webscout 5.2__py3-none-any.whl → 5.4__py3-none-any.whl

webscout/DWEBS.py

@@ -8,18 +8,19 @@ import time
 import random
 
 class GoogleS:
-    """Google search class to get search results from google.com."""
-
-    _executor: ThreadPoolExecutor = ThreadPoolExecutor(max_workers=10)
+    """
+    Class to perform Google searches and retrieve results.
+    """
 
     def __init__(
         self,
         headers: Optional[Dict[str, str]] = None,
         proxy: Optional[str] = None,
         timeout: Optional[int] = 10,
-    ) -> None:
-        """Initialize the GoogleS object."""
-        self.proxy: Optional[str] = proxy
+        max_workers: int = 20  # Increased max workers for thread pool
+    ):
+        """Initializes the GoogleS object."""
+        self.proxy = 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"
         }
@@ -28,20 +29,19 @@ class GoogleS:
         self.client.headers.update(self.headers)
         self.client.proxies.update({"http": self.proxy, "https": self.proxy})
         self.timeout = timeout
+        self._executor = ThreadPoolExecutor(max_workers=max_workers) 
 
-    def __enter__(self) -> "GoogleS":
+    def __enter__(self):
         return self
 
     def __exit__(self, exc_type, exc_val, exc_tb):
         self.client.close()
 
-    def _get_url(
-        self,
-        method: str,
-        url: str,
-        params: Optional[Dict[str, str]] = None,
-        data: Optional[Union[Dict[str, str], bytes]] = None,
-    ) -> bytes:
+    def _get_url(self, method: str, url: str, params: Optional[Dict[str, str]] = None,
+                  data: Optional[Union[Dict[str, str], bytes]] = None) -> bytes:
+        """
+        Makes an HTTP request and returns the response content.
+        """
         try:
             resp = self.client.request(method, url, params=params, data=data, timeout=self.timeout)
         except Exception as ex:
@@ -50,13 +50,13 @@ class GoogleS:
             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
+    def _extract_text_from_webpage(self, html_content: bytes, max_characters: Optional[int] = None) -> str:
+        """
+        Extracts visible text from HTML content using lxml parser.
+        """
+        soup = BeautifulSoup(html_content, 'lxml')  # Use lxml parser
         for tag in soup(["script", "style", "header", "footer", "nav"]):
             tag.extract()
-        # Get the remaining visible text
         visible_text = soup.get_text(strip=True)
         if max_characters:
             visible_text = visible_text[:max_characters]
@@ -64,32 +64,56 @@ class GoogleS:
 
     def search(
         self,
-        keywords: str,
+        query: str,
         region: str = "us-en",
-        lang: str = "en",
+        language: str = "en",
         safe: str = "off",
-        timelimit: Optional[str] = None,
-        max_results: Optional[int] = None,
-        extract_webpage_text: bool = False,
-        max_extract_characters: Optional[int] = 100,  
-    ) -> List[Dict[str, str]]:
-        """Google text search."""
-        assert keywords, "keywords is mandatory"
+        time_period: Optional[str] = None,
+        max_results: int = 10,
+        extract_text: bool = False,
+        max_text_length: Optional[int] = 100,
+    ) -> List[Dict[str, Union[str, int]]]:
+        """
+        Performs a Google search and returns the results.
+
+        Args:
+            query (str): The search query.
+            region (str, optional): The region to search in (e.g., "us-en"). Defaults to "us-en".
+            language (str, optional): The language of the search results (e.g., "en"). Defaults to "en".
+            safe (str, optional): Safe search setting ("off", "active"). Defaults to "off".
+            time_period (Optional[str], optional): Time period filter (e.g., "h" for past hour, "d" for past day). 
+                                                   Defaults to None.
+            max_results (int, optional): The maximum number of results to retrieve. Defaults to 10.
+            extract_text (bool, optional): Whether to extract text from the linked web pages. Defaults to False.
+            max_text_length (Optional[int], optional): The maximum length of the extracted text (in characters). 
+                                                      Defaults to 100.
+
+        Returns:
+            List[Dict[str, Union[str, int]]]: A list of dictionaries, each representing a search result, containing:
+                - 'title': The title of the result.
+                - 'href': The URL of the result.
+                - 'abstract': The description snippet of the result.
+                - 'index': The index of the result in the list.
+                - 'type': The type of result (currently always "web").
+                - 'visible_text': The extracted text from the web page (if `extract_text` is True).
+        """
+        assert query, "Query cannot be empty."
 
         results = []
         futures = []
         start = 0
+
         while len(results) < max_results:
             params = {
-                "q": keywords,
-                "num": 10,  # Number of results per page
-                "hl": lang,
+                "q": query,
+                "num": 10,
+                "hl": language,
                 "start": start,
                 "safe": safe,
                 "gl": region,
             }
-            if timelimit:
-                params["tbs"] = f"qdr:{timelimit}"
+            if time_period:
+                params["tbs"] = f"qdr:{time_period}"
 
             futures.append(self._executor.submit(self._get_url, "GET", "https://www.google.com/search", params=params))
             start += 10
@@ -97,54 +121,52 @@ class GoogleS:
             for future in as_completed(futures):
                 try:
                     resp_content = future.result()
-                    soup = BeautifulSoup(resp_content, "html.parser")
-                    result_block = soup.find_all("div", class_="g")
+                    soup = BeautifulSoup(resp_content, 'lxml')  # Use lxml parser
+                    result_blocks = soup.find_all("div", class_="g")
 
-                    if not result_block:
+                    if not result_blocks:
                         break
 
-                    for result in result_block:
-                        try:
-                            link = result.find("a", href=True)
-                            title = result.find("h3")
-                            description_box = result.find(
-                                "div", {"style": "-webkit-line-clamp:2"}
-                            )
-
-                            if link and title and description_box:
-                                url = link["href"]
-                                title = title.text
-                                description = description_box.text
-
-                                visible_text = ""
-                                if extract_webpage_text:
-                                    try:
-                                        page_content = self._get_url("GET", 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": 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}")
+                    # Extract links and titles first
+                    for result_block in result_blocks:
+                        link = result_block.find("a", href=True)
+                        title = result_block.find("h3")
+                        description_box = result_block.find(
+                            "div", {"style": "-webkit-line-clamp:2"}
+                        )
+
+                        if link and title and description_box:
+                            url = link["href"]
+                            results.append({
+                                "title": title.text,
+                                "href": url,
+                                "abstract": description_box.text,
+                                "index": len(results),
+                                "type": "web",
+                                "visible_text": ""  # Initialize visible_text as empty string
+                            })
+
+                            if len(results) >= max_results:
+                                break  # Stop if we have enough results
+
+                    # Parallelize text extraction if needed
+                    if extract_text:
+                        with ThreadPoolExecutor(max_workers=self._executor._max_workers) as text_extractor:
+                            extraction_futures = [
+                                text_extractor.submit(self._extract_text_from_webpage, 
+                                                    self._get_url("GET", result['href']),
+                                                    max_characters=max_text_length)
+                                for result in results 
+                                if 'href' in result
+                            ]
+                            for i, future in enumerate(as_completed(extraction_futures)):
+                                try:
+                                    results[i]['visible_text'] = future.result()
+                                except Exception as e:
+                                    print(f"Error extracting text: {e}")
 
                 except Exception as e:
-                    print(f"Error fetching URL: {e}")
+                    print(f"Error: {e}")  
 
         return results
 
@@ -152,6 +174,6 @@ class GoogleS:
 if __name__ == "__main__":
     from rich import print
     searcher = GoogleS()
-    results = searcher.search("HelpingAI-9B", max_results=20, extract_webpage_text=True, max_extract_characters=200)
+    results = searcher.search("HelpingAI-9B", max_results=20, extract_text=False, max_text_length=200)
     for result in results:
         print(result)

webscout/Local/_version.py

@@ -1,3 +1,3 @@
 from llama_cpp import __version__ as __llama_cpp_version__
-
-__version__ = '5.2'
+from webscout.version import __prog__, __version__
+__version__ = __version__

webscout/Provider/Andi.py

@@ -1,32 +1,12 @@
-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 requests
 import json
-import yaml
 from webscout.AIutel import Optimizers
 from webscout.AIutel import Conversation
 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
 from webscout import WEBS
 from rich import print
 

webscout/Provider/BasedGPT.py

@@ -1,32 +1,12 @@
-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
 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
+
 
 class BasedGPT(Provider):
     def __init__(

webscout/Provider/Blackboxai.py

@@ -1,32 +1,12 @@
-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
 from webscout.AIutel import AwesomePrompts, sanitize_stream
 from webscout.AIbase import Provider, AsyncProvider
-from Helpingai_T2 import Perplexity
 from webscout import exceptions
 from typing import Any, AsyncGenerator, Dict
-import logging
 import httpx
 
 #------------------------------------------------------BLACKBOXAI--------------------------------------------------------
@@ -433,7 +413,7 @@ class AsyncBLACKBOXAI(AsyncProvider):
             str: Message extracted
         """
         assert isinstance(response, dict), "Response should be of dict data-type only"
-        return response["text"]
+        return response["text"].replace('\\n', '\n').replace('\\n\\n', '\n\n')
 
 # Function to clean the response text
 def clean_response(response_text: str) -> str:

webscout/Provider/Chatify.py

@@ -0,0 +1,175 @@
+from webscout.AIutel import Optimizers
+from webscout.AIutel import Conversation
+from webscout.AIutel import AwesomePrompts
+from webscout.AIbase import Provider
+from webscout import exceptions
+import requests
+
+class Chatify(Provider):
+    """
+    A class to interact with the Chatify AI API.
+    """
+
+    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,
+        system_prompt: str = "You are a helpful and informative AI assistant.",
+    ):
+        """
+        Initializes the Chatify AI API with given parameters.
+        """
+        self.session = requests.Session()
+        self.is_conversation = is_conversation
+        self.max_tokens_to_sample = max_tokens
+        self.api_endpoint = "https://chatify-ai.vercel.app/api/chat"
+        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://chatify-ai.vercel.app',
+            'Referer': 'https://chatify-ai.vercel.app/',
+            '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-origin',
+            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36 Edg/127.0.0.0',
+        }
+
+        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
+        self.system_prompt = system_prompt
+
+    def ask(
+        self,
+        prompt: str,
+        stream: bool = False,
+        raw: bool = False,
+        optimizer: str = None,
+        conversationally: bool = False,
+    ) -> dict:
+        """
+        Sends a prompt to the Chatify 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}"
+                )
+
+        messages = []
+        if self.system_prompt:
+            messages.append({"role": "system", "content": self.system_prompt})
+        messages.append({"role": "user", "content": conversation_prompt})
+
+        payload = {
+            "messages": messages
+        }
+
+        def for_stream():
+            response = self.session.post(self.api_endpoint, headers=self.headers, json=payload, stream=True, timeout=self.timeout)
+            if not response.ok:
+                raise exceptions.FailedToGenerateResponseError(
+                    f"Failed to generate response - ({response.status_code}, {response.reason}) - {response.text}"
+                )
+
+            streaming_text = ""
+            for line in response.iter_lines(): 
+                if line:
+                    decoded_line = line.decode('utf-8')  # Decode the line
+                    parts = decoded_line.split(':', 1)
+                    if len(parts) > 1:
+                        content = parts[1].strip().strip('"')
+                        streaming_text += content
+                        yield content if raw else dict(text=streaming_text)
+            self.last_response.update(dict(text=streaming_text))
+            self.conversation.update_chat_history(
+                prompt, self.get_message(self.last_response)
+            )
+
+        def for_non_stream():
+            for _ in for_stream():
+                pass
+            return self.last_response
+
+        return for_stream() if stream else for_non_stream()
+
+    def chat(
+        self,
+        prompt: str,
+        stream: bool = False,
+        optimizer: str = None,
+        conversationally: bool = False,
+    ) -> str:
+        """
+        Generates a response from the Chatify 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 and formats it.
+        """
+        assert isinstance(response, dict), "Response should be of dict data-type only"
+        return response["text"].replace('\\n', '\n').replace('\\n\\n', '\n\n')
+
+
+# Example usage
+if __name__ == "__main__":
+    from rich import print
+
+    ai = Chatify() 
+    response = ai.chat(input(">>> "))
+    for chunk in response:
+        print(chunk, end="", flush=True)

webscout/Provider/Cloudflare.py

@@ -1,32 +1,11 @@
-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 uuid import uuid4
 from webscout.AIutel import Optimizers
 from webscout.AIutel import Conversation
 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 cloudscraper
 
 class Cloudflare(Provider):

webscout/Provider/Cohere.py

@@ -1,33 +1,12 @@
-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
 from webscout.AIutel import AwesomePrompts, sanitize_stream
 from webscout.AIbase import  Provider, AsyncProvider
-from Helpingai_T2 import Perplexity
 from webscout import exceptions
-from typing import Any, AsyncGenerator, Dict
-import logging
-import httpx
+
+
 #-----------------------------------------------Cohere--------------------------------------------
 class Cohere(Provider):
     def __init__(

webscout/Provider/DARKAI.py

@@ -1,4 +1,3 @@
-import time
 import json
 from typing import Any, Dict, Optional
 from webscout.AIutel import Optimizers

webscout/Provider/Deepinfra.py

@@ -1,26 +1,12 @@
-import time
-import uuid
-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 ..AIutel import Optimizers
 from ..AIutel import Conversation
 from ..AIutel import AwesomePrompts, sanitize_stream
 from ..AIbase import Provider, AsyncProvider
 from webscout import exceptions
 from typing import Any, AsyncGenerator
-import logging
 import httpx
 
 class DeepInfra(Provider):