Fixed Playwright sandbox freezing issue in Docker

scraper/aishe_downloader.py

@@ -115,7 +115,10 @@ def download_all_sections(
             print(msg, flush=True)
 
     with sync_playwright() as pw:
-        browser = pw.chromium.launch(headless=headless)
+        browser = pw.chromium.launch(
+            headless=headless,
+            args=["--no-sandbox", "--disable-dev-shm-usage"]
+        )
         context = browser.new_context(accept_downloads=True)
         page = context.new_page()
 

scraper/naac_downloader.py

@@ -13,7 +13,10 @@ def download_naac(output_dir: Path, headless: bool = True, log_fn=None) -> Path:
     output_dir.mkdir(parents=True, exist_ok=True)
     
     with sync_playwright() as p:
-        browser = p.chromium.launch(headless=headless)
+        browser = p.chromium.launch(
+            headless=headless,
+            args=["--no-sandbox", "--disable-dev-shm-usage"]
+        )
         context = browser.new_context(accept_downloads=True)
         page = context.new_page()
 

scraper/ugc_downloader.py

@@ -14,7 +14,10 @@ def download_ugc(output_dir: Path, headless: bool = True, log_fn=None) -> Path:
     save_path = output_dir / "ugc_raw.xlsx"
 
     with sync_playwright() as pw:
-        browser = pw.chromium.launch(headless=headless)
+        browser = pw.chromium.launch(
+            headless=headless,
+            args=["--no-sandbox", "--disable-dev-shm-usage"]
+        )
         context = browser.new_context(accept_downloads=True)
         page = context.new_page()