🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev
Python aiai-scrapingautomationcrawlercrawlingcrawling-pythondatadata-extractionmcpmcp-serverplaywrightpythonscrapingselectorsstealthweb-scraperweb-scrapingweb-scraping-pythonwebscrapingxpath
Testing some of the new tests on Github action
Karim shoaire594bba0c4e5
diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.ymlindex 77dd783..d6d6ef6 100644--- a/.github/workflows/tests.yml+++ b/.github/workflows/tests.yml@@ -44,6 +44,17 @@ jobs:with:python-version: ${{ matrix.python-version }}+ - name: Install Playwright Dependencies+ run: |+ pip install playwright+ playwright install chromium+ playwright install-deps chromium++ - name: Install Camoufox Dependencies+ run: |+ pip install camoufox+ python -m camoufox fetch --browserforge+- name: Run testsenv: ${{ matrix.env }}run: |diff --git a/tests/requirements.txt b/tests/requirements.txtindex cffeec6..fd7ef96 100644--- a/tests/requirements.txt+++ b/tests/requirements.txt@@ -1,2 +1,6 @@pytest-pytest-cov\ No newline at end of file+pytest-cov+playwright+camoufox+pytest-httpbin+pytest-playwrightdiff --git a/tests/test_fetchers/__init__.py b/tests/test_fetchers/__init__.pynew file mode 100644index 0000000..1014360--- /dev/null+++ b/tests/test_fetchers/__init__.py@@ -0,0 +1 @@+# Because I'm too lazy to mock requests :)diff --git a/tests/test_fetchers/test_stealthy_fetcher.py b/tests/test_fetchers/test_stealthy_fetcher.pynew file mode 100644index 0000000..b6c6182--- /dev/null+++ b/tests/test_fetchers/test_stealthy_fetcher.py@@ -0,0 +1,57 @@+import unittest+import pytest_httpbin++from scrapling import StealthyFetcher+++@pytest_httpbin.use_class_based_httpbin+# @pytest_httpbin.use_class_based_httpbin_secure+class TestParser(unittest.TestCase):+ def setUp(self):+ self.fetcher = StealthyFetcher(auto_match=False)+ # httpsbin = self.httpbin_secure.url+ url = self.httpbin.url+ self.status_200 = f'{url}/status/200'+ self.status_404 = f'{url}/status/404'+ self.status_501 = f'{url}/status/501'+ self.basic_url = f'{url}/get'+ self.html_url = f'{url}/html'++ def test_basic_fetch(self):+ """Test doing basic fetch request with multiple statuses"""+ self.assertEqual(self.fetcher.fetch(self.status_200).status, 200)+ self.assertEqual(self.fetcher.fetch(self.status_404).status, 404)+ self.assertEqual(self.fetcher.fetch(self.status_501).status, 501)++ def test_networkidle(self):+ """Test if waiting for `networkidle` make page does not finish loading or not"""+ self.assertEqual(self.fetcher.fetch(self.basic_url, network_idle=True).status, 200)++ def test_blocking_resources(self):+ """Test if blocking resources make page does not finish loading or not"""+ self.assertEqual(self.fetcher.fetch(self.basic_url, block_images=True).status, 200)+ self.assertEqual(self.fetcher.fetch(self.basic_url, disable_resources=True).status, 200)++ def test_waiting_selector(self):+ """Test if waiting for a selector make page does not finish loading or not"""+ self.assertEqual(self.fetcher.fetch(self.html_url, wait_selector='h1').status, 200)++ def test_automation(self):+ """Test if automation break the code or not"""+ def scroll_page(page):+ page.mouse.wheel(10, 0)+ page.mouse.move(100, 400)+ page.mouse.up()+ return page++ self.assertEqual(self.fetcher.fetch(self.html_url, page_action=scroll_page).status, 200)++ def test_properties(self):+ """Test if different arguments breaks the code or not"""+ self.assertEqual(self.fetcher.fetch(self.html_url, block_webrtc=True, allow_webgl=True).status, 200)+ self.assertEqual(self.fetcher.fetch(self.html_url, block_webrtc=False, allow_webgl=True).status, 200)+ self.assertEqual(self.fetcher.fetch(self.html_url, block_webrtc=True, allow_webgl=False).status, 200)++ def test_infinite_timeout(self):+ """Test if infinite timeout breaks the code or not"""+ self.assertEqual(self.fetcher.fetch(self.html_url, timeout=None).status, 200)diff --git a/tox.ini b/tox.iniindex 77d25dd..fdf42c3 100644--- a/tox.ini+++ b/tox.ini@@ -4,14 +4,18 @@# and then run "tox" from this directory.[tox]-envlist = pre-commit,py37,py38,py39,py310,py311,py312+envlist = pre-commit,py{38,39,310,311,312,313}[testenv]usedevelop = Truechangedir = testsdeps =-r{toxinidir}/tests/requirements.txt-commands = pytest --cov=scrapling --cov-report=xml+commands =+ playwright install chromium+ playwright install-deps chromium+ camoufox fetch --browserforge+ pytest --cov=scrapling --cov-report=xml[testenv:pre-commit]basepython = python3