webscout 5.1__py3-none-any.whl → 5.2__py3-none-any.whl

webscout/Bing_search.py

@@ -2,10 +2,12 @@ from bs4 import BeautifulSoup
 import requests
 from typing import Dict, List, Optional, Union
 from concurrent.futures import ThreadPoolExecutor, as_completed
-from urllib.parse import urlparse
-from termcolor import colored
-import time
-import random
+from urllib.parse import quote, urlparse, parse_qs
+import base64
+import urllib3
+
+# Disable SSL warnings
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
 class BingS:
     """Bing search class to get search results from bing.com."""
@@ -21,7 +23,7 @@ class BingS:
         """Initialize the BingS object."""
         self.proxy: Optional[str] = proxy
         self.headers = headers if headers else {
-            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36 Edg/111.0.1661.62"
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
         }
         self.headers["Referer"] = "https://www.bing.com/"
         self.client = requests.Session()
@@ -43,82 +45,110 @@ class BingS:
         data: Optional[Union[Dict[str, str], bytes]] = None,
     ) -> bytes:
         try:
-            resp = self.client.request(method, url, params=params, data=data, timeout=self.timeout)
+            resp = self.client.request(method, url, params=params, data=data, timeout=self.timeout, verify=False)
         except Exception as ex:
             raise Exception(f"{url} {type(ex).__name__}: {ex}") from ex
         if resp.status_code == 200:
             return resp.content
         raise Exception(f"{resp.url} returned status code {resp.status_code}. {params=} {data=}")
 
+    def extract_text_from_webpage(self, html_content, max_characters=None):
+        """Extracts visible text from HTML content using BeautifulSoup."""
+        soup = BeautifulSoup(html_content, "html.parser")
+        # Remove unwanted tags
+        for tag in soup(["script", "style", "header", "footer", "nav"]):
+            tag.extract()
+        # Get the remaining visible text
+        visible_text = soup.get_text(separator=' ', strip=True)
+        if max_characters:
+            visible_text = visible_text[:max_characters]
+        return visible_text
+
     def search(
         self,
         keywords: str,
-        region: str = "us-EN",  # Bing uses us-EN
-        lang: str = "en",
-        safe: str = "off",
-        timelimit: Optional[str] = None,  # Not directly supported by Bing
-        max_results: Optional[int] = None,
+        max_results: Optional[int] = 10,
+        extract_webpage_text: bool = False,
+        max_extract_characters: Optional[int] = 100,
     ) -> List[Dict[str, str]]:
         """Bing text search."""
         assert keywords, "keywords is mandatory"
 
         results = []
-        start = 1  # Bing uses 1-based indexing for pages
-        while len(results) < (max_results or float('inf')):
+        futures = []
+        start = 1
+        while len(results) < max_results:
             params = {
                 "q": keywords,
-                "count": 10,  # Number of results per page
-                "mkt": region,
-                "setlang": lang,
-                "safeSearch": safe,
-                "first": start,  # Bing uses 'first' for pagination
+                "first": start
             }
+            futures.append(self._executor.submit(self._get_url, "GET", "https://www.bing.com/search", params=params))
+            start += 10
 
-            try:
-                resp_content = self._get_url("GET", "https://www.bing.com/search", params=params)
-                soup = BeautifulSoup(resp_content, "html.parser")
-                result_block = soup.find_all("li", class_="b_algo")
-
-                if not result_block:
-                    break
+            for future in as_completed(futures):
+                try:
+                    resp_content = future.result()
+                    soup = BeautifulSoup(resp_content, "html.parser")
+                    result_block = soup.select('li.b_algo')
 
-                for result in result_block:
-                    try:
-                        link = result.find("a", href=True)
-                        if link:
-                            initial_url = link["href"]
+                    if not result_block:
+                        break
 
-                            title = result.find("h2").text if result.find("h2") else ""
-                            description = result.find("p").text.strip() if result.find("p") else ""  # Strip whitespace
+                    for result in result_block:
+                        try:
+                            link = result.select_one('h2 a')
+                            title = link.text if link else ""
+                            url = link['href'] if link else ""
+                            abstract = result.select_one('.b_caption p')
+                            description = abstract.text if abstract else ""
 
-                            # Remove 'WEB' prefix if present
+                            # Remove "WEB" from the beginning of the description if it exists
                             if description.startswith("WEB"):
-                                description = description[4:]  # Skip the first 4 characters ('WEB ')
+                                description = description[3:].strip()
+
+                            visible_text = ""
+                            if extract_webpage_text:
+                                try:
+                                    actual_url = self._decode_bing_url(url)
+                                    page_content = self._get_url("GET", actual_url)
+                                    visible_text = self.extract_text_from_webpage(
+                                        page_content, max_characters=max_extract_characters
+                                    )
+                                except Exception as e:
+                                    print(f"Error extracting text from {url}: {e}")
 
                             results.append({
                                 "title": title,
-                                "href": initial_url,
+                                "href": url,
                                 "abstract": description,
                                 "index": len(results),
                                 "type": "web",
+                                "visible_text": visible_text,
                             })
 
                             if len(results) >= max_results:
                                 return results
 
-                    except Exception as e:
-                        print(f"Error extracting result: {e}")
+                        except Exception as e:
+                            print(f"Error extracting result: {e}")
 
-            except Exception as e:
-                print(f"Error fetching URL: {e}")
-
-            start += 10
+                except Exception as e:
+                    print(f"Error fetching URL: {e}")
 
         return results
 
+    def _decode_bing_url(self, url):
+        if 'bing.com/ck/a' in url:
+            parsed_url = urlparse(url)
+            query_params = parse_qs(parsed_url.query)
+            if 'u' in query_params:
+                encoded_url = query_params['u'][0]
+                return base64.b64decode(encoded_url).decode('utf-8')
+        return url
+
 if __name__ == "__main__":
     from rich import print
     searcher = BingS()
-    results = searcher.search("Python development tools", max_results=30)
+    results = searcher.search("Python development tools", max_results=5, extract_webpage_text=True, max_extract_characters=2000)
     for result in results:
-        print(result)
+        print(result)

webscout/Local/_version.py

@@ -1,3 +1,3 @@
 from llama_cpp import __version__ as __llama_cpp_version__
 
-__version__ = '4.8'
+__version__ = '5.2'

webscout/Provider/AI21.py

@@ -0,0 +1,177 @@
+import requests
+import json
+from typing import Dict, Any
+
+from webscout.AIutel import Optimizers
+from webscout.AIutel import Conversation
+from webscout.AIutel import AwesomePrompts
+from webscout.AIbase import Provider
+from webscout import exceptions
+
+class AI21(Provider):
+    """
+    A class to interact with the AI21 Studio API.
+    """
+
+    def __init__(
+        self,
+        api_key: str,
+        model: str = "jamba-1.5-large",
+        max_tokens: int = 1024,
+        temperature: float = 0.4,
+        top_p: float = 1,
+        is_conversation: bool = True,
+        timeout: int = 30,
+        intro: str = None,
+        filepath: str = None,
+        update_file: bool = True,
+        proxies: dict = {},
+        history_offset: int = 10250,
+        act: str = None,
+        system_prompt: str = "You are a helpful and informative AI assistant."
+    ):
+        """
+        Initializes the AI21 Studio API with given parameters.
+        """
+        self.api_key = api_key
+        self.api_endpoint = "https://api.ai21.com/studio/v1/chat/completions"
+        self.model = model
+        self.max_tokens = max_tokens
+        self.temperature = temperature
+        self.top_p = top_p
+        self.system_prompt = system_prompt
+        self.session = requests.Session()
+        self.is_conversation = is_conversation
+        self.max_tokens_to_sample = max_tokens
+        self.timeout = timeout
+        self.last_response = {}
+        self.headers = {
+            'Accept': 'application/json, text/plain, */*',
+            'Accept-Encoding': 'gzip, deflate, br, zstd',
+            'Accept-Language': 'en-US,en;q=0.9,en-IN;q=0.8',
+            'Authorization': f"Bearer {self.api_key}",
+            'Content-Type': 'application/json',
+            'DNT': '1',
+            'Origin': 'https://studio.ai21.com',
+            'Referer': 'https://studio.ai21.com/',
+            '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-site',
+            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36 Edg/128.0.0.0',
+        }
+
+        self.__available_optimizers = (
+            method
+            for method in dir(Optimizers)
+            if callable(getattr(Optimizers, method)) and not method.startswith("__")
+        )
+        self.session.headers.update(self.headers)
+        Conversation.intro = (
+            AwesomePrompts().get_act(
+                act, raise_not_found=True, default=None, case_insensitive=True
+            )
+            if act
+            else intro or Conversation.intro
+        )
+        self.conversation = Conversation(
+            is_conversation, self.max_tokens_to_sample, filepath, update_file
+        )
+        self.conversation.history_offset = history_offset
+        self.session.proxies = proxies
+
+    def ask(
+        self,
+        prompt: str,
+        stream: bool = False,
+        raw: bool = False,
+        optimizer: str = None,
+        conversationally: bool = False,
+    ) -> Dict[str, Any]:
+        """
+        Sends a prompt to the AI21 Studio API and returns the response.
+        """
+        conversation_prompt = self.conversation.gen_complete_prompt(prompt)
+        if optimizer:
+            if optimizer in self.__available_optimizers:
+                conversation_prompt = getattr(Optimizers, optimizer)(
+                    conversation_prompt if conversationally else prompt
+                )
+            else:
+                raise Exception(
+                    f"Optimizer is not one of {self.__available_optimizers}"
+                )
+
+        payload = {
+            "messages": [
+                {"role": "system", "content": self.system_prompt},
+                {"role": "user", "content": conversation_prompt}
+            ],
+            "n": 1,
+            "max_tokens": self.max_tokens,
+            "model": self.model,
+            "stop": [],
+            "temperature": self.temperature,
+            "top_p": self.top_p,
+            "documents": [],
+        }
+
+        response = self.session.post(self.api_endpoint, headers=self.headers, json=payload, timeout=self.timeout)
+
+        if not response.ok:
+            raise exceptions.FailedToGenerateResponseError(
+                f"Failed to generate response - ({response.status_code}, {response.reason}) - {response.text}"
+            )
+
+        resp = response.json()
+        self.last_response.update(resp)
+        self.conversation.update_chat_history(
+            prompt, self.get_message(self.last_response)
+        )
+        return self.last_response
+
+    def chat(
+        self,
+        prompt: str,
+        stream: bool = False,
+        optimizer: str = None,
+        conversationally: bool = False,
+    ) -> str:
+        """
+        Generates a response from the AI21 API.
+        """
+
+        def for_stream():
+            for response in self.ask(
+                prompt, True, optimizer=optimizer, conversationally=conversationally
+            ):
+                yield self.get_message(response)
+
+        def for_non_stream():
+            return self.get_message(
+                self.ask(
+                    prompt,
+                    False,
+                    optimizer=optimizer,
+                    conversationally=conversationally,
+                )
+            )
+
+        return for_stream() if stream else for_non_stream()
+
+    def get_message(self, response: dict) -> str:
+        """
+        Extracts the message from the API response.
+        """
+        assert isinstance(response, dict), "Response should be of dict data-type only"
+        return response['choices'][0]['message']['content']
+
+# Example usage
+if __name__ == "__main__":
+    from rich import print
+    ai = AI21(api_key="api_key")
+    response = ai.chat(input(">>> "))
+    for line in response:
+        print(line, end="", flush=True)

webscout/Provider/Cloudflare.py

@@ -30,10 +30,6 @@ import httpx
 import cloudscraper
 
 class Cloudflare(Provider):
-    """
-    This class provides methods for interacting with the Playground AI API 
-    (Cloudflare) in a consistent provider structure for webscout.
-    """
 
     AVAILABLE_MODELS = [
         "@cf/llava-hf/llava-1.5-7b-hf",

webscout/Provider/EDITEE.py

@@ -0,0 +1,215 @@
+import time
+import uuid
+from selenium import webdriver
+from selenium.webdriver.chrome.options import Options
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.support.ui import WebDriverWait
+import click
+import requests
+from requests import get
+from uuid import uuid4
+from re import findall
+from requests.exceptions import RequestException
+from curl_cffi.requests import get, RequestsError
+import g4f
+from random import randint
+from PIL import Image
+import io
+import re
+import json
+import yaml
+from webscout.AIutel import Optimizers
+from webscout.AIutel import Conversation, Proxy
+from webscout.AIutel import AwesomePrompts, sanitize_stream
+from webscout.AIbase import  Provider, AsyncProvider
+from webscout import exceptions
+from typing import Any, AsyncGenerator, Dict
+import logging
+import httpx
+import random 
+proxy = Proxy()
+
+class Editee(Provider):
+    """
+    A class to interact with the Editee.com API.
+    """
+    AVAILABLE_MODELS = [
+        "gemini", # it is gemini 1.5pro
+        "claude", # it is claude 3.5
+        "gpt4", # it is gpt4o
+        "mistrallarge", # it is mistral large2
+    ]
+
+    def __init__(
+        self,
+        is_conversation: bool = True,
+        max_tokens: int = 600,
+        timeout: int = 30,
+        intro: str = None,
+        filepath: str = None,
+        update_file: bool = True,
+        proxies: dict = {},
+        history_offset: int = 10250,
+        act: str = None,
+        model: str = "mistrallarge",
+    ) -> None:
+        """
+        Initializes the Editee API with given parameters.
+
+        Args:
+            is_conversation (bool, optional): Flag for chatting conversationally. Defaults to True.
+            max_tokens (int, optional): Maximum number of tokens to be generated upon completion. Defaults to 600.
+            timeout (int, optional): Http request timeout. Defaults to 30.
+            intro (str, optional): Conversation introductory prompt. Defaults to None.
+            filepath (str, optional): Path to file containing conversation history. Defaults to None.
+            update_file (bool, optional): Add new prompts and responses to the file. Defaults to True.
+            proxies (dict, optional): Http request proxies. Defaults to {}.
+            history_offset (int, optional): Limit conversation history to this number of last texts. Defaults to 10250.
+            act (str|int, optional): Awesome prompt key or index. (Used as intro). Defaults to None.
+            model (str, optional): AI model to use for text generation. Defaults to "gemini". 
+        """
+        if model not in self.AVAILABLE_MODELS:
+            raise ValueError(f"Invalid model: {model}. Choose from: {self.AVAILABLE_MODELS}")
+
+        self.session = requests.Session()
+        self.is_conversation = is_conversation
+        self.max_tokens_to_sample = max_tokens
+        self.api_endpoint = "https://editee.com/submit/chatgptfree"
+        self.stream_chunk_size = 64
+        self.timeout = timeout
+        self.last_response = {}
+        self.model = model
+        self._sessionValue = self._get_session()
+        self.headers = {
+            "authority": "editee.com",
+            "path": "/submit/chatgptfree",
+            "scheme": "https",
+            "accept": "application/json, text/plain, */*",
+            "accept-encoding": "gzip, deflate, br",
+            "accept-language": "ru-RU,ru;q=0.9,en-US;q=0.8,en;q=0.7",
+            "content-type": "application/json",
+            "cookie": f"editeecom_session={self._sessionValue}",
+            "origin": "https://editee.com",
+            "referer": "https://editee.com/chat-gpt",
+            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36",
+            "x-requested-with": "XMLHttpRequest"
+        }
+        self.__available_optimizers = (
+            method
+            for method in dir(Optimizers)
+            if callable(getattr(Optimizers, method)) and not method.startswith("__")
+        )
+        self.session.headers.update(self.headers)
+        Conversation.intro = (
+            AwesomePrompts().get_act(
+                act, raise_not_found=True, default=None, case_insensitive=True
+            )
+            if act
+            else intro or Conversation.intro
+        )
+        self.conversation = Conversation(
+            is_conversation, self.max_tokens_to_sample, filepath, update_file
+        )
+        self.conversation.history_offset = history_offset
+        self.session.proxies = proxies
+
+    def _get_session(self):
+        """Gets the editeecom_session value."""
+        res = proxy.get("https://editee.com/chat-gpt")
+        if res.cookies.get_dict():
+            first_cookie_name, session_value = next(iter(res.cookies.get_dict().items()))
+        return session_value
+
+    def ask(
+        self,
+        prompt: str,
+        stream: bool = False,
+        raw: bool = False,
+        optimizer: str = None,
+        conversationally: bool = False,
+    ) -> dict:
+        """Chat with AI
+
+        Args:
+            prompt (str): Prompt to be send.
+            stream (bool, optional): Whether to stream the response. Defaults to False.
+            raw (bool, optional): Whether to return the raw response. Defaults to False.
+            optimizer (str, optional): The name of the optimizer to use. Defaults to None.
+            conversationally (bool, optional): Whether to chat conversationally. Defaults to False.
+
+        Returns:
+            The response from the API.
+        """
+        conversation_prompt = self.conversation.gen_complete_prompt(prompt)
+        if optimizer:
+            if optimizer in self.__available_optimizers:
+                conversation_prompt = getattr(Optimizers, optimizer)(
+                    conversation_prompt if conversationally else prompt
+                )
+            else:
+                raise Exception(
+                    f"Optimizer is not one of {self.__available_optimizers}"
+                )
+        
+        payload = {
+            "context": " ",
+            "selected_model": self.model,
+            "template_id": "",
+            "user_input": conversation_prompt
+        }
+
+        response = proxy.post(self.api_endpoint, headers=self.headers, json=payload, timeout=self.timeout)
+        if not response.ok:
+            raise exceptions.FailedToGenerateResponseError(
+                f"Failed to generate response - ({response.status_code}, {response.reason}) - {response.text}"
+            )
+
+        resp = response.json()
+        self.last_response.update(dict(text=resp['text']))
+        self.conversation.update_chat_history(
+            prompt, self.get_message(self.last_response)
+        )
+        return self.last_response
+
+    def chat(
+        self,
+        prompt: str,
+        stream: bool = False,
+        optimizer: str = None,
+        conversationally: bool = False,
+    ) -> str:
+        """Generate response `str`
+        Args:
+            prompt (str): Prompt to be send.
+            stream (bool, optional): Flag for streaming response. Defaults to False.
+            optimizer (str, optional): Prompt optimizer name - `[code, shell_command]`. Defaults to None.
+            conversationally (bool, optional): Chat conversationally when using optimizer. Defaults to False.
+        Returns:
+            str: Response generated
+        """
+        return self.get_message(
+            self.ask(
+                prompt,
+                optimizer=optimizer,
+                conversationally=conversationally,
+            )
+        )
+
+    def get_message(self, response: dict) -> str:
+        """Retrieves message only from response
+
+        Args:
+            response (dict): Response generated by `self.ask`
+
+        Returns:
+            str: Message extracted
+        """
+        assert isinstance(response, dict), "Response should be of dict data-type only"
+        return response["text"]
+if __name__ == '__main__':
+    from rich import print
+    ai = Editee()
+    response = ai.chat("tell me about india")
+    for chunk in response:
+        print(chunk, end="", flush=True)