Goodreads returns an empty HTML page to headless browsers it identifies as automated (navigator.webdriver=true, AutomationControlled feature). This caused the Export Library button to never be found. - Launch Chromium with --disable-blink-features=AutomationControlled - Set a realistic user agent and viewport on the browser context - Strip navigator.webdriver via an init script - Guard the logged_in check so a blank page isn't mistaken for a session - Wait for networkidle before querying the export button, and use wait_for(visible) instead of is_visible() to tolerate JS render delay - Add CSS class fallback (button.js-LibraryExport) if role lookup fails - Add AGENTS.md documenting the bot detection pattern and export flow Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
211 lines
6.8 KiB
Python
Executable file
211 lines
6.8 KiB
Python
Executable file
#!/usr/bin/python3
|
|
"""Backup list of books from Goodreads."""
|
|
|
|
import argparse
|
|
import configparser
|
|
import os
|
|
import sys
|
|
import time
|
|
from datetime import date
|
|
from urllib.parse import urljoin
|
|
|
|
from playwright.sync_api import Page, Playwright, TimeoutError, sync_playwright
|
|
|
|
|
|
refresh_backup = True
|
|
|
|
today = date.today().isoformat() # current date in ISO format
|
|
|
|
config = configparser.ConfigParser()
|
|
|
|
config_file_path = os.path.expanduser(
|
|
os.path.join(os.getenv("XDG_CONFIG_HOME", "~/.config"), "goodreads", "config")
|
|
)
|
|
assert os.path.exists(config_file_path)
|
|
config.read(os.path.expanduser(config_file_path))
|
|
script_dir = os.path.dirname(os.path.abspath(__file__))
|
|
|
|
|
|
def login(page: Page) -> None:
|
|
"""Login to Goodreads."""
|
|
page.get_by_role("link", name="Sign In").click()
|
|
page.get_by_role("button", name="Sign in with email").click()
|
|
page.get_by_label("Email").fill(config.get("login", "email"))
|
|
page.get_by_label("Password").fill(config.get("login", "password"))
|
|
page.get_by_role("checkbox", name="Keep me signed in").check()
|
|
try:
|
|
page.get_by_label("Sign in").click()
|
|
except TimeoutError:
|
|
# The submit can succeed but never reach Playwright's expected navigation state.
|
|
pass
|
|
|
|
|
|
def run_backup(page: Page) -> None:
|
|
"""Run backup."""
|
|
import_url = "https://www.goodreads.com/review/import"
|
|
page.goto(import_url)
|
|
page.wait_for_load_state("networkidle")
|
|
|
|
|
|
if refresh_backup:
|
|
print("backup requested")
|
|
export_button = page.get_by_role("button", name="Export Library")
|
|
# Fall back to CSS class in case accessible name lookup fails
|
|
if export_button.count() == 0:
|
|
export_button = page.locator("button.js-LibraryExport")
|
|
found = False
|
|
if export_button.count() > 0:
|
|
try:
|
|
export_button.first.wait_for(state="visible", timeout=10 * 1000)
|
|
found = True
|
|
except TimeoutError:
|
|
pass
|
|
if found:
|
|
export_button.first.click()
|
|
print("waiting for export to be ready...")
|
|
|
|
# JS clears #exportFile when generation starts, then populates it when ready.
|
|
export_file_link = page.locator("#exportFile a")
|
|
try:
|
|
export_file_link.wait_for(state="hidden", timeout=30 * 1000)
|
|
except TimeoutError:
|
|
pass
|
|
export_file_link.wait_for(state="visible", timeout=15 * 60 * 1000)
|
|
print("export ready")
|
|
else:
|
|
print("Export Library button not found, using latest ready export link")
|
|
|
|
print("download export")
|
|
export_link = page.get_by_role("link", name="Your export from").first
|
|
export_link.wait_for(state="visible", timeout=2 * 60 * 1000)
|
|
print(export_link.text_content())
|
|
href = export_link.get_attribute("href")
|
|
download_url = urljoin(page.url, href) if href else None
|
|
backup_dir = config.get("backup", "dir")
|
|
|
|
save_to = os.path.join(backup_dir, f"{today}_goodreads_library_export.csv")
|
|
try:
|
|
with page.expect_download(timeout=30 * 1000) as download_info:
|
|
export_link.click()
|
|
download = download_info.value
|
|
download.save_as(save_to)
|
|
except TimeoutError:
|
|
if not download_url:
|
|
raise RuntimeError("Could not find export download URL")
|
|
response = None
|
|
for _ in range(60):
|
|
response = page.context.request.get(download_url)
|
|
if response.ok:
|
|
with open(save_to, "wb") as fh:
|
|
fh.write(response.body())
|
|
break
|
|
time.sleep(2)
|
|
else:
|
|
assert response is not None
|
|
raise RuntimeError(f"Export download failed with status {response.status}")
|
|
|
|
|
|
def has_auth(path: str) -> bool:
|
|
"""Check if auth.json exists and is non-empty."""
|
|
return os.path.exists(path) and os.path.getsize(path) > 0
|
|
|
|
|
|
def run(
|
|
playwright: Playwright,
|
|
headless: bool = True,
|
|
har_path: str | None = None,
|
|
mode: str = "backup",
|
|
) -> int:
|
|
"""Download export."""
|
|
browser = playwright.chromium.launch(
|
|
headless=headless,
|
|
args=["--disable-blink-features=AutomationControlled"],
|
|
)
|
|
# Spoof user agent and viewport to look like a regular desktop browser.
|
|
context_kwargs: dict = dict(
|
|
user_agent=(
|
|
"Mozilla/5.0 (X11; Linux x86_64) "
|
|
"AppleWebKit/537.36 (KHTML, like Gecko) "
|
|
"Chrome/131.0.0.0 Safari/537.36"
|
|
),
|
|
viewport={"width": 1280, "height": 800},
|
|
)
|
|
auth_json = os.path.join(script_dir, "auth.json")
|
|
if has_auth(auth_json):
|
|
context_kwargs["storage_state"] = auth_json
|
|
if har_path:
|
|
context_kwargs["record_har_path"] = har_path
|
|
context_kwargs["record_har_mode"] = "minimal"
|
|
context = browser.new_context(**context_kwargs)
|
|
# Remove the navigator.webdriver flag that headless Chrome exposes.
|
|
context.add_init_script(
|
|
"Object.defineProperty(navigator, 'webdriver', {get: () => undefined})"
|
|
)
|
|
page = context.new_page()
|
|
|
|
page.goto("https://www.goodreads.com/")
|
|
page.wait_for_load_state("domcontentloaded")
|
|
# A blank page (bot-detection response) has no body content; treat as not logged in.
|
|
page_has_content = page.locator("body").inner_text().strip() != ""
|
|
logged_in = page_has_content and not page.get_by_role("link", name="Sign In").is_visible()
|
|
|
|
if mode == "check_login":
|
|
print("logged in" if logged_in else "not logged in")
|
|
page.close()
|
|
context.close()
|
|
browser.close()
|
|
return 0 if logged_in else 1
|
|
|
|
if not logged_in:
|
|
print("not logged in, logging in...")
|
|
login(page)
|
|
|
|
if mode == "login_only":
|
|
print("login complete")
|
|
else:
|
|
run_backup(page)
|
|
|
|
page.close()
|
|
|
|
context.storage_state(path=auth_json)
|
|
context.close()
|
|
browser.close()
|
|
return 0
|
|
|
|
|
|
parser = argparse.ArgumentParser(description="Backup list of books from Goodreads.")
|
|
parser.add_argument(
|
|
"--no-headless", action="store_true", help="run browser with a visible window"
|
|
)
|
|
parser.add_argument(
|
|
"--har-path",
|
|
help="record a HAR file for this run (includes login/export requests)",
|
|
)
|
|
mode_group = parser.add_mutually_exclusive_group()
|
|
mode_group.add_argument(
|
|
"--check-login",
|
|
action="store_true",
|
|
help="check whether current session is logged in and exit",
|
|
)
|
|
mode_group.add_argument(
|
|
"--login-only",
|
|
action="store_true",
|
|
help="perform login and save auth state without exporting CSV",
|
|
)
|
|
args = parser.parse_args()
|
|
|
|
mode = "backup"
|
|
if args.check_login:
|
|
mode = "check_login"
|
|
elif args.login_only:
|
|
mode = "login_only"
|
|
|
|
with sync_playwright() as playwright:
|
|
sys.exit(
|
|
run(
|
|
playwright,
|
|
headless=not args.no_headless,
|
|
har_path=args.har_path,
|
|
mode=mode,
|
|
)
|
|
)
|