scrapling 0.2.99__py3-none-any.whl → 0.3.1__py3-none-any.whl

tests/fetchers/sync/test_camoufox.py

@@ -1,70 +0,0 @@
-import pytest
-import pytest_httpbin
-
-from scrapling import StealthyFetcher
-
-StealthyFetcher.auto_match = True
-
-
-@pytest_httpbin.use_class_based_httpbin
-class TestStealthyFetcher:
-    @pytest.fixture(scope="class")
-    def fetcher(self):
-        """Fixture to create a StealthyFetcher instance for the entire test class"""
-        return StealthyFetcher
-
-    @pytest.fixture(autouse=True)
-    def setup_urls(self, httpbin):
-        """Fixture to set up URLs for testing"""
-        self.status_200 = f'{httpbin.url}/status/200'
-        self.status_404 = f'{httpbin.url}/status/404'
-        self.status_501 = f'{httpbin.url}/status/501'
-        self.basic_url = f'{httpbin.url}/get'
-        self.html_url = f'{httpbin.url}/html'
-        self.delayed_url = f'{httpbin.url}/delay/10'  # 10 Seconds delay response
-        self.cookies_url = f"{httpbin.url}/cookies/set/test/value"
-
-    def test_basic_fetch(self, fetcher):
-        """Test doing basic fetch request with multiple statuses"""
-        assert fetcher.fetch(self.status_200).status == 200
-        assert fetcher.fetch(self.status_404).status == 404
-        assert fetcher.fetch(self.status_501).status == 501
-
-    def test_networkidle(self, fetcher):
-        """Test if waiting for `networkidle` make page does not finish loading or not"""
-        assert fetcher.fetch(self.basic_url, network_idle=True).status == 200
-
-    def test_blocking_resources(self, fetcher):
-        """Test if blocking resources make page does not finish loading or not"""
-        assert fetcher.fetch(self.basic_url, block_images=True).status == 200
-        assert fetcher.fetch(self.basic_url, disable_resources=True).status == 200
-
-    def test_waiting_selector(self, fetcher):
-        """Test if waiting for a selector make page does not finish loading or not"""
-        assert fetcher.fetch(self.html_url, wait_selector='h1').status == 200
-        assert fetcher.fetch(self.html_url, wait_selector='h1', wait_selector_state='visible').status == 200
-
-    def test_cookies_loading(self, fetcher):
-        """Test if cookies are set after the request"""
-        assert fetcher.fetch(self.cookies_url).cookies == {'test': 'value'}
-
-    def test_automation(self, fetcher):
-        """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
-
-        assert fetcher.fetch(self.html_url, page_action=scroll_page).status == 200
-
-    def test_properties(self, fetcher):
-        """Test if different arguments breaks the code or not"""
-        assert fetcher.fetch(self.html_url, block_webrtc=True, allow_webgl=True).status == 200
-        assert fetcher.fetch(self.html_url, block_webrtc=False, allow_webgl=True).status == 200
-        assert fetcher.fetch(self.html_url, block_webrtc=True, allow_webgl=False).status == 200
-        assert fetcher.fetch(self.html_url, extra_headers={'ayo': ''}, os_randomize=True).status == 200
-
-    def test_infinite_timeout(self, fetcher):
-        """Test if infinite timeout breaks the code or not"""
-        assert fetcher.fetch(self.delayed_url, timeout=None).status == 200

tests/fetchers/sync/test_httpx.py

@@ -1,84 +0,0 @@
-import pytest
-import pytest_httpbin
-
-from scrapling import Fetcher
-
-Fetcher.auto_match = True
-
-
-@pytest_httpbin.use_class_based_httpbin
-class TestFetcher:
-    @pytest.fixture(scope="class")
-    def fetcher(self):
-        """Fixture to create a Fetcher instance for the entire test class"""
-        return Fetcher
-
-    @pytest.fixture(autouse=True)
-    def setup_urls(self, httpbin):
-        """Fixture to set up URLs for testing"""
-        self.status_200 = f'{httpbin.url}/status/200'
-        self.status_404 = f'{httpbin.url}/status/404'
-        self.status_501 = f'{httpbin.url}/status/501'
-        self.basic_url = f'{httpbin.url}/get'
-        self.post_url = f'{httpbin.url}/post'
-        self.put_url = f'{httpbin.url}/put'
-        self.delete_url = f'{httpbin.url}/delete'
-        self.html_url = f'{httpbin.url}/html'
-
-    def test_basic_get(self, fetcher):
-        """Test doing basic get request with multiple statuses"""
-        assert fetcher.get(self.status_200).status == 200
-        assert fetcher.get(self.status_404).status == 404
-        assert fetcher.get(self.status_501).status == 501
-
-    def test_get_properties(self, fetcher):
-        """Test if different arguments with GET request breaks the code or not"""
-        assert fetcher.get(self.status_200, stealthy_headers=True).status == 200
-        assert fetcher.get(self.status_200, follow_redirects=True).status == 200
-        assert fetcher.get(self.status_200, timeout=None).status == 200
-        assert fetcher.get(
-            self.status_200,
-            stealthy_headers=True,
-            follow_redirects=True,
-            timeout=None
-        ).status == 200
-
-    def test_post_properties(self, fetcher):
-        """Test if different arguments with POST request breaks the code or not"""
-        assert fetcher.post(self.post_url, data={'key': 'value'}).status == 200
-        assert fetcher.post(self.post_url, data={'key': 'value'}, stealthy_headers=True).status == 200
-        assert fetcher.post(self.post_url, data={'key': 'value'}, follow_redirects=True).status == 200
-        assert fetcher.post(self.post_url, data={'key': 'value'}, timeout=None).status == 200
-        assert fetcher.post(
-            self.post_url,
-            data={'key': 'value'},
-            stealthy_headers=True,
-            follow_redirects=True,
-            timeout=None
-        ).status == 200
-
-    def test_put_properties(self, fetcher):
-        """Test if different arguments with PUT request breaks the code or not"""
-        assert fetcher.put(self.put_url, data={'key': 'value'}).status == 200
-        assert fetcher.put(self.put_url, data={'key': 'value'}, stealthy_headers=True).status == 200
-        assert fetcher.put(self.put_url, data={'key': 'value'}, follow_redirects=True).status == 200
-        assert fetcher.put(self.put_url, data={'key': 'value'}, timeout=None).status == 200
-        assert fetcher.put(
-            self.put_url,
-            data={'key': 'value'},
-            stealthy_headers=True,
-            follow_redirects=True,
-            timeout=None
-        ).status == 200
-
-    def test_delete_properties(self, fetcher):
-        """Test if different arguments with DELETE request breaks the code or not"""
-        assert fetcher.delete(self.delete_url, stealthy_headers=True).status == 200
-        assert fetcher.delete(self.delete_url, follow_redirects=True).status == 200
-        assert fetcher.delete(self.delete_url, timeout=None).status == 200
-        assert fetcher.delete(
-            self.delete_url,
-            stealthy_headers=True,
-            follow_redirects=True,
-            timeout=None
-        ).status == 200

tests/fetchers/sync/test_playwright.py

@@ -1,89 +0,0 @@
-import pytest
-import pytest_httpbin
-
-from scrapling import PlayWrightFetcher
-
-PlayWrightFetcher.auto_match = True
-
-
-@pytest_httpbin.use_class_based_httpbin
-class TestPlayWrightFetcher:
-
-    @pytest.fixture(scope="class")
-    def fetcher(self):
-        """Fixture to create a StealthyFetcher instance for the entire test class"""
-        return PlayWrightFetcher
-
-    @pytest.fixture(autouse=True)
-    def setup_urls(self, httpbin):
-        """Fixture to set up URLs for testing"""
-        self.status_200 = f'{httpbin.url}/status/200'
-        self.status_404 = f'{httpbin.url}/status/404'
-        self.status_501 = f'{httpbin.url}/status/501'
-        self.basic_url = f'{httpbin.url}/get'
-        self.html_url = f'{httpbin.url}/html'
-        self.delayed_url = f'{httpbin.url}/delay/10'  # 10 Seconds delay response
-        self.cookies_url = f"{httpbin.url}/cookies/set/test/value"
-
-    def test_basic_fetch(self, fetcher):
-        """Test doing basic fetch request with multiple statuses"""
-        assert fetcher.fetch(self.status_200).status == 200
-        # There's a bug with playwright makes it crashes if a URL returns status code 4xx/5xx without body, let's disable this till they reply to my issue report
-        # assert fetcher.fetch(self.status_404).status == 404
-        # assert fetcher.fetch(self.status_501).status == 501
-
-    def test_networkidle(self, fetcher):
-        """Test if waiting for `networkidle` make page does not finish loading or not"""
-        assert fetcher.fetch(self.basic_url, network_idle=True).status == 200
-
-    def test_blocking_resources(self, fetcher):
-        """Test if blocking resources make page does not finish loading or not"""
-        assert fetcher.fetch(self.basic_url, disable_resources=True).status == 200
-
-    def test_waiting_selector(self, fetcher):
-        """Test if waiting for a selector make page does not finish loading or not"""
-        assert fetcher.fetch(self.html_url, wait_selector='h1').status == 200
-        assert fetcher.fetch(self.html_url, wait_selector='h1', wait_selector_state='visible').status == 200
-
-    def test_cookies_loading(self, fetcher):
-        """Test if cookies are set after the request"""
-        assert fetcher.fetch(self.cookies_url).cookies == {'test': 'value'}
-
-    def test_automation(self, fetcher):
-        """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
-
-        assert fetcher.fetch(self.html_url, page_action=scroll_page).status == 200
-
-    @pytest.mark.parametrize("kwargs", [
-        {"disable_webgl": True, "hide_canvas": False},
-        {"disable_webgl": False, "hide_canvas": True},
-        # {"stealth": True}, # causes issues with Github Actions
-        {"useragent": 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:131.0) Gecko/20100101 Firefox/131.0'},
-        {"extra_headers": {'ayo': ''}}
-    ])
-    def test_properties(self, fetcher, kwargs):
-        """Test if different arguments breaks the code or not"""
-        response = fetcher.fetch(self.html_url, **kwargs)
-        assert response.status == 200
-
-    def test_cdp_url_invalid(self, fetcher):
-        """Test if invalid CDP URLs raise appropriate exceptions"""
-        with pytest.raises(ValueError):
-            fetcher.fetch(self.html_url, cdp_url='blahblah')
-
-        with pytest.raises(ValueError):
-            fetcher.fetch(self.html_url, cdp_url='blahblah', nstbrowser_mode=True)
-
-        with pytest.raises(Exception):
-            fetcher.fetch(self.html_url, cdp_url='ws://blahblah')
-
-    def test_infinite_timeout(self, fetcher, ):
-        """Test if infinite timeout breaks the code or not"""
-        response = fetcher.fetch(self.delayed_url, timeout=None)
-        assert response.status == 200

tests/fetchers/test_utils.py

@@ -1,97 +0,0 @@
-import pytest
-
-from scrapling.engines.toolbelt.custom import ResponseEncoding, StatusText
-
-
-@pytest.fixture
-def content_type_map():
-    return {
-        # A map generated by ChatGPT for most possible `content_type` values and the expected outcome
-        'text/html; charset=UTF-8': 'UTF-8',
-        'text/html; charset=ISO-8859-1': 'ISO-8859-1',
-        'text/html': 'ISO-8859-1',
-        'application/json; charset=UTF-8': 'UTF-8',
-        'application/json': 'utf-8',
-        'text/json': 'utf-8',
-        'application/javascript; charset=UTF-8': 'UTF-8',
-        'application/javascript': 'utf-8',
-        'text/plain; charset=UTF-8': 'UTF-8',
-        'text/plain; charset=ISO-8859-1': 'ISO-8859-1',
-        'text/plain': 'ISO-8859-1',
-        'application/xhtml+xml; charset=UTF-8': 'UTF-8',
-        'application/xhtml+xml': 'utf-8',
-        'text/html; charset=windows-1252': 'windows-1252',
-        'application/json; charset=windows-1252': 'windows-1252',
-        'text/plain; charset=windows-1252': 'windows-1252',
-        'text/html; charset="UTF-8"': 'UTF-8',
-        'text/html; charset="ISO-8859-1"': 'ISO-8859-1',
-        'text/html; charset="windows-1252"': 'windows-1252',
-        'application/json; charset="UTF-8"': 'UTF-8',
-        'application/json; charset="ISO-8859-1"': 'ISO-8859-1',
-        'application/json; charset="windows-1252"': 'windows-1252',
-        'text/json; charset="UTF-8"': 'UTF-8',
-        'application/javascript; charset="UTF-8"': 'UTF-8',
-        'application/javascript; charset="ISO-8859-1"': 'ISO-8859-1',
-        'text/plain; charset="UTF-8"': 'UTF-8',
-        'text/plain; charset="ISO-8859-1"': 'ISO-8859-1',
-        'text/plain; charset="windows-1252"': 'windows-1252',
-        'application/xhtml+xml; charset="UTF-8"': 'UTF-8',
-        'application/xhtml+xml; charset="ISO-8859-1"': 'ISO-8859-1',
-        'application/xhtml+xml; charset="windows-1252"': 'windows-1252',
-        'text/html; charset="US-ASCII"': 'US-ASCII',
-        'application/json; charset="US-ASCII"': 'US-ASCII',
-        'text/plain; charset="US-ASCII"': 'US-ASCII',
-        'text/html; charset="Shift_JIS"': 'Shift_JIS',
-        'application/json; charset="Shift_JIS"': 'Shift_JIS',
-        'text/plain; charset="Shift_JIS"': 'Shift_JIS',
-        'application/xml; charset="UTF-8"': 'UTF-8',
-        'application/xml; charset="ISO-8859-1"': 'ISO-8859-1',
-        'application/xml': 'utf-8',
-        'text/xml; charset="UTF-8"': 'UTF-8',
-        'text/xml; charset="ISO-8859-1"': 'ISO-8859-1',
-        'text/xml': 'utf-8'
-    }
-
-
-@pytest.fixture
-def status_map():
-    return {
-        100: "Continue", 101: "Switching Protocols", 102: "Processing", 103: "Early Hints",
-        200: "OK", 201: "Created", 202: "Accepted", 203: "Non-Authoritative Information",
-        204: "No Content", 205: "Reset Content", 206: "Partial Content", 207: "Multi-Status",
-        208: "Already Reported", 226: "IM Used", 300: "Multiple Choices",
-        301: "Moved Permanently", 302: "Found", 303: "See Other", 304: "Not Modified",
-        305: "Use Proxy", 307: "Temporary Redirect", 308: "Permanent Redirect",
-        400: "Bad Request", 401: "Unauthorized", 402: "Payment Required", 403: "Forbidden",
-        404: "Not Found", 405: "Method Not Allowed", 406: "Not Acceptable",
-        407: "Proxy Authentication Required", 408: "Request Timeout", 409: "Conflict",
-        410: "Gone", 411: "Length Required", 412: "Precondition Failed",
-        413: "Payload Too Large", 414: "URI Too Long", 415: "Unsupported Media Type",
-        416: "Range Not Satisfiable", 417: "Expectation Failed", 418: "I'm a teapot",
-        421: "Misdirected Request", 422: "Unprocessable Entity", 423: "Locked",
-        424: "Failed Dependency", 425: "Too Early", 426: "Upgrade Required",
-        428: "Precondition Required", 429: "Too Many Requests",
-        431: "Request Header Fields Too Large", 451: "Unavailable For Legal Reasons",
-        500: "Internal Server Error", 501: "Not Implemented", 502: "Bad Gateway",
-        503: "Service Unavailable", 504: "Gateway Timeout",
-        505: "HTTP Version Not Supported", 506: "Variant Also Negotiates",
-        507: "Insufficient Storage", 508: "Loop Detected", 510: "Not Extended",
-        511: "Network Authentication Required"
-    }
-
-
-def test_parsing_content_type(content_type_map):
-    """Test if parsing different types of content-type returns the expected result"""
-    for header_value, expected_encoding in content_type_map.items():
-        assert ResponseEncoding.get_value(header_value) == expected_encoding
-
-
-def test_parsing_response_status(status_map):
-    """Test if using different http responses' status codes returns the expected result"""
-    for status_code, expected_status_text in status_map.items():
-        assert StatusText.get(status_code) == expected_status_text
-
-
-def test_unknown_status_code():
-    """Test handling of an unknown status code"""
-    assert StatusText.get(1000) == "Unknown Status Code"

tests/parser/test_automatch.py

@@ -1,111 +0,0 @@
-import asyncio
-
-import pytest
-
-from scrapling import Adaptor
-
-
-class TestParserAutoMatch:
-    def test_element_relocation(self):
-        """Test relocating element after structure change"""
-        original_html = '''
-                <div class="container">
-                    <section class="products">
-                        <article class="product" id="p1">
-                            <h3>Product 1</h3>
-                            <p class="description">Description 1</p>
-                        </article>
-                        <article class="product" id="p2">
-                            <h3>Product 2</h3>
-                            <p class="description">Description 2</p>
-                        </article>
-                    </section>
-                </div>
-                '''
-        changed_html = '''
-                <div class="new-container">
-                    <div class="product-wrapper">
-                        <section class="products">
-                            <article class="product new-class" data-id="p1">
-                                <div class="product-info">
-                                    <h3>Product 1</h3>
-                                    <p class="new-description">Description 1</p>
-                                </div>
-                            </article>
-                            <article class="product new-class" data-id="p2">
-                                <div class="product-info">
-                                    <h3>Product 2</h3>
-                                    <p class="new-description">Description 2</p>
-                                </div>
-                            </article>
-                        </section>
-                    </div>
-                </div>
-                '''
-
-        old_page = Adaptor(original_html, url='example.com', auto_match=True)
-        new_page = Adaptor(changed_html, url='example.com', auto_match=True)
-
-        # 'p1' was used as ID and now it's not and all the path elements have changes
-        # Also at the same time testing auto-match vs combined selectors
-        _ = old_page.css('#p1, #p2', auto_save=True)[0]
-        relocated = new_page.css('#p1', auto_match=True)
-
-        assert relocated is not None
-        assert relocated[0].attrib['data-id'] == 'p1'
-        assert relocated[0].has_class('new-class')
-        assert relocated[0].css('.new-description')[0].text == 'Description 1'
-
-    @pytest.mark.asyncio
-    async def test_element_relocation_async(self):
-        """Test relocating element after structure change in async mode"""
-        original_html = '''
-                <div class="container">
-                    <section class="products">
-                        <article class="product" id="p1">
-                            <h3>Product 1</h3>
-                            <p class="description">Description 1</p>
-                        </article>
-                        <article class="product" id="p2">
-                            <h3>Product 2</h3>
-                            <p class="description">Description 2</p>
-                        </article>
-                    </section>
-                </div>
-                '''
-        changed_html = '''
-                <div class="new-container">
-                    <div class="product-wrapper">
-                        <section class="products">
-                            <article class="product new-class" data-id="p1">
-                                <div class="product-info">
-                                    <h3>Product 1</h3>
-                                    <p class="new-description">Description 1</p>
-                                </div>
-                            </article>
-                            <article class="product new-class" data-id="p2">
-                                <div class="product-info">
-                                    <h3>Product 2</h3>
-                                    <p class="new-description">Description 2</p>
-                                </div>
-                            </article>
-                        </section>
-                    </div>
-                </div>
-                '''
-
-        # Simulate async operation
-        await asyncio.sleep(0.1)  # Minimal async operation
-
-        old_page = Adaptor(original_html, url='example.com', auto_match=True)
-        new_page = Adaptor(changed_html, url='example.com', auto_match=True)
-
-        # 'p1' was used as ID and now it's not and all the path elements have changes
-        # Also at the same time testing auto-match vs combined selectors
-        _ = old_page.css('#p1, #p2', auto_save=True)[0]
-        relocated = new_page.css('#p1', auto_match=True)
-
-        assert relocated is not None
-        assert relocated[0].attrib['data-id'] == 'p1'
-        assert relocated[0].has_class('new-class')
-        assert relocated[0].css('.new-description')[0].text == 'Description 1'