webscout 4.3__py3-none-any.whl → 4.5__py3-none-any.whl

webscout/GoogleS.py

@@ -0,0 +1,342 @@
+import os
+import random
+import sys
+import time
+import ssl
+
+if sys.version_info[0] > 2:
+    from http.cookiejar import LWPCookieJar
+    from urllib.request import Request, urlopen
+    from urllib.parse import quote_plus, urlparse, parse_qs
+else:
+    from cookielib import LWPCookieJar
+    from urllib import quote_plus
+    from urllib2 import Request, urlopen
+    from urlparse import urlparse, parse_qs
+
+try:
+    from bs4 import BeautifulSoup
+    is_bs4 = True
+except ImportError:
+    from BeautifulSoup import BeautifulSoup  # type: ignore
+    is_bs4 = False
+
+__all__ = [
+
+    # Main search function.
+    'search',
+
+    # Shortcut for "get lucky" search.
+    'lucky',
+
+    # Miscellaneous utility functions.
+    'get_random_user_agent', 'get_tbs',
+]
+
+# URL templates to make Google searches.
+url_home = "https://www.google.%(tld)s/"
+url_search = "https://www.google.%(tld)s/search?hl=%(lang)s&q=%(query)s&" \
+             "btnG=Google+Search&tbs=%(tbs)s&safe=%(safe)s&" \
+             "cr=%(country)s"
+url_next_page = "https://www.google.%(tld)s/search?hl=%(lang)s&q=%(query)s&" \
+                "start=%(start)d&tbs=%(tbs)s&safe=%(safe)s&" \
+                "cr=%(country)s"
+url_search_num = "https://www.google.%(tld)s/search?hl=%(lang)s&q=%(query)s&" \
+                 "num=%(num)d&btnG=Google+Search&tbs=%(tbs)s&safe=%(safe)s&" \
+                 "cr=%(country)s"
+url_next_page_num = "https://www.google.%(tld)s/search?hl=%(lang)s&" \
+                    "q=%(query)s&num=%(num)d&start=%(start)d&tbs=%(tbs)s&" \
+                    "safe=%(safe)s&cr=%(country)s"
+url_parameters = (
+    'hl', 'q', 'num', 'btnG', 'start', 'tbs', 'safe', 'cr')
+
+# Cookie jar. Stored at the user's home folder.
+# If the cookie jar is inaccessible, the errors are ignored.
+home_folder = os.getenv('HOME')
+if not home_folder:
+    home_folder = os.getenv('USERHOME')
+    if not home_folder:
+        home_folder = '.'   # Use the current folder on error.
+cookie_jar = LWPCookieJar(os.path.join(home_folder, '.google-cookie'))
+try:
+    cookie_jar.load()
+except Exception:
+    pass
+
+# Default user agent, unless instructed by the user to change it.
+USER_AGENT = 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0)'
+
+try:
+    install_folder = os.path.abspath(os.path.split(__file__)[0])
+    try:
+        user_agents_file = os.path.join(install_folder, 'user_agents.txt.gz')
+        import gzip
+        fp = gzip.open(user_agents_file, 'rb')
+        try:
+            user_agents_list = [_.strip() for _ in fp.readlines()]
+        finally:
+            fp.close()
+            del fp
+    except Exception:
+        user_agents_file = os.path.join(install_folder, 'user_agents.txt')
+        with open(user_agents_file) as fp:
+            user_agents_list = [_.strip() for _ in fp.readlines()]
+except Exception:
+    user_agents_list = [USER_AGENT]
+
+
+# Get a random user agent.
+def get_random_user_agent():
+    """
+    Get a random user agent string.
+
+    :rtype: str
+    :return: Random user agent string.
+    """
+    return random.choice(user_agents_list)
+
+
+# Helper function to format the tbs parameter.
+def get_tbs(from_date, to_date):
+    """
+    Helper function to format the tbs parameter.
+
+    :param datetime.date from_date: Python date object.
+    :param datetime.date to_date: Python date object.
+
+    :rtype: str
+    :return: Dates encoded in tbs format.
+    """
+    from_date = from_date.strftime('%m/%d/%Y')
+    to_date = to_date.strftime('%m/%d/%Y')
+    return 'cdr:1,cd_min:%(from_date)s,cd_max:%(to_date)s' % vars()
+
+
+# Request the given URL and return the response page, using the cookie jar.
+# If the cookie jar is inaccessible, the errors are ignored.
+def get_page(url, user_agent=None, verify_ssl=True):
+    """
+    Request the given URL and return the response page, using the cookie jar.
+
+    :param str url: URL to retrieve.
+    :param str user_agent: User agent for the HTTP requests.
+        Use None for the default.
+    :param bool verify_ssl: Verify the SSL certificate to prevent
+        traffic interception attacks. Defaults to True.
+
+    :rtype: str
+    :return: Web page retrieved for the given URL.
+
+    :raises IOError: An exception is raised on error.
+    :raises urllib2.URLError: An exception is raised on error.
+    :raises urllib2.HTTPError: An exception is raised on error.
+    """
+    if user_agent is None:
+        user_agent = USER_AGENT
+    request = Request(url)
+    request.add_header('User-Agent', user_agent)
+    cookie_jar.add_cookie_header(request)
+    if verify_ssl:
+        response = urlopen(request)
+    else:
+        context = ssl._create_unverified_context()
+        response = urlopen(request, context=context)
+    cookie_jar.extract_cookies(response, request)
+    html = response.read()
+    response.close()
+    try:
+        cookie_jar.save()
+    except Exception:
+        pass
+    return html
+
+
+# Filter links found in the Google result pages HTML code.
+# Returns None if the link doesn't yield a valid result.
+def filter_result(link):
+    try:
+
+        # Decode hidden URLs.
+        if link.startswith('/url?'):
+            o = urlparse(link, 'http')
+            link = parse_qs(o.query)['q'][0]
+
+        # Valid results are absolute URLs not pointing to a Google domain,
+        # like images.google.com or googleusercontent.com for example.
+        # TODO this could be improved!
+        o = urlparse(link, 'http')
+        if o.netloc and 'google' not in o.netloc:
+            return link
+
+    # On error, return None.
+    except Exception:
+        pass
+
+
+# Returns a generator that yields URLs.
+def search(query, tld='com', lang='en', tbs='0', safe='off', num=10, start=0,
+           stop=None, pause=2.0, country='', extra_params=None,
+           user_agent=None, verify_ssl=True):
+    """
+    Search the given query string using Google.
+
+    :param str query: Query string. Must NOT be url-encoded.
+    :param str tld: Top level domain.
+    :param str lang: Language.
+    :param str tbs: Time limits (i.e "qdr:h" => last hour,
+        "qdr:d" => last 24 hours, "qdr:m" => last month).
+    :param str safe: Safe search.
+    :param int num: Number of results per page.
+    :param int start: First result to retrieve.
+    :param int stop: Last result to retrieve.
+        Use None to keep searching forever.
+    :param float pause: Lapse to wait between HTTP requests.
+        A lapse too long will make the search slow, but a lapse too short may
+        cause Google to block your IP. Your mileage may vary!
+    :param str country: Country or region to focus the search on. Similar to
+        changing the TLD, but does not yield exactly the same results.
+        Only Google knows why...
+    :param dict extra_params: A dictionary of extra HTTP GET
+        parameters, which must be URL encoded. For example if you don't want
+        Google to filter similar results you can set the extra_params to
+        {'filter': '0'} which will append '&filter=0' to every query.
+    :param str user_agent: User agent for the HTTP requests.
+        Use None for the default.
+    :param bool verify_ssl: Verify the SSL certificate to prevent
+        traffic interception attacks. Defaults to True.
+
+    :rtype: generator of str
+    :return: Generator (iterator) that yields found URLs.
+        If the stop parameter is None the iterator will loop forever.
+    """
+    # Set of hashes for the results found.
+    # This is used to avoid repeated results.
+    hashes = set()
+
+    # Count the number of links yielded.
+    count = 0
+
+    # Prepare the search string.
+    query = quote_plus(query)
+
+    # If no extra_params is given, create an empty dictionary.
+    # We should avoid using an empty dictionary as a default value
+    # in a function parameter in Python.
+    if not extra_params:
+        extra_params = {}
+
+    # Check extra_params for overlapping.
+    for builtin_param in url_parameters:
+        if builtin_param in extra_params.keys():
+            raise ValueError(
+                'GET parameter "%s" is overlapping with \
+                the built-in GET parameter',
+                builtin_param
+            )
+
+    # Grab the cookie from the home page.
+    get_page(url_home % vars(), user_agent, verify_ssl)
+
+    # Prepare the URL of the first request.
+    if start:
+        if num == 10:
+            url = url_next_page % vars()
+        else:
+            url = url_next_page_num % vars()
+    else:
+        if num == 10:
+            url = url_search % vars()
+        else:
+            url = url_search_num % vars()
+
+    # Loop until we reach the maximum result, if any (otherwise, loop forever).
+    while not stop or count < stop:
+
+        # Remeber last count to detect the end of results.
+        last_count = count
+
+        # Append extra GET parameters to the URL.
+        # This is done on every iteration because we're
+        # rebuilding the entire URL at the end of this loop.
+        for k, v in extra_params.items():
+            k = quote_plus(k)
+            v = quote_plus(v)
+            url = url + ('&%s=%s' % (k, v))
+
+        # Sleep between requests.
+        # Keeps Google from banning you for making too many requests.
+        time.sleep(pause)
+
+        # Request the Google Search results page.
+        html = get_page(url, user_agent, verify_ssl)
+
+        # Parse the response and get every anchored URL.
+        if is_bs4:
+            soup = BeautifulSoup(html, 'html.parser')
+        else:
+            soup = BeautifulSoup(html)
+        try:
+            anchors = soup.find(id='search').findAll('a')
+            # Sometimes (depending on the User-agent) there is
+            # no id "search" in html response...
+        except AttributeError:
+            # Remove links of the top bar.
+            gbar = soup.find(id='gbar')
+            if gbar:
+                gbar.clear()
+            anchors = soup.findAll('a')
+
+        # Process every anchored URL.
+        for a in anchors:
+
+            # Get the URL from the anchor tag.
+            try:
+                link = a['href']
+            except KeyError:
+                continue
+
+            # Filter invalid links and links pointing to Google itself.
+            link = filter_result(link)
+            if not link:
+                continue
+
+            # Discard repeated results.
+            h = hash(link)
+            if h in hashes:
+                continue
+            hashes.add(h)
+
+            # Yield the result.
+            yield link
+
+            # Increase the results counter.
+            # If we reached the limit, stop.
+            count += 1
+            if stop and count >= stop:
+                return
+
+        # End if there are no more results.
+        # XXX TODO review this logic, not sure if this is still true!
+        if last_count == count:
+            break
+
+        # Prepare the URL for the next request.
+        start += num
+        if num == 10:
+            url = url_next_page % vars()
+        else:
+            url = url_next_page_num % vars()
+
+
+# Shortcut to single-item search.
+# Evaluates the iterator to return the single URL as a string.
+def lucky(*args, **kwargs):
+    """
+    Shortcut to single-item search.
+
+    Same arguments as the main search function, but the return value changes.
+
+    :rtype: str
+    :return: URL found by Google.
+    """
+    return next(search(*args, **kwargs))

webscout/Provider/Andi.py

@@ -0,0 +1,275 @@
+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
+from webscout import WEBS
+from rich import print
+
+class AndiSearch(Provider):
+    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,
+    ):
+        """Instantiates AndiSearch
+
+        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.
+        """
+        self.session = requests.Session()
+        self.is_conversation = is_conversation
+        self.max_tokens_to_sample = max_tokens
+        self.chat_endpoint = "https://write.andisearch.com/v1/write_streaming"
+        self.stream_chunk_size = 64
+        self.timeout = timeout
+        self.last_response = {}
+        self.headers = {
+            "accept": "text/event-stream",
+            "accept-encoding": "gzip, deflate, br, zstd",
+            "accept-language": "en-US,en;q=0.9,en-IN;q=0.8",
+            "andi-auth-key": "andi-summarizer",
+            "andi-origin": "x-andi-origin",
+            "authorization": str(uuid4()),
+            "content-type": "application/json",
+            "dnt": "1",
+            "origin": "https://andisearch.com",
+            "priority": "u=1, i",
+            "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": "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",
+            "x-amz-date": "20240730T031106Z",
+            "x-amz-security-token": str(uuid4()),
+        }
+
+        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:
+        """Chat with AI
+
+        Args:
+            prompt (str): Prompt to be send.
+            stream (bool, optional): Flag for streaming response. Defaults to False.
+            raw (bool, optional): Stream back raw response as received. 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:
+           dict : {}
+        ```json
+        {
+            "id": "chatcmpl-TaREJpBZsRVQFRFic1wIA7Q7XfnaD",
+            "object": "chat.completion",
+            "created": 1704623244,
+            "model": "gpt-3.5-turbo",
+            "usage": {
+                "prompt_tokens": 0,
+                "completion_tokens": 0,
+                "total_tokens": 0
+                },
+            "choices": [
+                {
+                    "message": {
+                        "role": "assistant",
+                        "content": "Hello! How can I assist you today?"
+                },
+                "finish_reason": "stop",
+                "index": 0
+                }
+            ]
+        }
+        ```
+        """
+        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}"
+                )
+
+        # Initialize the webscout instance
+        webs = WEBS()
+
+        # Fetch search results
+        search_query = prompt
+        search_results = webs.text(search_query, max_results=7)
+
+        # Format the search results into the required serp payload structure
+        serp_payload = {
+            "query": search_query,
+            "serp": {
+                "results_type": "Search",
+                "answer": "",
+                "type": "navigation",
+                "title": "",
+                "description": "",
+                "image": "",
+                "link": "",
+                "source": "liftndrift.com",
+                "engine": "andi-b",
+                "results": [
+                    {
+                        "title": result["title"],
+                        "link": result["href"],
+                        "desc": result["body"],
+                        "image": "",  
+                        "type": "website",
+                        "source": result["href"].split("//")[1].split("/")[0]  # Extract the domain name
+                    }
+                    for result in search_results
+                ]
+            }
+        }
+        self.session.headers.update(self.headers)
+        payload = serp_payload
+
+        def for_stream():
+            response = self.session.post(
+                self.chat_endpoint, 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 value in response.iter_lines(
+                decode_unicode=True,
+                chunk_size=self.stream_chunk_size,
+                delimiter="\n",
+            ):
+                try:
+                    if bool(value):
+                        streaming_text += value + ("\n" if stream else "")
+                        resp = dict(text=streaming_text)
+                        self.last_response.update(resp)
+                        yield value if raw else resp
+                except json.decoder.JSONDecodeError:
+                    pass
+            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:
+        """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
+        """
+
+        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:
+        """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"]

webscout/Provider/__init__.py

@@ -38,6 +38,7 @@ from .Geminipro import GEMINIPRO
 from .Geminiflash import GEMINIFLASH
 from .OLLAMA import OLLAMA
 from .FreeGemini import FreeGemini
+from .Andi import AndiSearch
 __all__ = [
     'ThinkAnyAI',
     'Xjai',
@@ -78,7 +79,8 @@ __all__ = [
     'GEMINIPRO',
     'GEMINIFLASH',
     'OLLAMA',
-    'FreeGemini'
+    'FreeGemini',
+    'AndiSearch'
 
 
 ]

webscout/__init__.py

@@ -5,16 +5,16 @@ from .DWEBS import *
 from .transcriber import transcriber
 from .voice import play_audio
 from .websx_search import WEBSX
-
 from .LLM import VLM, LLM
 from .YTdownloader import *
-# from .Local import *
+
 import g4f
 from .YTdownloader import *
 from .Provider import *
 from .Extra import gguf
 from .Extra import autollama
 from .Extra import weather_ascii, weather
+from .Agents import *
 __repo__ = "https://github.com/OE-LUCIFER/Webscout"
 
 webai = [
@@ -44,7 +44,8 @@ webai = [
    "vtlchat",
    "geminiflash",
    "geminipro",
-   "ollama"
+   "ollama",
+   "andi",
 ]
 
 gpt4free_providers = [
@@ -58,12 +59,15 @@ __all__ = [
    "WEBS",
    "AsyncWEBS",
    "__version__",
-   "DeepWEBS",
+   "DWEBS",
    "transcriber",
    "play_audio",
    "TempMailClient", 
    "TemporaryPhoneNumber",
    "LLM",
+   "YTdownloader",
+   "WEBSX",
+   "VLM",
    # Localai models and utilities 
    # "Model",
    # "Thread",