Skip to content

Updated deepl DOM handling #314

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
Monsterovich wants to merge 4 commits into from
Closed

Updated deepl DOM handling #314

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
b6e50d1
Updated deepl DOM handling
Monsterovich Mar 4, 2026
984e650
fix: install call for Playwright browser
eggplants Mar 5, 2026
fb4089b
fix: added additional check for progress-text
Monsterovich Mar 5, 2026
f2c4034
fix: made it work
Monsterovich Apr 20, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
86 changes: 12 additions & 74 deletions deepl/deepl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,6 @@
from collections.abc import Coroutine
from typing import Any

from install_playwright import install
from playwright._impl._errors import Error as PlaywrightError
from playwright.async_api import ProxySettings, async_playwright
from playwright.async_api._generated import Browser, Playwright
Expand Down Expand Up @@ -130,7 +129,7 @@ async def __translate(self, script: str) -> str:
url = "https://www.deepl.com/en/translator"

async with page.expect_response(lambda resp: resp.url == url and resp.request.method == "GET") as resp_info:
await page.goto(url)
await page.goto(f"{url}#{self.fr_lang}/{self.to_lang}/{script}")

response = await resp_info.value

Expand All @@ -146,90 +145,30 @@ async def __translate(self, script: str) -> str:
msg = f"Maybe Time limit exceeded. ({self.timeout} ms)"
raise DeepLCLIPageLoadError(msg) from e

await page.locator(
"button[data-testid=translator-source-lang-btn]",
).dispatch_event("click")

await (
page.get_by_test_id("translator-source-lang-list")
.get_by_test_id(
f"translator-lang-option-{self.fr_lang}",
)
.first.dispatch_event("click")
)

await page.locator(
"button[data-testid=translator-target-lang-btn]",
).dispatch_event("click")

await (
page.get_by_test_id("translator-target-lang-list")
.get_by_test_id(
f"translator-lang-option-{self.to_lang}",
)
.first.dispatch_event("click")
)

await page.fill(
"div[aria-labelledby=translation-source-heading]",
script,
)

# Wait for translation to complete
try:
await page.wait_for_function(
"""
() => document.querySelector(
'd-textarea[aria-labelledby=translation-target-heading]')?.value?.length > 0
""",
timeout=self.timeout,
)
except PlaywrightError as e:
msg = f"Time limit exceeded. ({self.timeout} ms)"
raise DeepLCLIPageLoadError(msg) from e

# Wait for translation to complete (check that [...] placeholder is gone)
try:
await page.wait_for_function(
"""
() => {
const elem = document.querySelector('d-textarea[aria-labelledby=translation-target-heading]');
const text = elem?.value ?? '';
return text.length > 0 && !text.includes('[...]');
}
""",
timeout=self.timeout,
)
except PlaywrightError as e:
msg = f"Translation incomplete after {self.timeout} ms"
raise DeepLCLIPageLoadError(msg) from e
input_textbox = page.get_by_test_id("translator-source-input")
output_textbox = page.get_by_test_id("translator-target-input")

# Get the translated text directly from the value attribute
try:
res = await page.evaluate(
"""
document.querySelector(
'd-textarea[aria-labelledby=translation-target-heading]'
).value
""",
)
except PlaywrightError as e:
msg = "Unable to get translated text"
raise DeepLCLIPageLoadError(msg) from e
# Optional: wait explicitly if still flaky (usually not needed with data-testid)
await input_textbox.wait_for(state="visible", timeout=10000)

input_textbox = page.get_by_role("region", name="Source text").locator(
"d-textarea",
)
output_textbox = page.get_by_role(
"region",
name="Translation results",
).locator("d-textarea")

self.translated_fr_lang = str(
await input_textbox.get_attribute("lang"),
).split("-")[0]
self.translated_to_lang = str(
await output_textbox.get_attribute("lang"),
).split("-")[0]
self.translated_fr_lang = str(await input_textbox.get_attribute("lang") or "unknown").split("-")[0]
self.translated_to_lang = str(await output_textbox.get_attribute("lang") or "unknown").split("-")[0]

editable = output_textbox.locator('div[contenteditable="true"]')
res = await editable.inner_text()
res = res.replace("\n\n", "\n")

await browser.close()

Expand All @@ -251,7 +190,6 @@ def __sanitize_script(self, script: str) -> str:

async def __get_browser(self, p: Playwright) -> Browser:
"""Launch browser executable and get playwright browser object."""
install([p.chromium], with_deps=True)

return await p.chromium.launch(
headless=True,
Expand Down
Loading