Official Crawl4AI Cloud: a hosted web scraping, extraction, and search API for AI agents. Free API key, 1,000 credits a month, no card. Fully open source: this repo is the Apache-2.0 crawler that powers it, and you can self-host it.
Python aiai-agentscrawl4ai-cloudcrawlerdata-extractionllmmarkdownmcpopen-sourceplaywrightpythonragscraperweb-crawlerweb-crawlingweb-scraping
Decode percent-encoded credentials in ProxyConfig.from_string
omarbounawarapy8b3a75da5fbc
diff --git a/crawl4ai/async_configs.py b/crawl4ai/async_configs.pyindex e76cae18..cc1efdb8 100644--- a/crawl4ai/async_configs.py+++ b/crawl4ai/async_configs.py@@ -3,6 +3,7 @@ import functoolsimport importlibimport osimport warnings+from urllib.parse import unquoteimport requestsfrom .config import (DEFAULT_PROVIDER,@@ -711,8 +712,8 @@ class ProxyConfig:username, password = credentials.split(":", 1)return ProxyConfig(server=f"{protocol}://{server_part}",- username=username,- password=password,+ username=unquote(username),+ password=unquote(password),)# URL without credentials (keep scheme)if "://" in s and "@" not in s:diff --git a/tests/proxy/test_http_proxy_url_encoding.py b/tests/proxy/test_http_proxy_url_encoding.pyindex e6d75d97..9e7515a1 100644--- a/tests/proxy/test_http_proxy_url_encoding.py+++ b/tests/proxy/test_http_proxy_url_encoding.py@@ -16,3 +16,12 @@ def test_proxy_url_roundtrips_credentials(password):assert url.port == 8080assert url.user == "us:er"assert url.password == password+++def test_encoded_proxy_string_is_sent_once_encoded():+ strategy = AsyncHTTPCrawlerStrategy()+ config = ProxyConfig.from_string("http://user:p%40ss@host:8080")+ assert config.password == "p@ss"+ url = URL(strategy._format_proxy_url(config))+ assert url.user == "user"+ assert url.password == "p@ss"