Add --no-headless option to brozzle-page and brozzler-worker CLI

brozzler/cli.py

@@ -270,6 +270,12 @@ def brozzle_page(argv=None):
         help="use this password to try to log in if a login form is found",
     )
     arg_parser.add_argument("--proxy", dest="proxy", default=None, help="http proxy")
+    arg_parser.add_argument(
+        "--no-headless",
+        dest="headless",
+        action="store_false",
+        help="Do not run Chrome headlessly",
+    )
     arg_parser.add_argument(
         "--browser_throughput",
         type=int,
@@ -358,6 +364,7 @@ def brozzle_page(argv=None):
     worker = brozzler.BrozzlerWorker(
         frontier=None,
         proxy=args.proxy,
+        headless=args.headless,
         skip_extract_outlinks=args.skip_extract_outlinks,
         skip_visit_hashtags=args.skip_visit_hashtags,
         skip_youtube_dl=args.skip_youtube_dl,
@@ -390,6 +397,7 @@ def brozzle_page(argv=None):
             proxy=args.proxy,
             window_height=args.window_height,
             window_width=args.window_width,
+            headless=args.headless,
         )
         outlinks = worker.brozzle_page(
             browser,
@@ -568,6 +576,12 @@ def brozzler_worker(argv=None):
         help="max number of chrome instances simultaneously browsing pages",
     )
     arg_parser.add_argument("--proxy", dest="proxy", default=None, help="http proxy")
+    arg_parser.add_argument(
+        "--no-headless",
+        dest="headless",
+        action="store_false",
+        help="Do not run Chrome headlessly",
+    )
     arg_parser.add_argument(
         "--browser_throughput",
         type=int,
@@ -707,6 +721,7 @@ def brozzler_worker(argv=None):
         max_browsers=int(args.max_browsers),
         chrome_exe=args.chrome_exe,
         proxy=args.proxy,
+        headless=args.headless,
         warcprox_auto=args.warcprox_auto,
         skip_extract_outlinks=args.skip_extract_outlinks,
         skip_visit_hashtags=args.skip_visit_hashtags,

brozzler/worker.py

@@ -67,6 +67,7 @@ class BrozzlerWorker:
         chrome_exe="chromium-browser",
         warcprox_auto=False,
         proxy=None,
+        headless=True,
         skip_extract_outlinks=False,
         skip_visit_hashtags=False,
         skip_youtube_dl=False,
@@ -94,6 +95,7 @@ class BrozzlerWorker:
         self._proxy = proxy
         assert not (warcprox_auto and proxy)
         self._proxy_is_warcprox = None
+        self._headless = headless
         self._skip_extract_outlinks = skip_extract_outlinks
         self._skip_visit_hashtags = skip_visit_hashtags
         self._skip_youtube_dl = skip_youtube_dl
@@ -509,6 +511,7 @@ class BrozzlerWorker:
                 cookie_db=site.get("cookie_db"),
                 window_height=self._window_height,
                 window_width=self._window_width,
+                headless=self._headless,
             )
         final_page_url, outlinks = browser.browse_page(
             page.url,