pydoll-python 2.2.1__tar.gz → 2.2.3__tar.gz

{pydoll_python-2.2.1 → pydoll_python-2.2.3}/PKG-INFO

@@ -1,19 +1,16 @@
 Metadata-Version: 2.3
 Name: pydoll-python
-Version: 2.2.1
+Version: 2.2.3
 Summary: 
 Author: Thalison Fernandes
 Author-email: thalissfernandes99@gmail.com
-Requires-Python: >=3.10,<4.0
+Requires-Python: >=3.11,<4.0
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Requires-Dist: aiofiles (>=23.2.1,<24.0.0)
 Requires-Dist: aiohttp (>=3.9.5,<4.0.0)
-Requires-Dist: beautifulsoup4 (>=4.12.3,<5.0.0)
-Requires-Dist: mkdocstrings (>=0.29.1,<0.30.0)
 Requires-Dist: websockets (>=13.1,<14.0)
 Description-Content-Type: text/markdown
 

{pydoll_python-2.2.1 → pydoll_python-2.2.3}/pydoll/browser/chromium/base.py

@@ -231,12 +231,13 @@ class Browser(ABC):  # noqa: PLR0904
         """
         targets = await self.get_targets()
         valid_tab_targets = [
-            target for target in targets if target['type'] == 'page'
-            and 'extension' not in target['url']
+            target
+            for target in targets
+            if target['type'] == 'page' and 'extension' not in target['url']
         ]
         return [
-            Tab(self, self._connection_port, target['targetId']) for target
-            in reversed(valid_tab_targets)
+            Tab(self, self._connection_port, target['targetId'])
+            for target in reversed(valid_tab_targets)
         ]
 
     async def set_download_path(self, path: str, browser_context_id: Optional[str] = None):

{pydoll_python-2.2.1 → pydoll_python-2.2.3}/pydoll/browser/tab.py

@@ -41,6 +41,7 @@ from pydoll.exceptions import (
     WaitElementTimeout,
 )
 from pydoll.protocol.base import Response
+from pydoll.protocol.dom.types import EventFileChooserOpened
 from pydoll.protocol.network.responses import GetResponseBodyResponse
 from pydoll.protocol.network.types import Cookie, CookieParam, NetworkLog
 from pydoll.protocol.page.events import PageEvent
@@ -678,10 +679,11 @@ class Tab(FindElementsMixin):  # noqa: PLR0904
             files: File path(s) for upload.
         """
 
-        async def event_handler(event):
+        async def event_handler(event: EventFileChooserOpened):
+            file_list = [str(file) for file in files] if isinstance(files, list) else [str(files)]
             await self._execute_command(
-                DomCommands.upload_files(
-                    files=files,
+                DomCommands.set_file_input_files(
+                    files=file_list,
                     backend_node_id=event['params']['backendNodeId'],
                 )
             )
@@ -695,7 +697,11 @@ class Tab(FindElementsMixin):  # noqa: PLR0904
         if self.intercept_file_chooser_dialog_enabled is False:
             await self.enable_intercept_file_chooser_dialog()
 
-        await self.on(PageEvent.FILE_CHOOSER_OPENED, event_handler, temporary=True)
+        await self.on(
+            PageEvent.FILE_CHOOSER_OPENED,
+            cast(Callable[[dict], Any], event_handler),
+            temporary=True,
+        )
 
         yield
 

{pydoll_python-2.2.1 → pydoll_python-2.2.3}/pydoll/elements/mixins/find_elements_mixin.py

@@ -403,8 +403,8 @@ class FindElementsMixin:
         if object_id and not by == By.XPATH:
             script = Scripts.RELATIVE_QUERY_SELECTOR.replace('{selector}', selector)
             command = RuntimeCommands.call_function_on(
-                object_id,
-                script,
+                function_declaration=script,
+                object_id=object_id,
                 return_by_value=False,
             )
         elif by == By.XPATH:
@@ -437,8 +437,8 @@ class FindElementsMixin:
         if object_id and not by == By.XPATH:
             script = Scripts.RELATIVE_QUERY_SELECTOR_ALL.replace('{selector}', escaped_value)
             command = RuntimeCommands.call_function_on(
-                object_id,
-                script,
+                function_declaration=script,
+                object_id=object_id,
                 return_by_value=False,
             )
         elif by == By.XPATH:
@@ -461,8 +461,8 @@ class FindElementsMixin:
             escaped_value = self._ensure_relative_xpath(escaped_value)
             script = Scripts.FIND_RELATIVE_XPATH_ELEMENT.replace('{escaped_value}', escaped_value)
             command = RuntimeCommands.call_function_on(
-                object_id,
-                script,
+                function_declaration=script,
+                object_id=object_id,
                 return_by_value=False,
             )
         else:

{pydoll_python-2.2.1 → pydoll_python-2.2.3}/pydoll/elements/web_element.py

@@ -3,7 +3,6 @@ import json
 from typing import Optional
 
 import aiofiles
-from bs4 import BeautifulSoup
 
 from pydoll.commands import (
     DomCommands,
@@ -34,7 +33,10 @@ from pydoll.protocol.dom.responses import (
 from pydoll.protocol.dom.types import Quad
 from pydoll.protocol.page.responses import CaptureScreenshotResponse
 from pydoll.protocol.page.types import Viewport
-from pydoll.utils import decode_base64_to_bytes
+from pydoll.utils import (
+    decode_base64_to_bytes,
+    extract_text_from_html,
+)
 
 
 class WebElement(FindElementsMixin):  # noqa: PLR0904
@@ -99,8 +101,7 @@ class WebElement(FindElementsMixin):  # noqa: PLR0904
     async def text(self) -> str:
         """Visible text content of the element."""
         outer_html = await self.inner_html
-        soup = BeautifulSoup(outer_html, 'html.parser')
-        return soup.get_text(strip=True)
+        return extract_text_from_html(outer_html, strip=True)
 
     @property
     async def bounds(self) -> Quad:

{pydoll_python-2.2.1 → pydoll_python-2.2.3}/pydoll/protocol/dom/types.py

@@ -79,3 +79,14 @@ class BoxModel(TypedDict):
     width: int
     height: int
     shapeOutside: NotRequired[ShapeOutsideInfo]
+
+
+class EventFileChooserOpenedParams(TypedDict):
+    frameId: str
+    mode: str
+    backendNodeId: int
+
+
+class EventFileChooserOpened(TypedDict):
+    method: str
+    params: EventFileChooserOpenedParams

{pydoll_python-2.2.1 → pydoll_python-2.2.3}/pydoll/utils.py

@@ -2,6 +2,8 @@ import base64
 import logging
 import os
 import re
+from html import unescape
+from html.parser import HTMLParser
 
 import aiohttp
 
@@ -10,6 +12,95 @@ from pydoll.exceptions import InvalidBrowserPath, InvalidResponse, NetworkError
 logger = logging.getLogger(__name__)
 
 
+class TextExtractor(HTMLParser):
+    """
+    HTML parser for text extraction.
+
+    Extracts visible text content from an HTML string, excluding the contents of
+    tags specified in _skip_tags.
+    """
+
+    def __init__(self):
+        super().__init__()
+        self._parts = []
+        self._skip = False
+        self._skip_tags = {'script', 'style', 'template'}
+
+    def handle_starttag(self, tag, attrs):
+        """
+        Marks the parser to skip content inside tags specified in _skip_tags.
+
+        Args:
+            tag (str): The tag name.
+            attrs (list): A list of (attribute, value) pairs.
+        """
+        if tag in self._skip_tags:
+            self._skip = True
+
+    def handle_endtag(self, tag):
+        """
+        Marks the parser the end of skip tags.
+
+        Args:
+            tag (str): The tag name.
+        """
+        if tag in self._skip_tags:
+            self._skip = False
+
+    def handle_data(self, data):
+        """
+        Handles text nodes. Adds them to the result unless they are within a skip tag.
+
+        Args:
+            data (str): The text data.
+        """
+        if not self._skip:
+            self._parts.append(unescape(data))
+
+    def get_strings(self, strip: bool):
+        """
+        Yields all collected visible text fragments.
+
+        Args:
+            strip (bool): Whether to strip leading/trailing whitespace from each fragment.
+
+        Yields:
+            str: Visible text fragments.
+        """
+        for text in self._parts:
+            yield text.strip() if strip else text
+
+    def get_text(self, separator: str, strip: bool) -> str:
+        """
+        Returns all visible text.
+
+        Args:
+            separator (str): String inserted between extracted text fragments.
+            strip (bool): Whether to strip whitespace from each fragment.
+
+        Returns:
+            str: The visible text.
+        """
+        return separator.join(self.get_strings(strip=strip))
+
+
+def extract_text_from_html(html: str, separator: str = '', strip: bool = False) -> str:
+    """
+    Extracts visible text content from an HTML string.
+
+    Args:
+        html (str): The HTML string to extract text from.
+        separator (str, optional): String inserted between extracted text fragments. Defaults to ''.
+        strip (bool, optional): Whether to strip whitespace from text fragments. Defaults to False.
+
+    Returns:
+        str: The extracted visible text.
+    """
+    parser = TextExtractor()
+    parser.feed(html)
+    return parser.get_text(separator=separator, strip=strip)
+
+
 def decode_base64_to_bytes(image: str) -> bytes:
     """
     Decodes a base64 image string to bytes.

{pydoll_python-2.2.1 → pydoll_python-2.2.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pydoll-python"
-version = "2.2.1"
+version = "2.2.3"
 description = ""
 authors = ["Thalison Fernandes <thalissfernandes99@gmail.com>"]
 readme = "README.md"
@@ -9,12 +9,10 @@ packages = [
 ]
 
 [tool.poetry.dependencies]
-python = "^3.10"
+python = "^3.11"
 websockets = "^13.1"
 aiohttp = "^3.9.5"
 aiofiles = "^23.2.1"
-beautifulsoup4 = "^4.12.3"
-mkdocstrings = "^0.29.1"
 
 
 [tool.poetry.group.dev.dependencies]