webscout 5.1__py3-none-any.whl → 5.3__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/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__ = '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)