he/py_facebook
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

修复发帖

Browse Source
This commit is contained in:
work
2026-04-02 13:36:36 +08:00
parent 48b0c6c53d
commit 29ef1ebc34
1 changed files with 109 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files

170
spider/task.py
View File

@@ -101,7 +101,7 @@ def _edit_privacy(page):
continue_btn.click()
sleep(1, 2)
page.click('//div[@aria-label="Select audience"]//span[text()="Public"]')
page.click('//div[@aria-label="Save"]')
page.click('//div[@aria-label="Save privacy audience selection and close dialog"]')
sleep(1, 2)
return
else:
@@ -111,7 +111,7 @@ def _edit_privacy(page):
page.click('//div[contains(@aria-label, "Edit privacy")]')
sleep(1, 2)
page.click('//div[@aria-label="Select audience"]//span[text()="Public"]')
page.click('//div[@aria-label="Done"]')
page.click('//div[@aria-label="Done with privacy audience selection and close dialog"]')
sleep(1, 2)
except Error as e:
logger.error(f"Error editing privacy settings: {e}")
@@ -225,6 +225,17 @@ def is_operation_failed(exception):
return isinstance(exception, OperationFailed) and "更改语言异常" in str(exception)
def is_page_crash_error(exception: Exception) -> bool:
error_message = str(exception).lower()
crash_patterns = (
"page crashed",
"target crashed",
"target page, context or browser has been closed",
"browser has been closed",
)
return any(pattern in error_message for pattern in crash_patterns)
@retry(
stop=stop_after_attempt(3),
wait=wait_fixed(2),
@@ -450,77 +461,110 @@ def retry_get_new_video(page, cookies, post_count):
raise TimeoutError("未获取到新视频(可能视频上传失败)，已超时")
@retry(
stop=stop_after_attempt(3),
wait=wait_fixed(2),
retry=retry_if_exception(is_operation_failed)
)
def playwright_post(cookies, content, image_key=None):
path = os.path.join(BASE_PATH, 'chrome', '130-0008', 'chrome.exe')
with lock:
with sync_playwright() as playwright:
update_windows_distinguish()
browser = playwright.chromium.launch(
headless=False, args=['--start-maximized'], executable_path=path
)
context = browser.new_context(no_viewport=True)
context.add_cookies(parse_cookies(cookies))
page = context.new_page()
page.evaluate(f'document.body.style.zoom = "{const.DISPLAY_SCALE}"')
max_browser_retries = 3
last_error = None
check_account_status(page, parse_cookies(cookies))
# 声明默认发布视频数量
video_count = 0
for browser_attempt in range(max_browser_retries):
browser = None
context = None
file_path = None
try:
browser = playwright.chromium.launch(
headless=False, args=['--start-maximized'], executable_path=path
)
context = browser.new_context(no_viewport=True)
context.add_cookies(parse_cookies(cookies))
page = context.new_page()
url = 'https://facebook.com'
try:
# 先获取视频数量
if image_key is not None and ".mp4" in image_key:
video_count = get_post_count(page, cookies)
check_account_status(page, parse_cookies(cookies))
# 声明默认发布视频数量
video_count = 0
retry_goto(page, url)
time.sleep(random.randint(3, 10))
time.sleep(5)
url = 'https://www.facebook.com'
# 先获取视频数量
if image_key is not None and ".mp4" in image_key:
video_count = get_post_count(page, cookies)
if image_key:
filename = image_key.split('/')[-1]
file_path = os.path.join(BASE_PATH, 'files', filename)
client.fget_object(BUCKET, image_key, file_path)
sleep(1, 2)
page.locator('input[accept="image/*,image/heif,image/heic,video/*,video/mp4,video/x-m4v,video/x-matroska,.mkv"]').set_input_files(file_path)
# check_account_status 已经把页面带到 Facebook 首页，避免重复二次跳转导致页面进程崩溃
if "facebook.com" not in page.url:
retry_goto(page, url)
time.sleep(random.randint(3, 10))
time.sleep(5)
if not image_key:
page.click('''//span[contains(text(), "What's on your mind")]''')
_edit_privacy(page)
# 修改后 (使用 fill)
page.fill('//div[contains(@aria-placeholder, "What\'s on your mind")]', content,
timeout=300000)
page.click('//div[@aria-label="Post"]', timeout=300000)
time.sleep(15)
post_index = page.locator('//div[@aria-posinset="1"]//a[@role="link"]').nth(2)
post_index.click(timeout=600000)
time.sleep(5)
page.reload(timeout=180000)
post_url = page.url
# 视频格式要单独去获取链接
if image_key is not None and ".mp4" in image_key:
post_url = retry_get_new_video(page, cookies, video_count)
time.sleep(random.randint(3, 10))
if image_key:
filename = image_key.split('/')[-1]
file_path = os.path.join(BASE_PATH, 'files', filename)
client.fget_object(BUCKET, image_key, file_path)
except Error as e:
raise OperationFailed(f'操作超时，请重试{e}')
sleep(1, 2)
page.locator('input[accept="image/*,image/heif,image/heic,video/*,video/mp4,video/x-m4v,video/x-matroska,.mkv"]').set_input_files(file_path)
time.sleep(5)
screenshot_content = _full_screenshot()
if image_key:
os.remove(file_path)
context.close()
browser.close()
if not image_key:
page.click('''//span[contains(text(), "What's on your mind")]''')
_edit_privacy(page)
# 修改后 (使用 fill)
page.fill('//div[contains(@aria-placeholder, "What\'s on your mind")]', content,
timeout=300000)
page.click('//div[@aria-label="Post"]', timeout=300000)
time.sleep(15)
post_index = page.locator('//div[@aria-posinset="1"]//a[@role="link"]').nth(2)
post_index.click(timeout=600000)
time.sleep(5)
page.reload(timeout=180000)
post_url = page.url
# 视频格式要单独去获取链接
if image_key is not None and ".mp4" in image_key:
post_url = retry_get_new_video(page, cookies, video_count)
time.sleep(random.randint(3, 10))
key = f'screenshot/{uuid.uuid4()}.png'
put_object(key, screenshot_content)
return {'response_url': post_url, 'screenshot_key': key}
screenshot_content = _full_screenshot()
key = f'screenshot/{uuid.uuid4()}.png'
put_object(key, screenshot_content)
return {'response_url': post_url, 'screenshot_key': key}
except TimeoutError as e:
last_error = e
logger.warning(
f"发布任务超时，尝试重建浏览器重试: attempt {browser_attempt + 1}/{max_browser_retries}, error={e}"
)
except Error as e:
last_error = e
if is_page_crash_error(e):
logger.warning(
f"发布任务页面崩溃，尝试重建浏览器重试: attempt {browser_attempt + 1}/{max_browser_retries}, error={e}"
)
else:
logger.warning(
f"发布任务 Playwright 异常，尝试重试: attempt {browser_attempt + 1}/{max_browser_retries}, error={e}"
)
finally:
if image_key and file_path and os.path.exists(file_path):
os.remove(file_path)
if context is not None:
try:
context.close()
except Exception:
pass
if browser is not None:
try:
browser.close()
except Exception:
pass
if browser_attempt < max_browser_retries - 1:
time.sleep(2)
if isinstance(last_error, TimeoutError):
raise OperationFailed(f'操作超时，请重试: {last_error}')
if isinstance(last_error, Error) and is_page_crash_error(last_error):
raise OperationFailed(f'页面崩溃，请重试: {last_error}')
raise OperationFailed(f'操作失败，请重试: {last_error}')
def playwright_comment(cookies, target_url, content, image_key=None):
@@ -772,11 +816,15 @@ def retry_goto(page: "Page", url: str, max_retries: int = 3, retry_delay: int =
print(f"All {max_retries} attempts failed for {url}.")
# If all retries fail, re-raise the exception
raise e
except Error as e:
if is_page_crash_error(e):
logger.error(f"Navigation page crashed for {url} on attempt {attempt + 1}: {e}")
else:
logger.error(f"Navigation playwright error for {url} on attempt {attempt + 1}: {e}")
raise e
except Exception as e:
# Catch any other unexpected errors during goto
print(f"An unexpected error occurred during navigation to {url} on attempt {attempt + 1}: {e}")
# Decide if other exceptions should also trigger retries
# For now, we'll just re-raise other exceptions immediately
raise e