pytrends-modern 0.1.1__tar.gz → 0.1.2__tar.gz

{pytrends_modern-0.1.1/pytrends_modern.egg-info → pytrends_modern-0.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pytrends-modern
-Version: 0.1.1
+Version: 0.1.2
 Summary: Modern Google Trends API - Combining the best of pytrends, with RSS feeds, Selenium scraping, and enhanced features
 Author: pytrends-modern contributors
 License: MIT
@@ -389,6 +389,44 @@ This project builds upon and combines features from:
 - CLI interface
 - Multiple export formats
 
+## 📌 Important Notes
+
+### Google API Changes
+
+Google has deprecated several trending search API endpoints. **pytrends-modern provides two working alternatives:**
+
+#### Option 1: Fast RSS Feed (Recommended for most use cases)
+```python
+from pytrends_modern import TrendsRSS
+
+rss = TrendsRSS()
+trends = rss.get_trends(geo='US')  # ~0.7s, returns 10 trends with images/articles
+```
+**Pros:** Lightning fast, includes rich media, no browser needed  
+**Cons:** Limited to 10 trends, no filtering options
+
+#### Option 2: Selenium Web Scraper (For complete data)
+```python
+from pytrends_modern import TrendsScraper
+
+scraper = TrendsScraper(headless=True)
+df = scraper.trending_searches(geo='US', hours=24)  # ~15s, returns 400+ trends
+scraper.close()
+```
+**Pros:** Complete data (400+ trends), supports categories/filters  
+**Cons:** Slower, requires Chrome browser
+
+### Working Features
+✅ All core API methods work perfectly:
+- `interest_over_time()` - Historical search trends
+- `interest_by_region()` - Geographic distribution  
+- `related_queries()` / `related_topics()` - Related searches
+- `suggestions()` - Keyword suggestions
+- And more!
+
+✅ RSS feeds for 125+ countries  
+✅ Selenium scraper for comprehensive trending data
+
 ## ⚠️ Disclaimer
 
 This is an unofficial library and is not affiliated with or endorsed by Google. Use responsibly and in accordance with Google's Terms of Service.

{pytrends_modern-0.1.1 → pytrends_modern-0.1.2}/README.md

@@ -342,6 +342,44 @@ This project builds upon and combines features from:
 - CLI interface
 - Multiple export formats
 
+## 📌 Important Notes
+
+### Google API Changes
+
+Google has deprecated several trending search API endpoints. **pytrends-modern provides two working alternatives:**
+
+#### Option 1: Fast RSS Feed (Recommended for most use cases)
+```python
+from pytrends_modern import TrendsRSS
+
+rss = TrendsRSS()
+trends = rss.get_trends(geo='US')  # ~0.7s, returns 10 trends with images/articles
+```
+**Pros:** Lightning fast, includes rich media, no browser needed  
+**Cons:** Limited to 10 trends, no filtering options
+
+#### Option 2: Selenium Web Scraper (For complete data)
+```python
+from pytrends_modern import TrendsScraper
+
+scraper = TrendsScraper(headless=True)
+df = scraper.trending_searches(geo='US', hours=24)  # ~15s, returns 400+ trends
+scraper.close()
+```
+**Pros:** Complete data (400+ trends), supports categories/filters  
+**Cons:** Slower, requires Chrome browser
+
+### Working Features
+✅ All core API methods work perfectly:
+- `interest_over_time()` - Historical search trends
+- `interest_by_region()` - Geographic distribution  
+- `related_queries()` / `related_topics()` - Related searches
+- `suggestions()` - Keyword suggestions
+- And more!
+
+✅ RSS feeds for 125+ countries  
+✅ Selenium scraper for comprehensive trending data
+
 ## ⚠️ Disclaimer
 
 This is an unofficial library and is not affiliated with or endorsed by Google. Use responsibly and in accordance with Google's Terms of Service.

{pytrends_modern-0.1.1 → pytrends_modern-0.1.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "pytrends-modern"
-version = "0.1.1"
+version = "0.1.2"
 description = "Modern Google Trends API - Combining the best of pytrends, with RSS feeds, Selenium scraping, and enhanced features"
 readme = "README.md"
 requires-python = ">=3.8"
@@ -92,3 +92,8 @@ python_files = ["test_*.py"]
 python_classes = ["Test*"]
 python_functions = ["test_*"]
 addopts = "-v --cov=pytrends_modern --cov-report=term-missing"
+
+[tool.uv.workspace]
+members = [
+    "test_space",
+]

{pytrends_modern-0.1.1 → pytrends_modern-0.1.2}/pytrends_modern/__init__.py

@@ -8,6 +8,7 @@ __license__ = "MIT"
 
 from pytrends_modern.request import TrendReq
 from pytrends_modern.rss import TrendsRSS
+from pytrends_modern.scraper import TrendsScraper
 from pytrends_modern.exceptions import (
     TooManyRequestsError,
     ResponseError,
@@ -19,6 +20,7 @@ from pytrends_modern.exceptions import (
 __all__ = [
     "TrendReq",
     "TrendsRSS",
+    "TrendsScraper",
     "TooManyRequestsError",
     "ResponseError",
     "InvalidParameterError",

{pytrends_modern-0.1.1 → pytrends_modern-0.1.2}/pytrends_modern/request.py

@@ -428,7 +428,7 @@ class TrendReq:
 
         # Add isPartial column
         if "isPartial" in df:
-            df = df.fillna(False)
+            df["isPartial"] = df["isPartial"].where(df["isPartial"].notna(), False)
             is_partial_df = df["isPartial"].apply(
                 lambda x: pd.Series(str(x).replace("[", "").replace("]", "").split(","))
             )
@@ -716,11 +716,6 @@ class TrendReq:
 
         Returns:
             DataFrame of real-time trending searches with entity names and titles
-
-        Example:
-            >>> pytrends = TrendReq()
-            >>> df = pytrends.realtime_trending_searches(pn='US', count=50)
-            >>> print(df.head())
         """
         # Validate count
         ri_value = min(count, 300)

{pytrends_modern-0.1.1 → pytrends_modern-0.1.2}/pytrends_modern/rss.py

@@ -36,7 +36,7 @@ class TrendsRSS:
         ...     print(f"{trend['title']}: {trend['traffic']}")
     """
 
-    RSS_URL_TEMPLATE = "https://trends.google.com/trends/trendingsearches/daily/rss?geo={geo}"
+    RSS_URL_TEMPLATE = "https://trends.google.com/trending/rss?geo={geo}"
 
     def __init__(self, timeout: int = 10):
         """
@@ -123,7 +123,7 @@ class TrendsRSS:
                     trend_data["pub_date_datetime"] = None
 
             # Traffic volume (from ht:approx_traffic namespace)
-            traffic_elem = item.find(".//{http://www.google.com/trends/hottrends}approx_traffic")
+            traffic_elem = item.find(".//{https://trends.google.com/trending/rss}approx_traffic")
             if traffic_elem is not None and traffic_elem.text:
                 # Remove '+' and ',' from traffic string
                 traffic_str = traffic_elem.text.replace("+", "").replace(",", "")
@@ -136,12 +136,12 @@ class TrendsRSS:
 
             # Image
             if include_images:
-                picture_elem = item.find(".//{http://www.google.com/trends/hottrends}picture")
+                picture_elem = item.find(".//{https://trends.google.com/trending/rss}picture")
                 trend_data["picture"] = picture_elem.text if picture_elem is not None else None
 
             # News articles
             if include_articles:
-                news_items = item.findall(".//{http://www.google.com/trends/hottrends}news_item")
+                news_items = item.findall(".//{https://trends.google.com/trending/rss}news_item")
                 articles = []
 
                 for news_item in news_items[:max_articles_per_trend]:
@@ -149,25 +149,25 @@ class TrendsRSS:
 
                     # Article title
                     title_elem = news_item.find(
-                        ".//{http://www.google.com/trends/hottrends}news_item_title"
+                        ".//{https://trends.google.com/trending/rss}news_item_title"
                     )
                     article["title"] = title_elem.text if title_elem is not None else None
 
                     # Article URL
                     url_elem = news_item.find(
-                        ".//{http://www.google.com/trends/hottrends}news_item_url"
+                        ".//{https://trends.google.com/trending/rss}news_item_url"
                     )
                     article["url"] = url_elem.text if url_elem is not None else None
 
                     # Article snippet
                     snippet_elem = news_item.find(
-                        ".//{http://www.google.com/trends/hottrends}news_item_snippet"
+                        ".//{https://trends.google.com/trending/rss}news_item_snippet"
                     )
                     article["snippet"] = snippet_elem.text if snippet_elem is not None else None
 
                     # Article source
                     source_elem = news_item.find(
-                        ".//{http://www.google.com/trends/hottrends}news_item_source"
+                        ".//{https://trends.google.com/trending/rss}news_item_source"
                     )
                     article["source"] = source_elem.text if source_elem is not None else None
 

pytrends_modern-0.1.2/pytrends_modern/scraper.py

@@ -0,0 +1,292 @@
+"""
+Selenium-based scraper for Google Trends trending searches
+Uses browser automation to download CSV data when API endpoints are unavailable
+"""
+
+import os
+import time
+from typing import Optional, Union, List, Dict
+from pathlib import Path
+import warnings
+
+import pandas as pd
+from selenium import webdriver
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.chrome.options import Options
+from selenium.common.exceptions import (
+    WebDriverException,
+    TimeoutException,
+    NoSuchElementException,
+)
+
+from . import exceptions
+
+
+class TrendsScraper:
+    """
+    Selenium-based scraper for Google Trends when API endpoints are unavailable
+
+    This provides an alternative to deprecated API methods like trending_searches()
+    by using browser automation to download actual trending data.
+    """
+
+    def __init__(self, headless: bool = True, download_dir: Optional[str] = None):
+        """
+        Initialize the scraper
+
+        Args:
+            headless: Run browser in headless mode
+            download_dir: Directory for downloads (default: temp directory)
+        """
+        self.headless = headless
+
+        if download_dir is None:
+            import tempfile
+
+            self.download_dir = tempfile.mkdtemp(prefix="pytrends_")
+        else:
+            self.download_dir = os.path.abspath(download_dir)
+            os.makedirs(self.download_dir, exist_ok=True)
+
+        self.driver = None
+
+    def _init_driver(self):
+        """Initialize Selenium WebDriver"""
+        if self.driver is not None:
+            return
+
+        chrome_options = Options()
+        prefs = {
+            "download.default_directory": self.download_dir,
+            "download.prompt_for_download": False,
+            "download.directory_upgrade": True,
+            "safebrowsing.enabled": True,
+        }
+        chrome_options.add_experimental_option("prefs", prefs)
+
+        if self.headless:
+            chrome_options.add_argument("--headless=new")
+            chrome_options.add_argument("--disable-gpu")
+            chrome_options.add_argument("--no-sandbox")
+            chrome_options.add_argument("--disable-dev-shm-usage")
+
+        chrome_options.add_argument("--log-level=3")
+        chrome_options.add_experimental_option("excludeSwitches", ["enable-logging"])
+
+        try:
+            self.driver = webdriver.Chrome(options=chrome_options)
+        except WebDriverException as e:
+            raise exceptions.BrowserError(
+                f"Failed to start Chrome browser: {e}\n\n"
+                "Please ensure:\n"
+                "1. Chrome/Chromium browser is installed\n"
+                "2. ChromeDriver is compatible with your Chrome version\n"
+                "3. You have proper permissions\n"
+            )
+
+    def trending_searches(
+        self,
+        geo: str = "US",
+        hours: int = 24,
+        category: str = "all",
+        active_only: bool = False,
+        sort_by: str = "relevance",
+        return_df: bool = True,
+    ) -> Union[pd.DataFrame, str]:
+        """
+        Get trending searches by scraping Google Trends
+
+        Args:
+            geo: Country code (US, GB, IN, etc.)
+            hours: Time period in hours (4, 24, 48, 168)
+            category: Category filter (all, sports, entertainment, etc.)
+            active_only: Show only active trends
+            sort_by: Sort criteria (relevance, title, volume, recency)
+            return_df: Return DataFrame (True) or CSV path (False)
+
+        Returns:
+            DataFrame of trending searches or path to CSV file
+
+        Raises:
+            BrowserError: If browser automation fails
+            DownloadError: If download fails
+
+        Example:
+            >>> scraper = TrendsScraper()
+            >>> df = scraper.trending_searches(geo='US', hours=24)
+            >>> print(df.head())
+        """
+        self._init_driver()
+
+        # Get existing files before download
+        existing_files = set(f for f in os.listdir(self.download_dir) if f.endswith(".csv"))
+
+        try:
+            # Build URL with parameters
+            url = f"https://trends.google.com/trending?geo={geo}"
+
+            if hours != 24:
+                url += f"&hours={hours}"
+
+            # Add category if not 'all'
+            categories = {
+                "all": "",
+                "business": "b",
+                "entertainment": "e",
+                "health": "m",
+                "science": "t",
+                "sports": "s",
+                "top": "h",
+            }
+            cat_code = categories.get(category.lower(), "")
+            if cat_code:
+                url += f"&cat={cat_code}"
+
+            # Navigate to page
+            self.driver.get(url)
+
+            # Wait for page to load by checking for Export button
+            WebDriverWait(self.driver, 10).until(
+                EC.presence_of_element_located((By.XPATH, "//button[contains(., 'Export')]"))
+            )
+
+            # Click Export button
+            try:
+                export_button = WebDriverWait(self.driver, 10).until(
+                    EC.element_to_be_clickable((By.XPATH, "//button[contains(., 'Export')]"))
+                )
+                export_button.click()
+                time.sleep(1)
+
+                # Click Download CSV from the menu
+                download_csv = WebDriverWait(self.driver, 5).until(
+                    EC.presence_of_element_located((By.CSS_SELECTOR, 'li[data-action="csv"]'))
+                )
+                self.driver.execute_script("arguments[0].click();", download_csv)
+                time.sleep(1)
+
+            except Exception as e:
+                raise exceptions.DownloadError(f"Could not find or click Export/CSV button: {e}")
+
+            # Wait for file download
+            max_wait = 30
+            waited = 0
+            downloaded_file = None
+
+            while waited < max_wait:
+                current_files = set(f for f in os.listdir(self.download_dir) if f.endswith(".csv"))
+                new_files = current_files - existing_files
+
+                if new_files:
+                    # Get the most recently created file
+                    newest = max(
+                        new_files,
+                        key=lambda f: os.path.getctime(os.path.join(self.download_dir, f)),
+                    )
+                    downloaded_file = os.path.join(self.download_dir, newest)
+
+                    # Verify file is complete (size > 0 and not growing)
+                    size1 = os.path.getsize(downloaded_file)
+                    time.sleep(0.5)
+                    size2 = os.path.getsize(downloaded_file)
+
+                    if size1 > 0 and size1 == size2:
+                        break
+
+                time.sleep(0.5)
+                waited += 0.5
+
+            if not downloaded_file:
+                raise exceptions.DownloadError(
+                    f"Download timeout after {max_wait}s. No CSV file appeared in {self.download_dir}"
+                )
+
+            # Return DataFrame or path
+            if return_df:
+                df = pd.read_csv(downloaded_file)
+                # Clean up file
+                try:
+                    os.remove(downloaded_file)
+                except:
+                    pass
+                return df
+            else:
+                return downloaded_file
+
+        except Exception as e:
+            if isinstance(e, (exceptions.BrowserError, exceptions.DownloadError)):
+                raise
+            raise exceptions.DownloadError(f"Scraping failed: {e}")
+
+    def today_searches(self, geo: str = "US", return_df: bool = True) -> Union[pd.DataFrame, str]:
+        """
+        Get today's trending searches (shortcut for 24 hour trends)
+
+        Args:
+            geo: Country code (US, GB, IN, etc.)
+            return_df: Return DataFrame (True) or CSV path (False)
+
+        Returns:
+            DataFrame of today's trending searches
+
+        Example:
+            >>> scraper = TrendsScraper()
+            >>> df = scraper.today_searches(geo='US')
+        """
+        return self.trending_searches(geo=geo, hours=24, return_df=return_df)
+
+    def realtime_trending_searches(
+        self, geo: str = "US", hours: int = 4, return_df: bool = True
+    ) -> Union[pd.DataFrame, str]:
+        """
+        Get real-time trending searches (4 hour window)
+
+        Args:
+            geo: Country code (US, GB, IN, etc.)
+            hours: Time period (default 4 for real-time)
+            return_df: Return DataFrame (True) or CSV path (False)
+
+        Returns:
+            DataFrame of real-time trending searches
+
+        Example:
+            >>> scraper = TrendsScraper()
+            >>> df = scraper.realtime_trending_searches(geo='US')
+        """
+        return self.trending_searches(geo=geo, hours=hours, return_df=return_df)
+
+    def __enter__(self):
+        """Context manager support"""
+        return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        """Context manager cleanup"""
+        self.close()
+
+    def close(self):
+        # Ignore errors during shutdown
+        """Close browser and cleanup"""
+        if self.driver:
+            try:
+                self.driver.quit()
+            except:
+                pass
+            self.driver = None
+
+        # Cleanup temp directory if we created it
+        if self.download_dir and "/tmp/" in self.download_dir:
+            import shutil
+
+            try:
+                shutil.rmtree(self.download_dir)
+            except:
+                pass
+
+    def __del__(self):
+        """Cleanup on deletion"""
+        try:
+            self.close()
+        except:
+            pass

{pytrends_modern-0.1.1 → pytrends_modern-0.1.2/pytrends_modern.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pytrends-modern
-Version: 0.1.1
+Version: 0.1.2
 Summary: Modern Google Trends API - Combining the best of pytrends, with RSS feeds, Selenium scraping, and enhanced features
 Author: pytrends-modern contributors
 License: MIT
@@ -389,6 +389,44 @@ This project builds upon and combines features from:
 - CLI interface
 - Multiple export formats
 
+## 📌 Important Notes
+
+### Google API Changes
+
+Google has deprecated several trending search API endpoints. **pytrends-modern provides two working alternatives:**
+
+#### Option 1: Fast RSS Feed (Recommended for most use cases)
+```python
+from pytrends_modern import TrendsRSS
+
+rss = TrendsRSS()
+trends = rss.get_trends(geo='US')  # ~0.7s, returns 10 trends with images/articles
+```
+**Pros:** Lightning fast, includes rich media, no browser needed  
+**Cons:** Limited to 10 trends, no filtering options
+
+#### Option 2: Selenium Web Scraper (For complete data)
+```python
+from pytrends_modern import TrendsScraper
+
+scraper = TrendsScraper(headless=True)
+df = scraper.trending_searches(geo='US', hours=24)  # ~15s, returns 400+ trends
+scraper.close()
+```
+**Pros:** Complete data (400+ trends), supports categories/filters  
+**Cons:** Slower, requires Chrome browser
+
+### Working Features
+✅ All core API methods work perfectly:
+- `interest_over_time()` - Historical search trends
+- `interest_by_region()` - Geographic distribution  
+- `related_queries()` / `related_topics()` - Related searches
+- `suggestions()` - Keyword suggestions
+- And more!
+
+✅ RSS feeds for 125+ countries  
+✅ Selenium scraper for comprehensive trending data
+
 ## ⚠️ Disclaimer
 
 This is an unofficial library and is not affiliated with or endorsed by Google. Use responsibly and in accordance with Google's Terms of Service.

{pytrends_modern-0.1.1 → pytrends_modern-0.1.2}/pytrends_modern.egg-info/SOURCES.txt

@@ -11,6 +11,7 @@ pytrends_modern/exceptions.py
 pytrends_modern/py.typed
 pytrends_modern/request.py
 pytrends_modern/rss.py
+pytrends_modern/scraper.py
 pytrends_modern/utils.py
 pytrends_modern.egg-info/PKG-INFO
 pytrends_modern.egg-info/SOURCES.txt