webscout 6.2b0__py3-none-any.whl → 6.3__py3-none-any.whl

webscout/DWEBS.py

@@ -1,179 +1,323 @@
-from bs4 import BeautifulSoup
-import requests
-from typing import Dict, List, Optional, Union
-from concurrent.futures import ThreadPoolExecutor, as_completed
-from urllib.parse import quote
-from termcolor import colored
-import time
-import random
-
-class GoogleS:
-    """
-    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,
-        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"
-        }
-        self.headers["Referer"] = "https://www.google.com/"
-        self.client = requests.Session()
-        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):
-        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:
-        """
-        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:
-            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: 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()
-        visible_text = soup.get_text(strip=True)
-        if max_characters:
-            visible_text = visible_text[:max_characters]
-        return visible_text
-
-    def search(
-        self,
-        query: str,
-        region: str = "us-en",
-        language: str = "en",
-        safe: str = "off",
-        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": query,
-                "num": 10,
-                "hl": language,
-                "start": start,
-                "safe": safe,
-                "gl": region,
-            }
-            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
-
-            for future in as_completed(futures):
-                try:
-                    resp_content = future.result()
-                    soup = BeautifulSoup(resp_content, 'lxml')  # Use lxml parser
-                    result_blocks = soup.find_all("div", class_="g")
-
-                    if not result_blocks:
-                        break
-
-                    # 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: {e}")  
-
-        return results
-
-
-if __name__ == "__main__":
-    from rich import print
-    searcher = GoogleS()
-    results = searcher.search("HelpingAI-9B", max_results=20, extract_text=False, max_text_length=200)
-    for result in results:
+from bs4 import BeautifulSoup
+import requests
+from typing import Dict, List, Optional, Union, Any
+from concurrent.futures import ThreadPoolExecutor, as_completed
+from urllib.parse import quote, urljoin
+from termcolor import colored
+import time
+import random
+import json
+import os
+from datetime import datetime, timedelta
+from functools import lru_cache
+import logging
+from tenacity import retry, stop_after_attempt, wait_exponential
+
+class GoogleS:
+    """
+    Enhanced Google Search class with support for web search, image search, and advanced filters.
+    """
+
+    SEARCH_TYPES = {
+        "web": "https://www.google.com/search",
+        "image": "https://www.google.com/images",
+        "news": "https://www.google.com/news",
+    }
+
+    def __init__(
+        self,
+        headers: Optional[Dict[str, str]] = None,
+        proxy: Optional[str] = None,
+        timeout: Optional[int] = 10,
+        max_workers: int = 20,
+        cache_dir: Optional[str] = None,
+        rate_limit: float = 0.01
+    ):
+        """
+        Initialize the GoogleS object with enhanced features.
+        
+        Args:
+            cache_dir: Directory to store search result cache
+            rate_limit: Minimum time between requests in seconds
+        """
+        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"
+        }
+        self.headers["Referer"] = "https://www.google.com/"
+        self.client = requests.Session()
+        self.client.headers.update(self.headers)
+        if proxy:
+            self.client.proxies.update({"http": proxy, "https": proxy})
+        self.timeout = timeout
+        self._executor = ThreadPoolExecutor(max_workers=max_workers)
+        self.cache_dir = cache_dir
+        if cache_dir and not os.path.exists(cache_dir):
+            os.makedirs(cache_dir)
+        self.last_request_time = 0
+        self.rate_limit = rate_limit
+        
+        # Setup logging
+        logging.basicConfig(level=logging.INFO)
+        self.logger = logging.getLogger(__name__)
+
+    def _respect_rate_limit(self):
+        """Ensure minimum time between requests"""
+        current_time = time.time()
+        time_since_last = current_time - self.last_request_time
+        if time_since_last < self.rate_limit:
+            time.sleep(self.rate_limit - time_since_last)
+        self.last_request_time = time.time()
+
+    @retry(stop=stop_after_attempt(3), wait=wait_exponential(multiplier=1, min=4, max=10))
+    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 with retry logic and rate limiting.
+        """
+        self._respect_rate_limit()
+        try:
+            resp = self.client.request(method, url, params=params, data=data, timeout=self.timeout)
+            resp.raise_for_status()
+            return resp.content
+        except requests.exceptions.RequestException as ex:
+            self.logger.error(f"Request failed: {url} - {str(ex)}")
+            raise
+
+    @lru_cache(maxsize=100)
+    def _cache_key(self, query: str, **kwargs) -> str:
+        """Generate a cache key from search parameters"""
+        cache_data = {'query': query, **kwargs}
+        return json.dumps(cache_data, sort_keys=True)
+
+    def _get_cached_results(self, cache_key: str) -> Optional[List[Dict[str, Any]]]:
+        """Retrieve cached results if they exist and are not expired"""
+        if not self.cache_dir:
+            return None
+        cache_file = os.path.join(self.cache_dir, f"{cache_key}.json")
+        if os.path.exists(cache_file):
+            with open(cache_file, 'r') as f:
+                cached_data = json.load(f)
+                if datetime.fromisoformat(cached_data['timestamp']) + timedelta(hours=24) > datetime.now():
+                    return cached_data['results']
+        return None
+
+    def _cache_results(self, cache_key: str, results: List[Dict[str, Any]]):
+        """Cache search results"""
+        if not self.cache_dir:
+            return
+        cache_file = os.path.join(self.cache_dir, f"{cache_key}.json")
+        with open(cache_file, 'w') as f:
+            json.dump({
+                'timestamp': datetime.now().isoformat(),
+                'results': results
+            }, f)
+
+    def search_images(
+        self,
+        query: str,
+        max_results: int = 10,
+        size: Optional[str] = None,  # large, medium, icon
+        color: Optional[str] = None,  # color, gray, transparent
+        type_filter: Optional[str] = None,  # face, photo, clipart, lineart
+        **kwargs
+    ) -> List[Dict[str, str]]:
+        """
+        Perform an image search and return results.
+        
+        Args:
+            size: Filter by image size
+            color: Filter by color
+            type_filter: Filter by image type
+        """
+        params = {
+            "q": query,
+            "tbm": "isch",
+            "num": max_results
+        }
+        
+        if size:
+            params["tbs"] = f"isz:{size}"
+        if color:
+            params["tbs"] = f"ic:{color}"
+        if type_filter:
+            params["tbs"] = f"itp:{type_filter}"
+
+        content = self._get_url("GET", self.SEARCH_TYPES["image"], params=params)
+        soup = BeautifulSoup(content, 'lxml')
+        
+        results = []
+        for img in soup.find_all("img", class_="rg_i"):
+            if len(results) >= max_results:
+                break
+            
+            img_data = {
+                "thumbnail": img.get("src", ""),
+                "title": img.get("alt", ""),
+                "type": "image"
+            }
+            
+            # Extract full resolution image URL if available
+            parent = img.parent
+            if parent and parent.get("href"):
+                img_data["full_url"] = urljoin("https://www.google.com", parent["href"])
+            
+            results.append(img_data)
+            
+        return results
+
+    def search(
+        self,
+        query: str,
+        region: str = "us-en",
+        language: str = "en",
+        safe: str = "off",
+        time_period: Optional[str] = None,
+        max_results: int = 10,
+        extract_text: bool = False,
+        max_text_length: Optional[int] = 100,
+        site: Optional[str] = None,  # Search within specific site
+        file_type: Optional[str] = None,  # Filter by file type
+        sort_by: str = "relevance",  # relevance, date
+        exclude_terms: Optional[List[str]] = None,  # Terms to exclude
+        exact_phrase: Optional[str] = None,  # Exact phrase match
+    ) -> List[Dict[str, Union[str, int]]]:
+        """
+        Enhanced search with additional filters and options.
+        
+        Args:
+            site: Limit search to specific website
+            file_type: Filter by file type (pdf, doc, etc.)
+            sort_by: Sort results by relevance or date
+            exclude_terms: List of terms to exclude from search
+            exact_phrase: Exact phrase to match
+        """
+        # Build advanced query
+        advanced_query = query
+        if site:
+            advanced_query += f" site:{site}"
+        if file_type:
+            advanced_query += f" filetype:{file_type}"
+        if exclude_terms:
+            advanced_query += " " + " ".join(f"-{term}" for term in exclude_terms)
+        if exact_phrase:
+            advanced_query = f'"{exact_phrase}"' + advanced_query
+
+        # Check cache first
+        cache_key = self._cache_key(advanced_query, region=region, language=language,
+                                  safe=safe, time_period=time_period, sort_by=sort_by)
+        cached_results = self._get_cached_results(cache_key)
+        if cached_results:
+            return cached_results[:max_results]
+
+        # Continue with regular search implementation...
+        results = []
+        futures = []
+        start = 0
+
+        while len(results) < max_results:
+            params = {
+                "q": advanced_query,
+                "num": 10,
+                "hl": language,
+                "start": start,
+                "safe": safe,
+                "gl": region,
+            }
+            if time_period:
+                params["tbs"] = f"qdr:{time_period}"
+
+            futures.append(self._executor.submit(self._get_url, "GET", self.SEARCH_TYPES["web"], params=params))
+            start += 10
+
+            for future in as_completed(futures):
+                try:
+                    resp_content = future.result()
+                    soup = BeautifulSoup(resp_content, 'lxml')  # Use lxml parser
+                    result_blocks = soup.find_all("div", class_="g")
+
+                    if not result_blocks:
+                        break
+
+                    # 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: {e}")  
+
+        # Cache results before returning
+        self._cache_results(cache_key, results)
+        return results
+
+    def get_search_suggestions(self, query: str) -> List[str]:
+        """Get search suggestions for a query"""
+        params = {
+            "client": "chrome",
+            "q": query
+        }
+        content = self._get_url("GET", "https://suggestqueries.google.com/complete/search",
+                               params=params)
+        suggestions = json.loads(content.decode('utf-8'))[1]
+        return suggestions
+
+    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()
+        visible_text = soup.get_text(strip=True)
+        if max_characters:
+            visible_text = visible_text[:max_characters]
+        return visible_text
+
+    def __enter__(self):
+        return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        self.client.close()
+        self._executor.shutdown()
+
+
+if __name__ == "__main__":
+    from rich import print
+    searcher = GoogleS()
+    results = searcher.search("HelpingAI-9B", max_results=200, extract_text=False, max_text_length=200)
+    for result in results:
         print(result)