Update patent_downloader.py

patent_downloader.py

@@ -22,7 +22,7 @@ import chromedriver_autoinstaller
 class PatentDownloader:
     url = "https://patents.google.com"
 
-    def __init__(self, verbose: bool = False):
+    def __init__(self, verbose: bool = True):
         """
         Initialize the Patent Downloader.
         Parameters:
@@ -36,12 +36,8 @@ class PatentDownloader:
     def install_chrome(self) -> str:
         """
         Download and install Google Chrome dynamically if not already installed.
-        Returns:
-        -------
-        str: Path to the Chrome binary.
         """
         chrome_path = "/usr/bin/google-chrome"
-
         if not shutil.which("google-chrome"):
             print("Downloading and installing Google Chrome...")
             subprocess.run(
@@ -90,6 +86,7 @@ class PatentDownloader:
         driver = webdriver.Chrome(service=service, options=chrome_options)
 
         file_path = os.path.join(output_path, f"{patent}.pdf")
+        pdf_link = None
 
         try:
             print(f"Navigating to Google Patents...")
@@ -103,19 +100,29 @@ class PatentDownloader:
             search_input.send_keys(Keys.RETURN)
 
             print("Waiting for the 'Download PDF' button...")
-            pdf_button_xpath = "//a[contains(text(),'Download PDF')]"
-            WebDriverWait(driver, 30).until(EC.presence_of_element_located((By.XPATH, pdf_button_xpath)))
-            pdf_link_element = driver.find_element(By.XPATH, pdf_button_xpath)
+            time.sleep(waiting_time)  # Allow full load
+            page_source = driver.page_source
+
+            # Log the page source for debugging
+            with open("page_source.html", "w", encoding="utf-8") as f:
+                f.write(page_source)
+            print("Page source saved as 'page_source.html' for debugging.")
+
+            soup = BeautifulSoup(page_source, "html.parser")
+
+            # First, look for the 'Download PDF' link explicitly
+            pdf_link = self.get_pdf_link(soup)
+
+            if not pdf_link:
+                raise FileNotFoundError("Could not find a valid PDF link.")
 
-            # Extract the PDF link
-            pdf_link = pdf_link_element.get_attribute("href")
-            print(f"PDF link found: {pdf_link}")
+            print(f"PDF link extracted: {pdf_link}")
 
             # Download and validate the PDF
             self.download_and_validate_pdf(pdf_link, file_path)
 
         except Exception as e:
-            print(f"An error occurred: {e}")
+            print(f"Error: {e}")
             raise FileNotFoundError("Could not find a valid PDF link.")
         finally:
             driver.quit()
@@ -137,6 +144,26 @@ class PatentDownloader:
             print(f"Downloading patent: {patent}")
             self.get_pdf(patent, output_path, waiting_time)
 
+    @staticmethod
+    def get_pdf_link(soup: BeautifulSoup) -> Optional[str]:
+        """
+        Extract the PDF link from the parsed HTML.
+        """
+        # Search explicitly for Download PDF button
+        download_button = soup.find("a", string=re.compile("Download PDF", re.IGNORECASE))
+        if download_button and download_button.get("href"):
+            return download_button["href"]
+
+        # Fallback: Find any links containing 'patentimages.storage.googleapis.com'
+        pdf_links = [link['href'] for link in soup.find_all('a', href=True)
+                     if 'patentimages.storage.googleapis.com' in link['href']]
+        if pdf_links:
+            print(f"Fallback: Found PDF Link: {pdf_links[0]}")
+            return pdf_links[0]
+
+        print("No valid PDF link found in HTML.")
+        return None
+
     def download_and_validate_pdf(self, pdf_link: str, file_path: str):
         """
         Download the PDF and validate its integrity.