scrapling 0.2.3__tar.gz → 0.2.5__tar.gz

{scrapling-0.2.3/scrapling.egg-info → scrapling-0.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: scrapling
-Version: 0.2.3
+Version: 0.2.5
 Summary: Scrapling is a powerful, flexible, and high-performance web scraping library for Python. It 
 Home-page: https://github.com/D4Vinci/Scrapling
 Author: Karim Shoair

{scrapling-0.2.3 → scrapling-0.2.5}/scrapling/__init__.py

@@ -4,7 +4,7 @@ from scrapling.parser import Adaptor, Adaptors
 from scrapling.core.custom_types import TextHandler, AttributesHandler
 
 __author__ = "Karim Shoair (karim.shoair@pm.me)"
-__version__ = "0.2.3"
+__version__ = "0.2.5"
 __copyright__ = "Copyright (c) 2024 Karim Shoair"
 
 

{scrapling-0.2.3 → scrapling-0.2.5}/scrapling/core/custom_types.py

@@ -129,9 +129,8 @@ class TextHandlers(List[TextHandler]):
 
 
 class AttributesHandler(Mapping):
-    """A read-only mapping to use instead of the standard dictionary for the speed boost but
-     at the same time I use it to add more functionalities.
-    If standard dictionary is needed, just convert this class to dictionary with `dict` function
+    """A read-only mapping to use instead of the standard dictionary for the speed boost but at the same time I use it to add more functionalities.
+        If standard dictionary is needed, just convert this class to dictionary with `dict` function
     """
     __slots__ = ('_data',)
 

{scrapling-0.2.3 → scrapling-0.2.5}/scrapling/core/translator.py

@@ -1,9 +1,11 @@
 """
 Most of this file is adapted version of the translator of parsel library with some modifications simply for 1 important reason...
-To add pseudo-elements ``::text`` and ``::attr(ATTR_NAME)`` so we match Parsel/Scrapy selectors format
-which will be important in future releases but most importantly...
-    so you don't have to learn a new selectors/api method like what bs4 done with soupsieve :)
-> if you want to learn about this, head to https://cssselect.readthedocs.io/en/latest/#cssselect.FunctionalPseudoElement
+
+To add pseudo-elements ``::text`` and ``::attr(ATTR_NAME)`` so we match Parsel/Scrapy selectors format which will be important in future releases but most importantly...
+
+So you don't have to learn a new selectors/api method like what bs4 done with soupsieve :)
+
+    if you want to learn about this, head to https://cssselect.readthedocs.io/en/latest/#cssselect.FunctionalPseudoElement
 """
 
 import re

{scrapling-0.2.3 → scrapling-0.2.5}/scrapling/engines/camo.py

@@ -4,6 +4,7 @@ from scrapling.core._types import Union, Callable, Optional, Dict, List, Literal
 from scrapling.engines.toolbelt import (
     Response,
     do_nothing,
+    StatusText,
     get_os_name,
     intercept_route,
     check_type_validity,
@@ -103,20 +104,22 @@ class CamoufoxEngine:
 
             if self.wait_selector and type(self.wait_selector) is str:
                 waiter = page.locator(self.wait_selector)
-                waiter.wait_for(state=self.wait_selector_state)
+                waiter.first.wait_for(state=self.wait_selector_state)
 
-            content_type = res.headers.get('content-type', '')
-            # Parse charset from content-type
-            encoding = 'utf-8'  # default encoding
-            if 'charset=' in content_type.lower():
-                encoding = content_type.lower().split('charset=')[-1].split(';')[0].strip()
+            # This will be parsed inside `Response`
+            encoding = res.headers.get('content-type', '') or 'utf-8'  # default encoding
+
+            status_text = res.status_text
+            # PlayWright API sometimes give empty status text for some reason!
+            if not status_text:
+                status_text = StatusText.get(res.status)
 
             response = Response(
                 url=res.url,
                 text=page.content(),
-                body=res.body(),
+                body=page.content().encode('utf-8'),
                 status=res.status,
-                reason=res.status_text,
+                reason=status_text,
                 encoding=encoding,
                 cookies={cookie['name']: cookie['value'] for cookie in page.context.cookies()},
                 headers=res.all_headers(),

{scrapling-0.2.3 → scrapling-0.2.5}/scrapling/engines/pw.py

@@ -6,6 +6,7 @@ from scrapling.engines.constants import DEFAULT_STEALTH_FLAGS, NSTBROWSER_DEFAUL
 from scrapling.engines.toolbelt import (
     Response,
     do_nothing,
+    StatusText,
     js_bypass_path,
     intercept_route,
     generate_headers,
@@ -213,20 +214,22 @@ class PlaywrightEngine:
 
             if self.wait_selector and type(self.wait_selector) is str:
                 waiter = page.locator(self.wait_selector)
-                waiter.wait_for(state=self.wait_selector_state)
+                waiter.first.wait_for(state=self.wait_selector_state)
 
-            content_type = res.headers.get('content-type', '')
-            # Parse charset from content-type
-            encoding = 'utf-8'  # default encoding
-            if 'charset=' in content_type.lower():
-                encoding = content_type.lower().split('charset=')[-1].split(';')[0].strip()
+            # This will be parsed inside `Response`
+            encoding = res.headers.get('content-type', '') or 'utf-8'  # default encoding
+
+            status_text = res.status_text
+            # PlayWright API sometimes give empty status text for some reason!
+            if not status_text:
+                status_text = StatusText.get(res.status)
 
             response = Response(
                 url=res.url,
                 text=page.content(),
-                body=res.body(),
+                body=page.content().encode('utf-8'),
                 status=res.status,
-                reason=res.status_text,
+                reason=status_text,
                 encoding=encoding,
                 cookies={cookie['name']: cookie['value'] for cookie in page.context.cookies()},
                 headers=res.all_headers(),

{scrapling-0.2.3 → scrapling-0.2.5}/scrapling/engines/static.py

@@ -23,7 +23,7 @@ class StaticEngine:
     @staticmethod
     def _headers_job(headers: Optional[Dict], url: str, stealth: bool) -> Dict:
         """Adds useragent to headers if it doesn't exist, generates real headers and append it to current headers, and
-        finally generates a referer header that looks like if this request came from Google's search of the current URL's domain.
+            finally generates a referer header that looks like if this request came from Google's search of the current URL's domain.
 
         :param headers: Current headers in the request if the user passed any
         :param url: The Target URL.
@@ -65,6 +65,7 @@ class StaticEngine:
 
     def get(self, url: str, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response:
         """Make basic HTTP GET request for you but with some added flavors.
+
         :param url: Target url.
         :param stealthy_headers: If enabled (default), Fetcher will create and add real browser's headers and
             create a referer header as if this request had came from Google's search of this URL's domain.
@@ -77,6 +78,7 @@ class StaticEngine:
 
     def post(self, url: str, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response:
         """Make basic HTTP POST request for you but with some added flavors.
+
         :param url: Target url.
         :param stealthy_headers: If enabled (default), Fetcher will create and add real browser's headers and
             create a referer header as if this request had came from Google's search of this URL's domain.
@@ -89,6 +91,7 @@ class StaticEngine:
 
     def delete(self, url: str, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response:
         """Make basic HTTP DELETE request for you but with some added flavors.
+
         :param url: Target url.
         :param stealthy_headers: If enabled (default), Fetcher will create and add real browser's headers and
             create a referer header as if this request had came from Google's search of this URL's domain.
@@ -101,6 +104,7 @@ class StaticEngine:
 
     def put(self, url: str, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response:
         """Make basic HTTP PUT request for you but with some added flavors.
+
         :param url: Target url.
         :param stealthy_headers: If enabled (default), Fetcher will create and add real browser's headers and
             create a referer header as if this request had came from Google's search of this URL's domain.

{scrapling-0.2.3 → scrapling-0.2.5}/scrapling/engines/toolbelt/__init__.py

@@ -6,6 +6,7 @@ from .fingerprints import (
 from .custom import (
     Response,
     do_nothing,
+    StatusText,
     BaseFetcher,
     get_variable_name,
     check_type_validity,

{scrapling-0.2.3 → scrapling-0.2.5}/scrapling/engines/toolbelt/custom.py

@@ -3,10 +3,78 @@ Functions related to custom types or type checking
 """
 import inspect
 import logging
+from email.message import Message
 
-from scrapling.core.utils import setup_basic_logging
+from scrapling.core.custom_types import MappingProxyType
 from scrapling.parser import Adaptor, SQLiteStorageSystem
-from scrapling.core._types import Any, List, Type, Union, Optional, Dict, Callable
+from scrapling.core.utils import setup_basic_logging, cache
+from scrapling.core._types import Any, List, Type, Union, Optional, Dict, Callable, Tuple
+
+
+class ResponseEncoding:
+    __DEFAULT_ENCODING = "utf-8"
+    __ISO_8859_1_CONTENT_TYPES = {"text/plain", "text/html", "text/css", "text/javascript"}
+
+    @classmethod
+    @cache(maxsize=None)
+    def __parse_content_type(cls, header_value: str) -> Tuple[str, Dict[str, str]]:
+        """Parse content type and parameters from a content-type header value.
+
+            Uses `email.message.Message` for robust header parsing according to RFC 2045.
+
+        :param header_value: Raw content-type header string
+        :return: Tuple of (content_type, parameters_dict)
+        """
+        # Create a Message object and set the Content-Type header then get the content type and parameters
+        msg = Message()
+        msg['content-type'] = header_value
+
+        content_type = msg.get_content_type()
+        params = dict(msg.get_params(failobj=[]))
+
+        # Remove the content-type from params if present somehow
+        params.pop('content-type', None)
+
+        return content_type, params
+
+    @classmethod
+    @cache(maxsize=None)
+    def get_value(cls, content_type: Optional[str]) -> str:
+        """Determine the appropriate character encoding from a content-type header.
+
+        The encoding is determined by these rules in order:
+            1. If no content-type is provided, use UTF-8
+            2. If charset parameter is present, use that encoding
+            3. If content-type is `text/*`, use ISO-8859-1 per HTTP/1.1 spec
+            4. If content-type is application/json, use UTF-8 per RFC 4627
+            5. Default to UTF-8 if nothing else matches
+
+        :param content_type: Content-Type header value or None
+        :return: String naming the character encoding
+        """
+        if not content_type:
+            return cls.__DEFAULT_ENCODING
+
+        try:
+            content_type, params = cls.__parse_content_type(content_type)
+
+            # First check for explicit charset parameter
+            if "charset" in params:
+                encoding = params["charset"].strip("'\"")
+                "test".encode(encoding)  # Validate encoding
+                return encoding
+
+            # Apply content-type specific rules
+            if content_type in cls.__ISO_8859_1_CONTENT_TYPES:
+                return "ISO-8859-1"
+
+            if content_type == "application/json":
+                return cls.__DEFAULT_ENCODING
+
+            return cls.__DEFAULT_ENCODING
+
+        except (ValueError, LookupError, UnicodeEncodeError):
+            return cls.__DEFAULT_ENCODING
 
 
 class Response(Adaptor):
@@ -19,6 +87,7 @@ class Response(Adaptor):
         self.cookies = cookies
         self.headers = headers
         self.request_headers = request_headers
+        encoding = ResponseEncoding.get_value(encoding)
         super().__init__(text=text, body=body, url=automatch_domain or url, encoding=encoding, **adaptor_arguments)
         # For back-ward compatibility
         self.adaptor = self
@@ -67,6 +136,83 @@ class BaseFetcher:
                 self.adaptor_arguments.update({'automatch_domain': automatch_domain})
 
 
+class StatusText:
+    """A class that gets the status text of response status code.
+
+        Reference: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status
+    """
+    _phrases = MappingProxyType({
+        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"
+    })
+
+    @classmethod
+    @cache(maxsize=128)
+    def get(cls, status_code: int) -> str:
+        """Get the phrase for a given HTTP status code."""
+        return cls._phrases.get(status_code, "Unknown Status Code")
+
+
 def check_if_engine_usable(engine: Callable) -> Union[Callable, None]:
     """This function check if the passed engine can be used by a Fetcher-type class or not.
 

{scrapling-0.2.3 → scrapling-0.2.5}/scrapling/fetchers.py

@@ -11,6 +11,7 @@ class Fetcher(BaseFetcher):
     """
     def get(self, url: str, follow_redirects: bool = True, timeout: Optional[Union[int, float]] = 10, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response:
         """Make basic HTTP GET request for you but with some added flavors.
+
         :param url: Target url.
         :param follow_redirects: As the name says -- if enabled (default), redirects will be followed.
         :param timeout: The time to wait for the request to finish in seconds. The default is 10 seconds.
@@ -24,6 +25,7 @@ class Fetcher(BaseFetcher):
 
     def post(self, url: str, follow_redirects: bool = True, timeout: Optional[Union[int, float]] = 10, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response:
         """Make basic HTTP POST request for you but with some added flavors.
+
         :param url: Target url.
         :param follow_redirects: As the name says -- if enabled (default), redirects will be followed.
         :param timeout: The time to wait for the request to finish in seconds. The default is 10 seconds.
@@ -37,12 +39,14 @@ class Fetcher(BaseFetcher):
 
     def put(self, url: str, follow_redirects: bool = True, timeout: Optional[Union[int, float]] = 10, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response:
         """Make basic HTTP PUT request for you but with some added flavors.
+
         :param url: Target url
         :param follow_redirects: As the name says -- if enabled (default), redirects will be followed.
         :param timeout: The time to wait for the request to finish in seconds. The default is 10 seconds.
         :param stealthy_headers: If enabled (default), Fetcher will create and add real browser's headers and
-        create a referer header as if this request came from Google's search of this URL's domain.
+            create a referer header as if this request came from Google's search of this URL's domain.
         :param kwargs: Any additional keyword arguments are passed directly to `httpx.put()` function so check httpx documentation for details.
+
         :return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers`
         """
         response_object = StaticEngine(follow_redirects, timeout, adaptor_arguments=self.adaptor_arguments).put(url, stealthy_headers, **kwargs)
@@ -50,6 +54,7 @@ class Fetcher(BaseFetcher):
 
     def delete(self, url: str, follow_redirects: bool = True, timeout: Optional[Union[int, float]] = 10, stealthy_headers: Optional[bool] = True, **kwargs: Dict) -> Response:
         """Make basic HTTP DELETE request for you but with some added flavors.
+
         :param url: Target url
         :param follow_redirects: As the name says -- if enabled (default), redirects will be followed.
         :param timeout: The time to wait for the request to finish in seconds. The default is 10 seconds.
@@ -77,6 +82,7 @@ class StealthyFetcher(BaseFetcher):
     ) -> Response:
         """
         Opens up a browser and do your request based on your chosen options below.
+
         :param url: Target url.
         :param headless: Run the browser in headless/hidden (default), 'virtual' screen mode, or headful/visible mode.
         :param block_images: Prevent the loading of images through Firefox preferences.
@@ -127,14 +133,15 @@ class PlayWrightFetcher(BaseFetcher):
      Using this Fetcher class, you can do requests with:
         - Vanilla Playwright without any modifications other than the ones you chose.
         - Stealthy Playwright with the stealth mode I wrote for it. It's still a work in progress but it bypasses many online tests like bot.sannysoft.com
-        Some of the things stealth mode does include:
-            1) Patches the CDP runtime fingerprint.
-            2) Mimics some of the real browsers' properties by injecting several JS files and using custom options.
-            3) Using custom flags on launch to hide Playwright even more and make it faster.
-            4) Generates real browser's headers of the same type and same user OS then append it to the request.
+            Some of the things stealth mode does include:
+                1) Patches the CDP runtime fingerprint.
+                2) Mimics some of the real browsers' properties by injecting several JS files and using custom options.
+                3) Using custom flags on launch to hide Playwright even more and make it faster.
+                4) Generates real browser's headers of the same type and same user OS then append it to the request.
         - Real browsers by passing the CDP URL of your browser to be controlled by the Fetcher and most of the options can be enabled on it.
         - NSTBrowser's docker browserless option by passing the CDP URL and enabling `nstbrowser_mode` option.
-        > Note that these are the main options with PlayWright but it can be mixed together.
+
+    > Note that these are the main options with PlayWright but it can be mixed together.
     """
     def fetch(
             self, url: str, headless: Union[bool, str] = True, disable_resources: bool = None,
@@ -147,6 +154,7 @@ class PlayWrightFetcher(BaseFetcher):
             nstbrowser_mode: bool = False, nstbrowser_config: Optional[Dict] = None,
     ) -> Response:
         """Opens up a browser and do your request based on your chosen options below.
+
         :param url: Target url.
         :param headless: Run the browser in headless/hidden (default), or headful/visible mode.
         :param disable_resources: Drop requests of unnecessary resources for speed boost. It depends but it made requests ~25% faster in my tests for some websites.

{scrapling-0.2.3 → scrapling-0.2.5/scrapling.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: scrapling
-Version: 0.2.3
+Version: 0.2.5
 Summary: Scrapling is a powerful, flexible, and high-performance web scraping library for Python. It 
 Home-page: https://github.com/D4Vinci/Scrapling
 Author: Karim Shoair

{scrapling-0.2.3 → scrapling-0.2.5}/scrapling.egg-info/SOURCES.txt

@@ -42,6 +42,7 @@ tests/fetchers/__init__.py
 tests/fetchers/test_camoufox.py
 tests/fetchers/test_httpx.py
 tests/fetchers/test_playwright.py
+tests/fetchers/test_utils.py
 tests/parser/__init__.py
 tests/parser/test_automatch.py
 tests/parser/test_general.py

{scrapling-0.2.3 → scrapling-0.2.5}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = scrapling
-version = 0.2.3
+version = 0.2.5
 author = Karim Shoair
 author_email = karim.shoair@pm.me
 description = Scrapling is an undetectable, powerful, flexible, adaptive, and high-performance web scraping library for Python.

{scrapling-0.2.3 → scrapling-0.2.5}/setup.py

@@ -6,7 +6,7 @@ with open("README.md", "r", encoding="utf-8") as fh:
 
 setup(
     name="scrapling",
-    version="0.2.3",
+    version="0.2.5",
     description="""Scrapling is a powerful, flexible, and high-performance web scraping library for Python. It 
     simplifies the process of extracting data from websites, even when they undergo structural changes, and offers 
     impressive speed improvements over many popular scraping tools.""",

{scrapling-0.2.3 → scrapling-0.2.5}/tests/fetchers/test_camoufox.py

@@ -36,6 +36,7 @@ class TestStealthyFetcher(unittest.TestCase):
     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)
+        self.assertEqual(self.fetcher.fetch(self.html_url, wait_selector='h1', wait_selector_state='visible').status, 200)
 
     def test_cookies_loading(self):
         """Test if cookies are set after the request"""
@@ -56,6 +57,7 @@ class TestStealthyFetcher(unittest.TestCase):
         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)
+        self.assertEqual(self.fetcher.fetch(self.html_url, extra_headers={'ayo': ''}, os_randomize=True).status, 200)
 
     def test_infinite_timeout(self):
         """Test if infinite timeout breaks the code or not"""

{scrapling-0.2.3 → scrapling-0.2.5}/tests/fetchers/test_playwright.py

@@ -35,6 +35,7 @@ class TestPlayWrightFetcher(unittest.TestCase):
     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)
+        self.assertEqual(self.fetcher.fetch(self.html_url, wait_selector='h1', wait_selector_state='visible').status, 200)
 
     def test_cookies_loading(self):
         """Test if cookies are set after the request"""
@@ -56,6 +57,7 @@ class TestPlayWrightFetcher(unittest.TestCase):
         self.assertEqual(self.fetcher.fetch(self.html_url, disable_webgl=False, hide_canvas=True).status, 200)
         self.assertEqual(self.fetcher.fetch(self.html_url, stealth=True).status, 200)
         self.assertEqual(self.fetcher.fetch(self.html_url, useragent='Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:131.0) Gecko/20100101 Firefox/131.0').status, 200)
+        self.assertEqual(self.fetcher.fetch(self.html_url, extra_headers={'ayo': ''}).status, 200)
 
     def test_cdp_url(self):
         """Test if it's going to try to connect to cdp url or not"""

scrapling-0.2.5/tests/fetchers/test_utils.py

@@ -0,0 +1,129 @@
+import unittest
+
+from scrapling.engines.toolbelt.custom import ResponseEncoding, StatusText
+
+
+class TestPlayWrightFetcher(unittest.TestCase):
+    def setUp(self):
+        self.content_type_map = {
+            # 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'
+        }
+        self.status_map = {
+            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(self):
+        """Test if parsing different types of content-type returns the expected result"""
+        for header_value, expected_encoding in self.content_type_map.items():
+            self.assertEqual(ResponseEncoding.get_value(header_value), expected_encoding)
+
+    def test_parsing_response_status(self):
+        """Test if using different http responses' status codes returns the expected result"""
+        for status_code, expected_status_text in self.status_map.items():
+            self.assertEqual(StatusText.get(status_code), expected_status_text)
+
+        self.assertEqual(StatusText.get(1000), "Unknown Status Code")

{scrapling-0.2.3 → scrapling-0.2.5}/tests/parser/test_general.py

@@ -278,7 +278,7 @@ class TestParser(unittest.TestCase):
         self.assertEqual(len(elements), 5000)
         # Converting 5000 elements to a class and doing operations on them will take time
         # Based on my tests with 100 runs, 1 loop each Scrapling (given the extra work/features) takes 10.4ms on average
-        self.assertLess(end_time - start_time, 0.1)
+        self.assertLess(end_time - start_time, 0.5)  # Locally I test on 0.1 but on GitHub actions with browsers and threading sometimes closing adds fractions of seconds
 
 
 # Use `coverage run -m unittest --verbose tests/test_parser_functions.py` instead for the coverage report