webscout 6.4__py3-none-any.whl → 6.6__py3-none-any.whl

webscout/Extra/YTToolkit/ytapi/stream.py

@@ -0,0 +1,60 @@
+import re
+from typing import Dict, Any
+
+from .pool import collect
+from .https import video_data
+from .patterns import _VideoPatterns as Patterns
+
+
+class Video:
+
+    _HEAD = 'https://www.youtube.com/watch?v='
+
+    def __init__(self, video_id: str):
+        pattern = re.compile('.be/(.*?)$|=(.*?)$|^(\w{11})$')  # noqa
+        self._matched_id = (
+                pattern.search(video_id).group(1)
+                or pattern.search(video_id).group(2)
+                or pattern.search(video_id).group(3)
+        )
+        if self._matched_id:
+            self._url = self._HEAD + self._matched_id
+            self._video_data = video_data(self._matched_id)
+        else:
+            raise ValueError('invalid video id or url')
+
+    def __repr__(self):
+        return f'<Video {self._url}>'
+
+    @property
+    def metadata(self) -> Dict[str, Any]:
+        patterns = [
+            Patterns.title,
+            Patterns.views,
+            Patterns.likes,
+            Patterns.duration,
+            Patterns.author_id,
+            Patterns.upload_date,
+            Patterns.thumbnail,
+            Patterns.tags,
+            Patterns.description,
+            Patterns.is_streamed,
+            Patterns.is_premiered
+        ]
+        ext = collect(lambda x: x.findall(self._video_data) or None, patterns)
+        data = [i[0] if i else i for i in ext]
+        return {
+            'title': data[0],
+            'id': self._matched_id,
+            'views': data[1][:-6] if data[1] else None,
+            'likes': data[2],
+            'streamed': data[9] is not None,
+            'premiered': data[10],
+            'duration': int(data[3]) / 1000 if data[3] else None,
+            'author': data[4],
+            'upload_date': data[5],
+            'url': self._url,
+            'thumbnail': data[6],
+            'tags': data[7].split(',') if data[7] else None,
+            'description': data[8].replace('\\n', '\n') if data[8] else None
+        }

webscout/Extra/YTToolkit/ytapi/utils.py

@@ -0,0 +1,62 @@
+from urllib.request import Request, urlopen
+from collections import OrderedDict
+from urllib.error import HTTPError
+from .errors import TooManyRequests, InvalidURL, RequestError
+from webscout.litagent import LitAgent
+
+
+__all__ = ['dup_filter', 'request']
+
+
+_USER_AGENT_GENERATOR = LitAgent()
+
+
+def request(url: str, retry_attempts: int = 3) -> str:
+    """
+    Send a request with a random user agent and built-in retry mechanism.
+    
+    Args:
+        url (str): The URL to request
+        retry_attempts (int, optional): Number of retry attempts. Defaults to 3.
+    
+    Raises:
+        InvalidURL: If the URL cannot be found
+        TooManyRequests: If rate-limited
+        RequestError: For other request-related errors
+    
+    Returns:
+        str: Decoded response content
+    """
+    for attempt in range(retry_attempts):
+        try:
+            headers = {
+                "User-Agent": _USER_AGENT_GENERATOR.random()
+            }
+            
+            req = Request(url, headers=headers)
+            response = urlopen(req)
+            return response.read().decode('utf-8')
+        
+        except HTTPError as e:
+            if e.code == 404:
+                raise InvalidURL(f'Cannot find anything with the requested URL: {url}')
+            if e.code == 429:
+                raise TooManyRequests(f'Rate-limited on attempt {attempt + 1}')
+            
+            if attempt == retry_attempts - 1:
+                raise RequestError(f'HTTP Error {e.code}: {e.reason}') from e
+        
+        except Exception as e:
+            if attempt == retry_attempts - 1:
+                raise RequestError(f'Request failed: {e!r}') from None
+
+
+def dup_filter(iterable: list, limit: int = None) -> list:
+    if not iterable:
+        return []
+    lim = limit if limit else len(iterable)
+    converted = list(OrderedDict.fromkeys(iterable))
+    if len(converted) - lim > 0:
+        return converted[:-len(converted) + lim]
+    else:
+        return converted

webscout/Extra/YTToolkit/ytapi/video.py

@@ -0,0 +1,102 @@
+import re
+import json
+from .https import video_data
+from typing import Dict, Any
+
+
+class Video:
+
+    _HEAD = 'https://www.youtube.com/watch?v='
+
+    def __init__(self, video_id: str):
+        """
+        Represents a YouTube video
+
+        Parameters
+        ----------
+        video_id : str
+            The id or url of the video
+        """
+        pattern = re.compile('.be/(.*?)$|=(.*?)$|^(\w{11})$')  # noqa
+        self._matched_id = (
+                pattern.search(video_id).group(1)
+                or pattern.search(video_id).group(2)
+                or pattern.search(video_id).group(3)
+        )
+        if self._matched_id:
+            self._url = self._HEAD + self._matched_id
+            self._video_data = video_data(self._matched_id)
+        else:
+            raise ValueError('invalid video id or url')
+
+    def __repr__(self):
+        return f'<Video {self._url}>'
+
+    @property
+    def metadata(self):
+        """
+        Fetches video metadata in a dict format
+
+        Returns
+        -------
+        Dict
+            Video metadata in a dict format containing keys: title, id, views, duration, author_id,
+            upload_date, url, thumbnails, tags, description
+        """
+        details_pattern = re.compile('videoDetails\":(.*?)\"isLiveContent\":.*?}')
+        upload_date_pattern = re.compile("<meta itemprop=\"uploadDate\" content=\"(.*?)\">")
+        genre_pattern = re.compile("<meta itemprop=\"genre\" content=\"(.*?)\">")
+        like_count_pattern = re.compile("iconType\":\"LIKE\"},\"defaultText\":(.*?)}}")
+        
+        # Add robust error handling
+        raw_details_match = details_pattern.search(self._video_data)
+        if not raw_details_match:
+            # Fallback metadata for search results or incomplete video data
+            return {
+                'title': getattr(self, 'title', None),
+                'id': getattr(self, 'id', None),
+                'views': getattr(self, 'views', None),
+                'streamed': False,
+                'duration': None,
+                'author_id': None,
+                'upload_date': None,
+                'url': f"https://www.youtube.com/watch?v={getattr(self, 'id', '')}" if hasattr(self, 'id') else None,
+                'thumbnails': None,
+                'tags': None,
+                'description': None,
+                'likes': None,
+                'genre': None
+            }
+        
+        raw_details = raw_details_match.group(0)
+        
+        # Add None checking for upload_date
+        upload_date_match = upload_date_pattern.search(self._video_data)
+        upload_date = upload_date_match.group(1) if upload_date_match else None
+        
+        metadata = json.loads(raw_details.replace('videoDetails\":', ''))
+        data = {
+            'title': metadata['title'],
+            'id': metadata['videoId'],
+            'views': metadata.get('viewCount'),
+            'streamed': metadata['isLiveContent'],
+            'duration': metadata['lengthSeconds'],
+            'author_id': metadata['channelId'],
+            'upload_date': upload_date,
+            'url': f"https://www.youtube.com/watch?v={metadata['videoId']}",
+            'thumbnails': metadata.get('thumbnail', {}).get('thumbnails'),
+            'tags': metadata.get('keywords'),
+            'description': metadata.get('shortDescription'),
+        }
+        try:
+            likes_count = like_count_pattern.search(self._video_data).group(1)
+            data['likes'] = json.loads(likes_count + '}}}')[
+                'accessibility'
+            ]['accessibilityData']['label'].split(' ')[0].replace(',', '')
+        except (AttributeError, KeyError, json.decoder.JSONDecodeError):
+            data['likes'] = None
+        try:
+            data['genre'] = genre_pattern.search(self._video_data).group(1)
+        except AttributeError:
+            data['genre'] = None
+        return data

webscout/Extra/__init__.py

@@ -2,4 +2,5 @@ from .gguf import *
 from .autollama import *
 from .weather import *
 from .weather_ascii import *
-from .autocoder import *
+from .autocoder import *
+from .YTToolkit import *

webscout/Extra/autocoder/autocoder_utiles.py

@@ -5,117 +5,135 @@ import platform
 import datetime
 import pygetwindow as gw
 import sys
+from typing import List, Optional
 
 from webscout.optimizers import Optimizers
 
-def get_current_app():
+
+def get_current_app() -> str:
     """Get the current active application name."""
     try:
-        active_window = gw.getActiveWindow()
+        active_window: Optional[gw.Window] = gw.getActiveWindow()
         return f"{active_window.title if active_window else 'Unknown'}"
     except Exception as e:
         return "Unknown"
 
-def get_intro_prompt():
-    """Get the introduction prompt for the AutoCoder."""
-    current_app = get_current_app()
-    python_version = sys.version.split()[0]
-    
-    return f"""
-You are a command-line coding assistant called Rawdog that generates and auto-executes Python scripts.
-
-A typical interaction goes like this:
-1. The user gives you a natural language PROMPT.
-2. You:
-    i. Determine what needs to be done
-    ii. Write a short Python SCRIPT to do it
-    iii. Communicate back to the user by printing to the console in that SCRIPT
-3. The compiler extracts the script and then runs it using exec(). If there will be an exception raised,
- it will be send back to you starting with "PREVIOUS SCRIPT EXCEPTION:".
-4. In case of exception, regenerate error free script.
-
-If you need to review script outputs before completing the task, you can print the word "CONTINUE" at the end of your SCRIPT.
-This can be useful for summarizing documents or technical readouts, reading instructions before
-deciding what to do, or other tasks that require multi-step reasoning.
-A typical 'CONTINUE' interaction looks like this:
-1. The user gives you a natural language PROMPT.
-2. You:
-    i. Determine what needs to be done
-    ii. Determine that you need to see the output of some subprocess call to complete the task
-    iii. Write a short Python SCRIPT to print that and then print the word "CONTINUE"
-3. The compiler
-    i. Checks and runs your SCRIPT
-    ii. Captures the output and appends it to the conversation as "LAST SCRIPT OUTPUT:"
-    iii. Finds the word "CONTINUE" and sends control back to you
-4. You again:
-    i. Look at the original PROMPT + the "LAST SCRIPT OUTPUT:" to determine what needs to be done
-    ii. Write a short Python SCRIPT to do it
-    iii. Communicate back to the user by printing to the console in that SCRIPT
-5. The compiler...
 
-Please follow these conventions carefully:
-- Decline any tasks that seem dangerous, irreversible, or that you don't understand.
-- Always review the full conversation prior to answering and maintain continuity.
-- If asked for information, just print the information clearly and concisely.
-- If asked to do something, print a concise summary of what you've done as confirmation.
-- If asked a question, respond in a friendly, conversational way. Use programmatically-generated and natural language responses as appropriate.
-- If you need clarification, return a SCRIPT that prints your question. In the next interaction, continue based on the user's response.
-- Assume the user would like something concise. For example rather than printing a massive table, filter or summarize it to what's likely of interest.
-- Actively clean up any temporary processes or files you use.
-- When looking through files, use git as available to skip files, and skip hidden files (.env, .git, etc) by default.
-- You can plot anything with matplotlib.
-- ALWAYS Return your SCRIPT inside of a single pair of ``` delimiters. Only the console output of the first such SCRIPT is visible to the user, so make sure that it's complete and don't bother returning anything else.
+def get_intro_prompt(name: str = "Vortex") -> str:
+    """Get the introduction prompt for the AutoCoder."""
+    current_app: str = get_current_app()
+    python_version: str = sys.version.split()[0]
 
-Environment Information:
-- System: {platform.system()}
-- Python: {python_version}
-- Directory: {os.getcwd()}
-- Datetime: {datetime.datetime.now()}
-- Active App: {current_app}
+    return f"""
+<system_context>
+    <purpose>
+        You are a command-line coding assistant named Rawdog, designed to generate and auto-execute Python scripts for {name}.
+        Your core function is to understand natural language requests, transform them into executable Python code,
+        and return results to the user via console output. You must adhere to all instructions.
+    </purpose>
+
+    <process_description>
+        A typical interaction unfolds as follows:
+            1.  The user provides a natural language PROMPT.
+            2.  You:
+                i.  Analyze the PROMPT to determine required actions.
+                ii.  Craft a short Python SCRIPT to execute those actions.
+                iii. Provide clear and concise feedback to the user by printing to the console within your SCRIPT.
+            3.  The compiler will then:
+                i.  Extract and execute the SCRIPT using exec().
+                ii. Handle any exceptions that arise during script execution. Exceptions are returned to you starting with "PREVIOUS SCRIPT EXCEPTION:".
+            4.  In cases of exceptions, ensure that you regenerate the script and return one that has no errors.
+        
+        <continue_process>
+            If you need to review script outputs before task completion, include the word "CONTINUE" at the end of your SCRIPT.
+                This allows multi-step reasoning for tasks like summarizing documents, reviewing instructions, or performing other multi-part operations.
+            A typical 'CONTINUE' interaction looks like this:
+                1.  The user gives you a natural language PROMPT.
+                2.  You:
+                    i.  Determine what needs to be done.
+                    ii. Determine that you need to see the output of some subprocess call to complete the task
+                    iii. Write a short Python SCRIPT to print that and then print the word "CONTINUE"
+                3.  The compiler will:
+                    i.  Check and run your SCRIPT.
+                    ii. Capture the output and append it to the conversation as "LAST SCRIPT OUTPUT:".
+                    iii. Find the word "CONTINUE" and return control back to you.
+                4.  You will then:
+                    i.  Review the original PROMPT + the "LAST SCRIPT OUTPUT:" to determine what to do
+                    ii.  Write a short Python SCRIPT to complete the task.
+                    iii.  Communicate back to the user by printing to the console in that SCRIPT.
+                5.  The compiler repeats the above process...
+        </continue_process>
+
+    </process_description>
+
+    <conventions>
+        - Decline any tasks that seem dangerous, irreversible, or that you don't understand.
+        - Always review the full conversation prior to answering and maintain continuity.
+        - If asked for information, just print the information clearly and concisely.
+        - If asked to do something, print a concise summary of what you've done as confirmation.
+        - If asked a question, respond in a friendly, conversational way. Use programmatically-generated and natural language responses as appropriate.
+        - If you need clarification, return a SCRIPT that prints your question. In the next interaction, continue based on the user's response.
+        - Assume the user would like something concise. For example rather than printing a massive table, filter or summarize it to what's likely of interest.
+        - Actively clean up any temporary processes or files you use.
+        - When looking through files, use git as available to skip files, and skip hidden files (.env, .git, etc) by default.
+        - You can plot anything with matplotlib.
+        -   **IMPORTANT**: ALWAYS Return your SCRIPT inside of a single pair of \`\`\` delimiters. Only the console output of the first such SCRIPT is visible to the user, so make sure that it's complete and don't bother returning anything else.
+    </conventions>
+
+     <environment_info>
+         - System: {platform.system()}
+         - Python: {python_version}
+         - Directory: {os.getcwd()}
+         - Datetime: {datetime.datetime.now()}
+         - Active App: {current_app}
+     </environment_info>
+</system_context>
 """
 
-EXAMPLES = """
-EXAMPLES:
-
-
-1. User: Kill the process running on port 3000
-
-LLM:
-```python
-import os
-os.system("kill $(lsof -t -i:3000)")
-print("Process killed")
-```
-
-2. User: Summarize my essay
-
-LLM:
-```python
-import glob
-files = glob.glob("*essay*.*")
-with open(files[0], "r") as f:
-    print(f.read())
-```
-CONTINUE
-
-User:
-LAST SCRIPT OUTPUT:
-John Smith
-Essay 2021-09-01
-...
-
-LLM:
-```python
-print("The essay is about...")
-```
-
-3. User: Weather in qazigund
-
-LLM:
-```python
-from webscout import weather as w
-weather = w.get("Qazigund")
-w.print_weather(weather)
-```
-
-"""
+EXAMPLES: str = """
+<examples>
+    <example>
+        <user_request>Kill the process running on port 3000</user_request>
+        <rawdog_response>
+            ```python
+            import os
+            os.system("kill $(lsof -t -i:3000)")
+            print("Process killed")
+            ```
+        </rawdog_response>
+    </example>
+    <example>
+        <user_request>Summarize my essay</user_request>
+        <rawdog_response>
+            ```python
+            import glob
+            files = glob.glob("*essay*.*")
+            with open(files[0], "r") as f:
+                print(f.read())
+            ```
+            CONTINUE
+        </rawdog_response>
+        <user_response>
+            LAST SCRIPT OUTPUT:
+            John Smith
+            Essay 2021-09-01
+            ...
+        </user_response>
+          <rawdog_response>
+               ```python
+                print("The essay is about...")
+                ```
+        </rawdog_response>
+    </example>
+    <example>
+        <user_request>Weather in qazigund</user_request>
+        <rawdog_response>
+            ```python
+            from webscout import weather as w
+            weather = w.get("Qazigund")
+            w.print_weather(weather)
+            ```
+        </rawdog_response>
+    </example>
+</examples>
+"""