From d488cdbb3bd7598d5c9f5fbeb26a094a71c9e94c Mon Sep 17 00:00:00 2001 From: Barbara Miller Date: Fri, 18 Oct 2024 16:40:24 -0700 Subject: [PATCH 1/2] fixes for chrome v.130 --- brozzler/browser.py | 2 -- brozzler/worker.py | 2 +- 2 files changed, 1 insertion(+), 3 deletions(-) diff --git a/brozzler/browser.py b/brozzler/browser.py index 9c72589..4b602f1 100644 --- a/brozzler/browser.py +++ b/brozzler/browser.py @@ -658,11 +658,9 @@ class Browser: ): headers = extra_headers or {} headers["Accept-Encoding"] = "gzip" # avoid encodings br, sdch - self.websock_thread.expect_result(self._command_id.peek()) msg_id = self.send_to_chrome( method="Network.setExtraHTTPHeaders", params={"headers": headers} ) - self._wait_for(lambda: self.websock_thread.received_result(msg_id), timeout=10) if user_agent: msg_id = self.send_to_chrome( method="Network.setUserAgentOverride", params={"userAgent": user_agent} diff --git a/brozzler/worker.py b/brozzler/worker.py index 116bb75..1d238a1 100644 --- a/brozzler/worker.py +++ b/brozzler/worker.py @@ -414,7 +414,7 @@ class BrozzlerWorker: self.logger.trace("%r", chrome_msg) if chrome_msg.get("params", {}).get("versions"): url = chrome_msg.get("params", {}).get("versions")[0].get("scriptURL") - if url and url not in sw_fetched: + if url and url.startswith('http') and url not in sw_fetched: self.logger.info("fetching service worker script %s", url) self._fetch_url(site, url=url) sw_fetched.add(url) From c781f53e3f8d53520ede477096d5fbdf72c9a4ca Mon Sep 17 00:00:00 2001 From: Barbara Miller Date: Mon, 2 Dec 2024 15:19:50 -0800 Subject: [PATCH 2/2] black'd --- brozzler/worker.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/brozzler/worker.py b/brozzler/worker.py index 1d238a1..3f9d15a 100644 --- a/brozzler/worker.py +++ b/brozzler/worker.py @@ -414,7 +414,7 @@ class BrozzlerWorker: self.logger.trace("%r", chrome_msg) if chrome_msg.get("params", {}).get("versions"): url = chrome_msg.get("params", {}).get("versions")[0].get("scriptURL") - if url and url.startswith('http') and url not in sw_fetched: + if url and url.startswith("http") and url not in sw_fetched: self.logger.info("fetching service worker script %s", url) self._fetch_url(site, url=url) sw_fetched.add(url)