diff --git a/docker/crawler/requirements.txt b/docker/crawler/requirements.txt index ce48f80d..171331da 100644 --- a/docker/crawler/requirements.txt +++ b/docker/crawler/requirements.txt @@ -2,6 +2,7 @@ # HTTP 请求 aiohttp>=3.9.0 requests>=2.31.0 +googlenewsdecoder>=0.1.7 httpx>=0.27.0 curl_cffi>=0.7.0 # TLS 指纹模拟 (绕过 JA3 检测) diff --git a/qa/crawler/test_news_collection_static.py b/qa/crawler/test_news_collection_static.py index 712dfe8f..16369cd9 100644 --- a/qa/crawler/test_news_collection_static.py +++ b/qa/crawler/test_news_collection_static.py @@ -39,6 +39,10 @@ class NewsCollectionRegressionTest(unittest.TestCase): source = self.read(name) self.assertIn("allow_summary=True", source, name) + def test_crawler_installs_google_news_decoder(self): + requirements = (CRAWLER / "requirements.txt").read_text(encoding="utf-8") + self.assertRegex(requirements, r"(?m)^googlenewsdecoder(?:[<>=!~].*)?$") + if __name__ == "__main__": unittest.main()