etr = {"order": i * unit + j, "source": t}
lock.acquire()
ppc.copy(t)
textarea.send_keys(Keys.CONTROL, "v")
lock.release()
transtext = ""
cnt = 0
while transtext in ("", preText):
time.sleep(1)
if tool == "DeepL":
transtext = driver.find_element_by_css_selector(
'.lmt__textarea.lmt__target_textarea.lmt__textarea_base_style'
).get_property("value")
elif tool == "GT":
try:
transtext = driver.find_element_by_css_selector(
'.tlid-translation.translation').text
except:
pass
cnt += 1
if cnt % 10 == 0: textarea.send_keys(".")
etr["result"] = transtext
tr.append(etr)
textarea.send_keys(Keys.CONTROL, "a")
textarea.send_keys(Keys.BACKSPACE)
preText = transtext
if len(tr) == length: html_gen(title, filename)
def runDriver(order):
driver = webdriver.Chrome(DRIVER_PATH)
url = 'https://www.deepl.com/ja/translator' if tool == "DeepL" else f'https://translate.google.co.jp/?hl=ja&tab=TT&authuser=0#view=home&op=translate&sl=auto&tl={"en" if inv else "ja"}'
driver.get(url)
translate(driver, order,
source[order * unit:min(len(source), (order + 1) * unit)])
driver.close()
def multiThreadTranslate(n):
global tr, threads, source, length, unit, lock
length, source = textParser(ppc.paste())
unit = ceil(length / n)
lock = Lock()
clipboard = ppc.paste()
for t in range(n):
thread = Thread(target=runDriver, args=(t, ))
thread.setDaemon(True)
thread.start()
threads.append(thread)
for thread in threads:
thread.join()
ppc.copy(clipboard)
if __name__ == "__main__":
tr = []
threads = []
n, inv, tool, filename, title = 10, False, "DeepL", "translated_text", "ORIGINAL ↔ TRANSLATED"
n_ = input("いくつのChromeで並行翻訳しますか？ ")
if n_.isdigit(): n = int(n_)
if input("1. 英語 → 日本語 2. 日本語 → 英語 ") == "2": inv = True
if input("1. DeepL 2.GoogleTranslate ") == "2": tool = "GT"
filename_ = input("出力ファイルにつける名前を入力してください（デフォルトは'translated_text.html'） ")
if filename_:
filename = filename_.replace(" ", "_")
title_ = input("（論文の）タイトルを入力してください ")
if title_:
title = title_
input("準備ができたらEnterを押してください")
multiThreadTranslate(n)
マウスオーバーで対応する文章へと高さを揃えるver.
from selenium import webdriver
from selenium.webdriver import Chrome
import concurrent.futures
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.keys import Keys
import time
import pyperclip as ppc
import re
import unicodedata
from math import ceil
from threading import Thread, Lock
DRIVER_PATH = 'chromedriver.exe'
options = Options()
options.add_argument('--disable-gpu')
options.add_argument('--disable-extensions')
options.add_argument('--proxy-server="direct://"')
options.add_argument('--proxy-bypass-list=*')
options.add_argument('--start-maximized')
def html_gen(title, filename):
global tr
source = ""
result = ""
tr = sorted(tr, key=lambda x: x["order"])
for item in tr:
i, s, r = item.values()
source += f'<br><a id="s{i}" onmouseover="over(' + f"'s{i}', 'r{i}'" + ')" onmouseout="out(' + f"'r{i}'" + f')">{s}</a><br>'
result += f'<br><a id="r{i}" onmouseover="over(' + f"'r{i}', 's{i}'" + ')" onmouseout="out(' + f"'s{i}'" + f')">{r}</a><br>'
with open(filename + ".html", "w", encoding='UTF-8') as f:
f.write(
f'<h1 align="center">{title}</h1>\n<input id="btn-mode" type="checkbox">\n<hr>\n<body>\n<div class="parent">\n<div id="source">\n{source}\n</div>\n<div id="result">\n{result}\n</div>\n</div>'
+
'<style>\n:root {\n--main-text: #452b15;\n--main-bg: #f8f1e2;\n--highlight-text: #db8e3c;\n}\n:root[theme="dark"] {\n--main-text: #b0b0b0;\n--main-bg: #121212;\n--highlight-text: #fd8787;\n}\nh1 {\ncolor: var(--main-text);\n}\ninput {\nposition: absolute;\ntop: 1%;\nright: 1%;\n}\n#source {\nwidth: 43%;\nheight: 90%;\npadding: 0 2%;\nfloat: left;\nborder-right:1px solid #ccc;\nmargin: 1%;\noverflow: auto;\n}\n#result {\nwidth: 43%;\nheight: 90%;\npadding: 0 2%;\nfloat: right;\nmargin: 1%;\noverflow: auto;\n}\na,\na:hover,\na:visited,\na:link,\na:active {\ncolor: var(--main-text);\ntext-decoration: none;\n}\nbody {\nbackground-color: var(--main-bg);\n}\n</style>\n<script>\nvar a = document.getElementsByTagName("a");\nfunction over(s,o) {\nvar elements = document.getElementById(s);\nvar elemento = document.getElementById(o);\nvar rects = elements.getBoundingClientRect();\nvar recto = elemento.getBoundingClientRect();\nvar x = recto.left;\nvar y = recto.top - rects.top;\nelemento.parentNode.scrollBy(x, y);\nelemento.style.color = getComputedStyle(elemento).getPropertyValue("--highlight-text");\n}\nfunction out(e) {\ndocument.getElementById(e).style.color = getComputedStyle(document.getElementById(e)).getPropertyValue("--main-text");\n}\nconst btn = document.querySelector("#btn-mode");\nbtn.addEventListener("change", () => {\nif (btn.checked == true) {\ndocument.documentElement.setAttribute("theme", "dark");\n} else {\ndocument.documentElement.setAttribute("theme", "light");\n}\nfor (var i = 0; i < a.length; i++) {\na[i].style.color = getComputedStyle(a[i]).getPropertyValue("--main-text");\n}\n});\n</script>\n</body>'
)
def len_(text):
cnt = 0
for t in text:
if unicodedata.east_asian_width(t) in "FWA":
cnt += 2
else:
cnt += 1
return cnt
def textParser(text, n=30, bracketDetect=True):
text = text.splitlines()
sentences = []
t = ""
bra_cnt = ket_cnt = bra_cnt_jp = ket_cnt_jp = 0
for i in range(len(text)):
if not bool(re.search("\S", text[i])): continue
if bracketDetect:
bra_cnt += len(re.findall("[\(（]", text[i]))
ket_cnt += len(re.findall("[\)）]", text[i]))
bra_cnt_jp += len(re.findall("[｢「『]", text[i]))
ket_cnt_jp += len(re.findall("[｣」』]", text[i]))
if i != len(text) - 1:
if bool(re.fullmatch(r"[A-Z\s]+", text[i])):
if t != "": sentences.append(t)
t = ""
sentences.append(text[i])
elif bool(
re.match(
"(\d{1,2}[\.,、．]\s?(\d{1,2}[\.,、．]*)*\s?|I{1,3}V{0,1}X{0,1}[\.,、．]|V{0,1}X{0,1}I{1,3}[\.,、．]|[・•●])+\s",
text[i])) or re.match("\d{1,2}．\w", text[i]) or (
bool(re.match("[A-Z]", text[i][0]))
and abs(len_(text[i]) - len_(text[i + 1])) > n
and len_(text[i]) < n):
if t != "": sentences.append(t)
t = ""
sentences.append(text[i])
elif (
text[i][-1] not in ("。", ".", "．") and
(abs(len_(text[i]) - len_(text[i + 1])) < n or
(len_(t + text[i]) > len_(text[i + 1]) and bool(
re.search("[。\.．]\s\d|..[。\.．]|.[。\.．]", text[i + 1][-3:])
or bool(re.match("[A-Z]", text[i + 1][:1]))))
or bool(re.match("\s?[a-z,\)]", text[i + 1]))
or bra_cnt > ket_cnt or bra_cnt_jp > ket_cnt_jp)):
t += text[i]
else:
sentences.append(t + text[i])
t = ""
else:
sentences.append(t + text[i])
return len(sentences), sentences
def translate(driver, i, texts):
global tr
preText = ""
if tool == "DeepL":
textarea = driver.find_element_by_css_selector(
'.lmt__textarea.lmt__source_textarea.lmt__textarea_base_style')
elif tool == "GT":
textarea = driver.find_element_by_id('source')
for j, t in enumerate(texts):
etr = {"order": i * unit + j, "source": t}
lock.acquire()
ppc.copy(t)
textarea.send_keys(Keys.CONTROL, "v")
lock.release()
transtext = ""
cnt = 0
while transtext in ("", preText):
time.sleep(1)
if tool == "DeepL":
transtext = driver.find_element_by_css_selector(
'.lmt__textarea.lmt__target_textarea.lmt__textarea_base_style'
).get_property("value")
elif tool == "GT":
try:
transtext = driver.find_element_by_css_selector(
'.tlid-translation.translation').text
except:
pass
cnt += 1
if cnt % 10 == 0: textarea.send_keys(".")
etr["result"] = transtext
tr.append(etr)
textarea.send_keys(Keys.CONTROL, "a")
textarea.send_keys(Keys.BACKSPACE)
preText = transtext
if len(tr) == length: html_gen(title, filename)
def runDriver(order):
driver = webdriver.Chrome(DRIVER_PATH)
url = 'https://www.deepl.com/ja/translator' if tool == "DeepL" else f'https://translate.google.co.jp/?hl=ja&tab=TT&authuser=0#view=home&op=translate&sl=auto&tl={"en" if inv else "ja"}'
driver.get(url)
translate(driver, order,
source[order * unit:min(len(source), (order + 1) * unit)])
driver.close()
def multiThreadTranslate(n):
global tr, threads, source, length, unit, lock
length, source = textParser(ppc.paste())
unit = ceil(length / n)
lock = Lock()
clipboard = ppc.paste()
for t in range(n):
thread = Thread(target=runDriver, args=(t, ))
thread.setDaemon(True)
thread.start()
threads.append(thread)
for thread in threads:
thread.join()
ppc.copy(clipboard)
if __name__ == "__main__":
tr = []
threads = []
n, inv, tool, filename, title = 10, False, "DeepL", "translated_text", "ORIGINAL ↔ TRANSLATED"
n_ = input("いくつのChromeで並行翻訳しますか？ ")
if n_.isdigit(): n = int(n_)
if input("1. 英語 → 日本語 2. 日本語 → 英語 ") == "2": inv = True
if input("1. DeepL 2.GoogleTranslate ") == "2": tool = "GT"
filename_ = input("出力ファイルにつける名前を入力してください（デフォルトは'translated_text.html'） ")
if filename_:
filename = filename_.replace(" ", "_")
title_ = input("（論文の）タイトルを入力してください ")
if title_:
title = title_
input("準備ができたらEnterを押してください")
multiThreadTranslate(n)
まとめ
HTMLやCSSはズブの素人なのでこうしたらもっと良くなる！という点があればご教示いただけると嬉しいです。