webscout 8.2.2__py3-none-any.whl → 8.2.7__py3-none-any.whl

webscout/Provider/AISEARCH/felo_search.py

@@ -1,228 +0,0 @@
-import requests
-from uuid import uuid4
-import json
-from typing import Any, Dict, Generator, Optional, Union
-
-from webscout.AIbase import AISearch
-from webscout import exceptions
-from webscout.litagent import LitAgent
-
-
-class Response:
-    """A wrapper class for API responses.
-    
-    This class automatically converts response objects to their text representation
-    when printed or converted to string.
-    
-    Attributes:
-        text (str): The text content of the response
-        
-    Example:
-        >>> response = Response("Hello, world!")
-        >>> print(response)
-        Hello, world!
-        >>> str(response)
-        'Hello, world!'
-    """
-    def __init__(self, text: str):
-        self.text = text
-    
-    def __str__(self):
-        return self.text
-    
-    def __repr__(self):
-        return self.text
-
-
-class Felo(AISearch):
-    """A class to interact with the Felo AI search API.
-    
-    Felo provides a powerful search interface that returns AI-generated responses
-    based on web content. It supports both streaming and non-streaming responses.
-    
-    Basic Usage:
-        >>> from webscout import Felo
-        >>> ai = Felo()
-        >>> # Non-streaming example
-        >>> response = ai.search("What is Python?")
-        >>> print(response)
-        Python is a high-level programming language...
-        
-        >>> # Streaming example
-        >>> for chunk in ai.search("Tell me about AI", stream=True):
-        ...     print(chunk, end="", flush=True)
-        Artificial Intelligence is...
-        
-        >>> # Raw response format
-        >>> for chunk in ai.search("Hello", stream=True, raw=True):
-        ...     print(chunk)
-        {'text': 'Hello'}
-        {'text': ' there!'}
-    
-    Args:
-        timeout (int, optional): Request timeout in seconds. Defaults to 30.
-        proxies (dict, optional): Proxy configuration for requests. Defaults to None.
-    
-    Attributes:
-        api_endpoint (str): The Felo API endpoint URL.
-        stream_chunk_size (int): Size of chunks when streaming responses.
-        timeout (int): Request timeout in seconds.
-        headers (dict): HTTP headers used in requests.
-    """
-
-    def __init__(
-        self,
-        timeout: int = 30,
-        proxies: Optional[dict] = None,
-    ):
-        """Initialize the Felo API client.
-        
-        Args:
-            timeout (int, optional): Request timeout in seconds. Defaults to 30.
-            proxies (dict, optional): Proxy configuration for requests. Defaults to None.
-        
-        Example:
-            >>> ai = Felo(timeout=60)  # Longer timeout
-            >>> ai = Felo(proxies={'http': 'http://proxy.com:8080'})  # With proxy
-        """
-        self.session = requests.Session()
-        self.chat_endpoint = "https://api.felo.ai/search/threads"
-        self.stream_chunk_size = 64
-        self.timeout = timeout
-        self.last_response = {}
-        self.headers = {
-            "accept": "*/*",
-            "accept-encoding": "gzip, deflate, br, zstd",
-            "accept-language": "en-US,en;q=0.9,en-IN;q=0.8",
-            "content-type": "application/json",
-            "cookie": "_clck=1gifk45%7C2%7Cfoa%7C0%7C1686; _clsk=1g5lv07%7C1723558310439%7C1%7C1%7Cu.clarity.ms%2Fcollect; _ga=GA1.1.877307181.1723558313; _ga_8SZPRV97HV=GS1.1.1723558313.1.1.1723558341.0.0.0; _ga_Q9Q1E734CC=GS1.1.1723558313.1.1.1723558341.0.0.0",
-            "dnt": "1",
-            "origin": "https://felo.ai",
-            "referer": "https://felo.ai/",
-            "sec-ch-ua": '"Not)A;Brand";v="99", "Microsoft Edge";v="127", "Chromium";v="127"',
-            "sec-ch-ua-mobile": "?0",
-            "sec-ch-ua-platform": '"Windows"',
-            "sec-fetch-dest": "empty",
-            "sec-fetch-mode": "cors",
-            "sec-fetch-site": "same-site",
-            "user-agent": LitAgent().random()
-        }
-        self.session.headers.update(self.headers)
-        self.proxies = proxies
-
-    def search(
-        self,
-        prompt: str,
-        stream: bool = False,
-        raw: bool = False,
-    ) -> Union[Response, Generator[Union[Dict[str, str], Response], None, None]]:
-        """Search using the Felo API and get AI-generated responses.
-        
-        This method sends a search query to Felo and returns the AI-generated response.
-        It supports both streaming and non-streaming modes, as well as raw response format.
-        
-        Args:
-            prompt (str): The search query or prompt to send to the API.
-            stream (bool, optional): If True, yields response chunks as they arrive.
-                                   If False, returns complete response. Defaults to False.
-            raw (bool, optional): If True, returns raw response dictionaries with 'text' key.
-                                If False, returns Response objects that convert to text automatically.
-                                Defaults to False.
-        
-        Returns:
-            Union[Response, Generator[Union[Dict[str, str], Response], None, None]]: 
-                - If stream=False: Returns complete response as Response object
-                - If stream=True: Yields response chunks as either Dict or Response objects
-        
-        Raises:
-            APIConnectionError: If the API request fails
-        
-        Examples:
-            Basic search:
-            >>> ai = Felo()
-            >>> response = ai.search("What is Python?")
-            >>> print(response)
-            Python is a programming language...
-            
-            Streaming response:
-            >>> for chunk in ai.search("Tell me about AI", stream=True):
-            ...     print(chunk, end="")
-            Artificial Intelligence...
-            
-            Raw response format:
-            >>> for chunk in ai.search("Hello", stream=True, raw=True):
-            ...     print(chunk)
-            {'text': 'Hello'}
-            {'text': ' there!'}
-            
-            Error handling:
-            >>> try:
-            ...     response = ai.search("My question")
-            ... except exceptions.APIConnectionError as e:
-            ...     print(f"API error: {e}")
-        """
-        payload = {
-            "query": prompt,
-            "search_uuid": uuid4().hex,
-            "lang": "",
-            "agent_lang": "en",
-            "search_options": {
-                "langcode": "en-US"
-            },
-            "search_video": True,
-            "contexts_from": "google"
-        }
-
-        def for_stream():
-            try:
-                with self.session.post(
-                    self.chat_endpoint,
-                    json=payload,
-                    stream=True,
-                    timeout=self.timeout,
-                ) as response:
-                    if not response.ok:
-                        raise exceptions.APIConnectionError(
-                            f"Failed to generate response - ({response.status_code}, {response.reason}) - {response.text}"
-                        )
-
-                    streaming_text = ""
-                    for line in response.iter_lines(decode_unicode=True):
-                        if line.startswith('data:'):
-                            try:
-                                data = json.loads(line[5:].strip())
-                                if data['type'] == 'answer' and 'text' in data['data']:
-                                    new_text = data['data']['text']
-                                    if len(new_text) > len(streaming_text):
-                                        delta = new_text[len(streaming_text):]
-                                        streaming_text = new_text
-                                        if raw:
-                                            yield {"text": delta}
-                                        else:
-                                            yield Response(delta)
-                            except json.JSONDecodeError:
-                                pass
-                    self.last_response = Response(streaming_text)
-            except requests.exceptions.RequestException as e:
-                raise exceptions.APIConnectionError(f"Request failed: {e}")
-
-        def for_non_stream():
-            full_response = ""
-            for chunk in for_stream():
-                if raw:
-                    yield chunk
-                else:
-                    full_response += str(chunk)
-            if not raw:
-                self.last_response = Response(full_response)
-                return self.last_response
-        
-        return for_stream() if stream else for_non_stream()
-
-
-if __name__ == "__main__":
-    from rich import print
-    ai = Felo()
-    response = ai.search(input(">>> "), stream=True, raw=False)
-    for chunk in response:
-        print(chunk, end="", flush=True)

webscout/Provider/AISEARCH/genspark_search.py

@@ -1,208 +0,0 @@
-import cloudscraper
-from uuid import uuid4
-import json
-import re
-from typing import Dict, Optional, Generator, Union, Any
-
-from webscout.AIbase import AISearch
-from webscout import exceptions
-from webscout.litagent import LitAgent
-
-
-class Response:
-    """A wrapper class for Genspark API responses.
-    
-    This class automatically converts response objects to their text representation
-    when printed or converted to string.
-    
-    Attributes:
-        text (str): The text content of the response
-        
-    Example:
-        >>> response = Response("Hello, world!")
-        >>> print(response)
-        Hello, world!
-        >>> str(response)
-        'Hello, world!'
-    """
-    def __init__(self, text: str):
-        self.text = text
-    
-    def __str__(self):
-        return self.text
-    
-    def __repr__(self):
-        return self.text
-
-
-class Genspark(AISearch):
-    """A class to interact with the Genspark AI search API.
-    
-    Genspark provides a powerful search interface that returns AI-generated responses
-    based on web content. It supports both streaming and non-streaming responses.
-    
-    Basic Usage:
-        >>> from webscout import Genspark
-        >>> ai = Genspark()
-        >>> # Non-streaming example
-        >>> response = ai.search("What is Python?")
-        >>> print(response)
-        Python is a high-level programming language...
-        
-        >>> # Streaming example
-        >>> for chunk in ai.search("Tell me about AI", stream=True):
-        ...     print(chunk, end="", flush=True)
-        Artificial Intelligence is...
-        
-        >>> # Raw response format
-        >>> for chunk in ai.search("Hello", stream=True, raw=True):
-        ...     print(chunk)
-        {'text': 'Hello'}
-        {'text': ' there!'}
-    
-    Args:
-        timeout (int, optional): Request timeout in seconds. Defaults to 30.
-        proxies (dict, optional): Proxy configuration for requests. Defaults to None.
-        max_tokens (int, optional): Maximum tokens to generate. Defaults to 600.
-    """
-
-    def __init__(
-        self,
-        timeout: int = 30,
-        proxies: Optional[dict] = None,
-        max_tokens: int = 600,
-    ):
-        """Initialize the Genspark API client.
-        
-        Args:
-            timeout (int, optional): Request timeout in seconds. Defaults to 30.
-            proxies (dict, optional): Proxy configuration for requests. Defaults to None.
-            max_tokens (int, optional): Maximum tokens to generate. Defaults to 600.
-        """
-        self.session = cloudscraper.create_scraper()
-        self.max_tokens = max_tokens
-        self.chat_endpoint = "https://www.genspark.ai/api/search/stream"
-        self.stream_chunk_size = 64
-        self.timeout = timeout
-        self.last_response = {}
-        
-        self.headers = {
-            "Accept": "*/*",
-            "Accept-Encoding": "gzip, deflate, br, zstd",
-            "Accept-Language": "en-US,en;q=0.9,en-IN;q=0.8",
-            "Content-Type": "application/json",
-            "DNT": "1",
-            "Origin": "https://www.genspark.ai",
-            "Priority": "u=1, i",
-            "Sec-CH-UA": '"Chromium";v="128", "Not;A=Brand";v="24", "Microsoft Edge";v="128"',
-            "Sec-CH-UA-Mobile": "?0",
-            "Sec-CH-UA-Platform": '"Windows"',
-            "Sec-Fetch-Dest": "empty",
-            "Sec-Fetch-Mode": "cors",
-            "Sec-Fetch-Site": "same-origin",
-            "User-Agent": LitAgent().random(),
-        }
-        
-        self.cookies = {
-            "i18n_redirected": "en-US",
-            "agree_terms": "0",
-            "session_id": uuid4().hex,
-        }
-
-        self.session.headers.update(self.headers)
-        self.session.proxies = proxies or {}
-
-    def search(
-        self,
-        prompt: str,
-        stream: bool = False,
-        raw: bool = False,
-    ) -> Union[Response, Generator[Union[Dict[str, str], Response], None, None]]:
-        """Search using the Genspark API and get AI-generated responses.
-        
-        Args:
-            prompt (str): The search query or prompt to send to the API.
-            stream (bool, optional): If True, yields response chunks as they arrive.
-                                   If False, returns complete response. Defaults to False.
-            raw (bool, optional): If True, returns raw response dictionaries with 'text' key.
-                                If False, returns Response objects that convert to text automatically.
-                                Defaults to False.
-        
-        Returns:
-            Union[Dict[str, Any], Generator[Union[Dict[str, Any], str], None, None]]: 
-                - If stream=False: Returns complete response
-                - If stream=True: Yields response chunks as they arrive
-        
-        Raises:
-            APIConnectionError: If the API request fails
-        """
-        url = f"https://www.genspark.ai/api/search/stream?query={prompt.replace(' ', '%20')}"
-        
-        def for_stream():
-            try:
-                with self.session.post(
-                    url,
-                    headers=self.headers,
-                    cookies=self.cookies,
-                    json={},  # Empty payload as query is in URL
-                    stream=True,
-                    timeout=self.timeout,
-                ) as response:
-                    if not response.ok:
-                        raise exceptions.APIConnectionError(
-                            f"Failed to generate response - ({response.status_code}, {response.reason}) - {response.text}"
-                        )
-                    
-                    for line in response.iter_lines(decode_unicode=True):
-                        if line and line.startswith("data: "):
-                            try:
-                                data = json.loads(line[6:])
-                                if "field_name" in data and "delta" in data:
-                                    if data["field_name"].startswith("streaming_detail_answer"):
-                                        delta_text = data.get("delta", "")
-                                        
-                                        # Clean up markdown links in text
-                                        delta_text = re.sub(r"\[.*?\]\(.*?\)", "", delta_text)
-                                        
-                                        if raw:
-                                            yield {"text": delta_text}
-                                        else:
-                                            yield Response(delta_text)
-                            except json.JSONDecodeError:
-                                continue
-                                
-            except cloudscraper.exceptions as e:
-                raise exceptions.APIConnectionError(f"Request failed: {e}")
-                
-        def for_non_stream():
-            full_response = ""
-            for chunk in for_stream():
-                if raw:
-                    yield chunk
-                else:
-                    full_response += str(chunk)
-            
-            if not raw:
-                # Process the full response to clean up any JSON structures
-                try:
-                    text_json = json.loads(full_response)
-                    if isinstance(text_json, dict) and "detailAnswer" in text_json:
-                        full_response = text_json.get("detailAnswer", full_response)
-                except (json.JSONDecodeError, TypeError):
-                    # Not valid JSON or not a dictionary, keep as is
-                    pass
-                    
-                self.last_response = Response(full_response)
-                return self.last_response
-
-        return for_stream() if stream else for_non_stream()
-
-
-if __name__ == "__main__":
-
-    from rich import print
-    
-    ai = Genspark()
-    response = ai.search(input(">>> "), stream=True, raw=False)
-    for chunk in response:
-        print(chunk, end="", flush=True)

webscout/Provider/AISEARCH/hika_search.py

@@ -1,194 +0,0 @@
-import requests
-import hashlib
-import json
-import random
-import time
-import re
-from typing import Dict, Optional, Generator, Union, Any
-
-from webscout.AIbase import AISearch
-from webscout import exceptions
-from webscout.litagent import LitAgent
-
-
-class Response:
-    """A wrapper class for Hika API responses."""
-    def __init__(self, text: str):
-        self.text = text
-    
-    def __str__(self):
-        return self.text
-    
-    def __repr__(self):
-        return self.text
-
-
-class Hika(AISearch):
-    """A class to interact with the Hika AI search API."""
-
-    def __init__(
-        self,
-        timeout: int = 60,
-        proxies: Optional[dict] = None,
-        language: str = "en",
-    ):
-        self.session = requests.Session()
-        self.base_url = "https://api.hika.fyi/api/"
-        self.endpoint = "kbase/web"
-        self.timeout = timeout
-        self.language = language
-        self.last_response = {}
-        
-        self.headers = {
-            "Content-Type": "application/json",
-            "Origin": "https://hika.fyi",
-            "Referer": "https://hika.fyi/",
-            "User-Agent": LitAgent().random()
-        }
-        
-        self.session.headers.update(self.headers)
-        self.proxies = proxies
-
-    def generate_id(self):
-        """Generate a unique ID and hash for the request."""
-        uid = ''.join(random.choice('0123456789abcdefghijklmnopqrstuvwxyz') for _ in range(10))
-        uid += hex(int(time.time()))[2:]
-        hash_id = hashlib.sha256(f"#{uid}*".encode()).hexdigest()
-        return {"uid": uid, "hashId": hash_id}
-
-    def clean_text(self, text):
-        """Clean all XML tags and control markers from text.
-        
-        Args:
-            text (str): The text to clean
-            
-        Returns:
-            str: Cleaned text
-        """
-        if not text:
-            return ""
-            
-        # Remove XML tags and special markers
-        # First remove <r> tag at the beginning
-        text = text.lstrip("<r>")
-        
-        # Remove any remaining XML tags
-        text = re.sub(r'<[^>]+>', '', text)
-        
-        # Remove [DONE] marker at the end
-        text = re.sub(r'\[DONE\]\s*$', '', text)
-        
-        return text
-
-    def search(
-        self,
-        prompt: str,
-        stream: bool = False,
-        raw: bool = False,
-    ) -> Union[Response, Generator[Union[Dict[str, str], Response], None, None]]:
-        """Search using the Hika API and get AI-generated responses."""
-        if not prompt or len(prompt) < 2:
-            raise exceptions.APIConnectionError("Search query must be at least 2 characters long")
-        
-        # Generate ID for this request
-        id_data = self.generate_id()
-        uid, hash_id = id_data["uid"], id_data["hashId"]
-        
-        # Update headers with request-specific values
-        request_headers = {
-            **self.headers,
-            "x-hika": hash_id,
-            "x-uid": uid
-        }
-        
-        # Prepare payload
-        payload = {
-            "keyword": prompt,
-            "language": self.language,
-            "stream": True  # Always request streaming for consistent handling
-        }
-
-        def for_stream():
-            try:
-                with self.session.post(
-                    f"{self.base_url}{self.endpoint}",
-                    json=payload,
-                    headers=request_headers,
-                    stream=True,
-                    timeout=self.timeout,
-                    proxies=self.proxies
-                ) as response:
-                    if not response.ok:
-                        raise exceptions.APIConnectionError(
-                            f"Failed to generate response - ({response.status_code}, {response.reason}) - {response.text}"
-                        )
-                    
-                    for line in response.iter_lines(decode_unicode=True):
-                        if line and line.startswith("data: "):
-                            try:
-                                data = json.loads(line[6:])
-                                if "chunk" in data:
-                                    chunk = data["chunk"]
-                                    
-                                    # Skip [DONE] markers completely
-                                    if "[DONE]" in chunk:
-                                        continue
-                                    
-                                    # Clean the chunk
-                                    clean_chunk = self.clean_text(chunk)
-                                    
-                                    if clean_chunk:  # Only yield if there's content after cleaning
-                                        if raw:
-                                            yield {"text": clean_chunk}
-                                        else:
-                                            yield Response(clean_chunk)
-                            except json.JSONDecodeError:
-                                pass
-                                
-            except requests.exceptions.RequestException as e:
-                raise exceptions.APIConnectionError(f"Request failed: {e}")
-
-        def for_non_stream():
-            full_response = ""
-            for chunk in for_stream():
-                if raw:
-                    yield chunk
-                else:
-                    full_response += str(chunk)
-            
-            if not raw:
-                # Clean up the response text one final time
-                cleaned_response = self.format_response(full_response)
-                self.last_response = Response(cleaned_response)
-                return self.last_response
-
-        return for_stream() if stream else for_non_stream()
-    
-    def format_response(self, text: str) -> str:
-        """Format the response text for better readability."""
-        if not text:
-            return ""
-            
-        # First clean any tags or markers
-        cleaned_text = self.clean_text(text)
-        
-        # Remove any empty lines
-        cleaned_text = re.sub(r'\n\s*\n', '\n\n', cleaned_text)
-        
-        # Remove any trailing whitespace
-        cleaned_text = cleaned_text.strip()
-        
-        return cleaned_text
-
-
-if __name__ == "__main__":
-    from rich import print
-    ai = Hika()
-    try:
-        response = ai.search(input(">>> "), stream=True, raw=False)
-        for chunk in response:
-            print(chunk, end="", flush=True)
-    except KeyboardInterrupt:
-        print("\nSearch interrupted by user.")
-    except Exception as e:
-        print(f"\nError: {e}")