browserfetch 0.11.0__tar.gz → 0.13.0__tar.gz

{browserfetch-0.11.0 → browserfetch-0.13.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: browserfetch
-Version: 0.11.0
+Version: 0.13.0
 Summary: fetch in Python using your browser! 
 Keywords: browser,fetch,python,cookies
 Requires-Python: >=3.11

{browserfetch-0.11.0 → browserfetch-0.13.0}/browserfetch/__init__.py

@@ -1,17 +1,16 @@
-__version__ = '0.11.0'
+__version__ = '0.13.0'
 __all__ = [
     'BrowserError',
+    'Response',
     'evaluate',
     'fetch',
     'get',
     'post',
-    'Response',
     'start_server',
 ]
 import atexit
 from asyncio import (
     AbstractEventLoop,
-    CancelledError,
     Event,
     Task,
     get_running_loop,
@@ -21,8 +20,9 @@ from collections import defaultdict
 from dataclasses import dataclass
 from functools import partial as _partial
 from html import escape
-from json import dumps as _dumps, loads
+from json import dumps as _dumps, loads as _loads
 from logging import getLogger
+from typing import Any as _Any
 from urllib.parse import parse_qsl, urlencode, urlparse, urlunparse
 
 from aiohttp import ClientSession, ClientWebSocketResponse
@@ -72,8 +72,8 @@ class Response:
 
     def json(self, encoding=None, errors='strict'):
         if encoding is None:
-            return loads(self.body)
-        return loads(self.text(encoding=encoding, errors=errors))
+            return _loads(self.body)
+        return _loads(self.text(encoding=encoding, errors=errors))
 
 
 def extract_host(url: str) -> str:
@@ -123,7 +123,7 @@ async def receive_responses(ws: WebSocketResponse | ClientWebSocketResponse):
     while True:
         blob = await ws.receive_bytes()
         json_blob, _, body = blob.partition(b'\0')
-        j = loads(json_blob)
+        j = _loads(json_blob)
         j['body'] = body
         event_id = j.pop('event_id')
         try:
@@ -151,10 +151,21 @@ async def _(request):
     )
     logger.info('registering host %s', host)
 
-    ws_or_e = hosts[host]
+    ws_or_event = hosts[host]
+    if not isinstance(ws_or_event, Event):
+        await ws.send_bytes(
+            _dumps(
+                {
+                    'action': 'close_ws',
+                    'reason': f'a host with the name `{host}` is already registered',
+                }
+            ).encode()
+        )
+        await ws.close()
+        return ws
+
     hosts[host] = ws
-    if isinstance(ws_or_e, Event):
-        ws_or_e.set()
+    ws_or_event.set()
 
     try:
         await receive_responses(ws)
@@ -175,7 +186,7 @@ async def _(request: Request) -> WebSocketResponse:
         except TypeError:  # ws closed
             return ws
         data, null, body = bytes_.partition(b'\0')
-        data = loads(data)
+        data = _loads(data)
         relay_event_id = data['event_id']
 
         try:
@@ -231,14 +242,18 @@ async def relay_client(server_host, server_port):
 
 
 async def evaluate(
-    string: str,
+    expression: str,
+    /,
+    *,
     host: str,
     timeout: int | float = 95,
+    arg: _Any = None,
 ):
     """Evaluate string in browser context and return JSON.stringify(result)."""
-    d = await _request(
-        host, {'action': 'eval', 'string': string, 'timeout': timeout}, None
-    )
+    data = {'action': 'eval', 'string': expression, 'timeout': timeout}
+    if arg is not None:
+        data['arg'] = arg
+    d = await _request(host, data, None)
     return d['result']
 
 
@@ -267,7 +282,7 @@ async def fetch(
         url = urlunparse(
             parsed_url._replace(
                 query=urlencode(
-                    parse_qsl(parsed_url.query) + [*params.items()]
+                    [*parse_qsl(parsed_url.query), *params.items()]
                 )
             )
         )
@@ -352,18 +367,9 @@ app.add_routes(routes)
 app_runner = AppRunner(app)
 
 
-def _shutdown_server(loop: AbstractEventLoop):
-    logger.info('waiting for app_runner.cleanup()')
-    loop.run_until_complete(app_runner.cleanup())
-
-
 def _cancel_relay_task(loop: AbstractEventLoop, task: Task):
     logger.info('cancelling relay task')
     task.cancel()
-    try:
-        loop.run_until_complete(task)
-    except CancelledError:
-        pass
 
 
 _server = False
@@ -389,5 +395,4 @@ async def start_server(*, host=_host, port=_port):
         atexit.register(_cancel_relay_task, loop, relay_task)
     else:
         _server = True
-        atexit.register(_shutdown_server, loop)
         logger.info('server started at http://%s:%s', host, port)

browserfetch-0.13.0/browserfetch/browserfetch.egg-info/PKG-INFO

@@ -0,0 +1,71 @@
+Metadata-Version: 2.1
+Name: browserfetch
+Version: 0.1.1.dev0
+Summary: fetch in Python using your browser! 
+License: GNU General Public License v3 (GPLv3)
+Project-URL: Homepage, https://github.com/5j9/browserfetch
+Keywords: browser,fetch,python,cookies
+Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
+Requires-Python: >=3.11
+Description-Content-Type: text/x-rst
+License-File: LICENSE
+Requires-Dist: aiohttp
+Requires-Dist: pyperclip
+
+Fetch using your browser.
+
+Let the browser manage cookies for you.
+
+⚠️ This project is a very simple implementation. Not tested thoroughly. Consider it a proof of concept.
+
+Usage
+-----
+1. You'll run a Python script containing some code like this:
+
+.. code-block:: python
+
+    from asyncio import gather, get_event_loop
+
+    from browserfetch import fetch, run_server
+
+
+    async def main():
+        response1, response2, reponse3 = await gather(
+            fetch('https://example.com/path1'),
+            fetch('https://example.com/image.png'),
+            fetch('https://example.com/path2'),
+        )
+        # do stuff with retrieved responses
+
+
+    loop = get_event_loop()
+    loop.create_task(main())
+    run_server(loop=loop)
+
+
+2. Open your browser, goto http://example.com (perhaps solve a captcha and log in).
+3. Copy the contents of `browserfetch.js`_ file and paste it in browser's console. (You can use a browser extensions like violentmonkey_/tampermonkey_ to do this step for you.)
+
+That's it! Your Python script starts handling requests.
+The browser tab should remain open of-coarse.
+
+The server can handle multiple websocket connections from different websites simultaneously.
+
+How it works
+------------
+``browserfetch`` communicates with your browser using a websocket. The ``fetch`` function just passes the request to browser and it is the browser that handles the actual request. Response data is sent back to Python using the same WebSocket connection.
+
+Motivations
+-----------
+* `browser_cookie3 stopped working on Chrome-based browsers`_. There is a workaround: ShadowCopy, but it requires admin privilege.
+* Another issue with browser_cookie's approach is that it retrieves cookies from cookie files, but these files are not updated instantly. Thus, you might have to wait or retry a few times before you can successfully access newly set cookies.
+* ShadowCopying and File access are slow and inefficient operations.
+
+Downsides
+---------
+* Setting up ``browserfetch`` is a more cumbersome since it requires running a Python server and also injecting a small script into the webpage. Using ``browser_cookie3`` might be a better choice if there are many websites that you need to communicate with.
+
+.. _`browser_cookie3 stopped working on Chrome-based browsers`: https://github.com/borisbabic/browser_cookie3/issues/180
+.. _tampermonkey: https://github.com/Tampermonkey/tampermonkey
+.. _violentmonkey: https://github.com/violentmonkey/violentmonkey
+.. _browserfetch.js: https://github.com/5j9/browserfetch/blob/master/browserfetch/browserfetch.js

browserfetch-0.13.0/browserfetch/browserfetch.egg-info/SOURCES.txt

@@ -0,0 +1,9 @@
+LICENSE
+README.rst
+pyproject.toml
+browserfetch/browserfetch.egg-info/PKG-INFO
+browserfetch/browserfetch.egg-info/SOURCES.txt
+browserfetch/browserfetch.egg-info/dependency_links.txt
+browserfetch/browserfetch.egg-info/not-zip-safe
+browserfetch/browserfetch.egg-info/requires.txt
+browserfetch/browserfetch.egg-info/top_level.txt

browserfetch-0.13.0/browserfetch/browserfetch.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

browserfetch-0.13.0/browserfetch/browserfetch.egg-info/not-zip-safe

@@ -0,0 +1 @@
+

browserfetch-0.13.0/browserfetch/browserfetch.egg-info/requires.txt

@@ -0,0 +1,2 @@
+aiohttp
+pyperclip

browserfetch-0.13.0/browserfetch/browserfetch.egg-info/top_level.txt

@@ -0,0 +1 @@
+

{browserfetch-0.11.0 → browserfetch-0.13.0}/browserfetch/browserfetch.js

@@ -57,13 +57,13 @@
             evalled = eval(req['string']);
             switch (evalled.constructor.name) {
                 case 'AsyncFunction':
-                    evalled = await evalled;
+                    evalled = await evalled(req['arg']);
                     break;
                 case 'Promise':
                     evalled = await evalled;
                     break;
                 case 'Function':
-                    evalled = evalled();
+                    evalled = evalled(req['arg']);
                     break;
             }
             resp = { 'result': evalled, 'event_id': req['event_id'] };
@@ -117,6 +117,11 @@
             var /**@type {Uint8Array | Blob} */ result, j, b;
             [b, j] = parseData(evt.data);
             switch (j['action']) {
+                case 'close_ws':
+                    console.debug(`websocket closed. reason: ${j["reason"]}`)
+                    ws.onclose = null;
+                    ws.close();
+                    return;
                 case 'fetch':
                     result = await doFetch(j, b);
                     break;

{browserfetch-0.11.0 → browserfetch-0.13.0}/pyproject.toml

@@ -40,13 +40,21 @@ lint.extend-select = [
     'FA',  # flake8-future-annotations
     'I',  # isort
     'UP',  # pyupgrade
+    'RUF', # Ruff-specific rules (RUF)
 ]
 lint.ignore = [
     'E721',  # Do not compare types, use `isinstance()`
+    'RUF001',  # ambiguous-unicode-character-string	
+    'RUF002',  # ambiguous-unicode-character-docstring
+    'RUF003',  # ambiguous-unicode-character-comment
+    'RUF012',  # mutable-class-default
 ]
 
 [tool.pytest.ini_options]
 addopts = '--quiet --tb=short'
+asyncio_mode = "auto"
+asyncio_default_test_loop_scope = "session"
+asyncio_default_fixture_loop_scope = "session"
 
 [tool.pyright]
 typeCheckingMode = 'standard'
@@ -60,3 +68,10 @@ reportInvalidStringEscapeSequence = false
 reportConstantRedefinition = 'error'
 reportTypeCommentUsage = 'warning'
 reportUnnecessaryComparison = 'warning'
+
+[dependency-groups]
+dev = [
+    "playwright>=1.52.0",
+    "pytest>=8.4.0",
+    "pytest-asyncio>=1.0.0",
+]

browserfetch-0.11.0/tests/test_init.py

@@ -1,25 +0,0 @@
-from contextlib import suppress
-from unittest.mock import Mock, patch
-
-from browserfetch import fetch
-
-request_mock = Mock()
-
-
-@patch('browserfetch._request', new=request_mock)
-async def test_params():
-    with suppress(TypeError):
-        await fetch(
-            url='http://stackoverflow.com/search?q=question',
-            params={'lang': 'en', 'tag': 'python', 'q': True},
-        )
-    request_mock.assert_called_once_with(
-        None,  # host
-        {
-            'action': 'fetch',
-            'url': 'http://stackoverflow.com/search?q=question&lang=en&tag=python&q=True',
-            'options': None,
-            'timeout': 95,
-        },  # data
-        None,  # body
-    )