Merge pull request #3624 from seleniumbase/cdp-mode-patch-43

CDP Mode: Patch 43

Author: mdmintz

examples/cdp_mode/ReadMe.md

@@ -512,6 +512,7 @@ sb.cdp.scroll_to_bottom()
 sb.cdp.scroll_up(amount=25)
 sb.cdp.scroll_down(amount=25)
 sb.cdp.save_screenshot(name, folder=None, selector=None)
+sb.cdp.print_to_pdf(name, folder=None)
 ```
 
 --------

seleniumbase/__version__.py

@@ -1,2 +1,2 @@
 # seleniumbase package
-__version__ = "4.36.0"
+__version__ = "4.36.1"

seleniumbase/core/browser_launcher.py

@@ -1,4 +1,5 @@
 import fasteners
+import json
 import logging
 import os
 import platform
@@ -769,6 +770,7 @@ def uc_open_with_cdp_mode(driver, url=None):
     cdp.scroll_up = CDPM.scroll_up
     cdp.scroll_down = CDPM.scroll_down
     cdp.save_screenshot = CDPM.save_screenshot
+    cdp.print_to_pdf = CDPM.print_to_pdf
     cdp.page = page  # async world
     cdp.driver = driver.cdp_base  # async world
     cdp.tab = cdp.page  # shortcut (original)
@@ -2125,6 +2127,15 @@ def _set_chrome_options(
         prefs["enable_do_not_track"] = True
     if external_pdf:
         prefs["plugins.always_open_pdf_externally"] = True
+        pdf_settings = {
+            "recentDestinations": [
+                {"id": "Save as PDF", "origin": "local", "account": ""}
+            ],
+            "selectedDestinationId": "Save as PDF",
+            "version": 2,
+        }
+        app_state = "printing.print_preview_sticky_settings.appState"
+        prefs[app_state] = json.dumps(pdf_settings)
     if proxy_string or proxy_pac_url:
         # Implementation of https://stackoverflow.com/q/65705775/7058266
         prefs["webrtc.ip_handling_policy"] = "disable_non_proxied_udp"
@@ -3299,7 +3310,6 @@ def get_remote_driver(
         from seleniumbase.core import capabilities_parser
         desired_caps = capabilities_parser.get_desired_capabilities(cap_file)
     if cap_string:
-        import json
         try:
             extra_caps = json.loads(str(cap_string))
         except Exception as e:

seleniumbase/core/sb_cdp.py

@@ -2181,6 +2181,12 @@ def save_screenshot(self, name, folder=None, selector=None):
         else:
             self.select(selector).save_screenshot(filename)
 
+    def print_to_pdf(self, name, folder=None):
+        filename = name
+        if folder:
+            filename = os.path.join(folder, name)
+        self.loop.run_until_complete(self.page.print_to_pdf(filename))
+
 
 class Chrome(CDPMethods):
     def __init__(self, url=None, **kwargs):

seleniumbase/undetected/__init__.py

@@ -459,7 +459,9 @@ def reconnect(self, timeout=0.1):
                 if self.current_url.startswith(
                     "chrome-extension://"
                 ):
-                    self.close()
+                    # https://issues.chromium.org/issues/396611138
+                    # (Uncomment below when resolved)
+                    # self.close()
                     if self.service.is_connectable():
                         self.stop_client()
                         self.service.stop()
@@ -496,7 +498,9 @@ def connect(self):
                 if self.current_url.startswith(
                     "chrome-extension://"
                 ):
-                    self.close()
+                    # https://issues.chromium.org/issues/396611138
+                    # (Uncomment below when resolved)
+                    # self.close()
                     if self.service.is_connectable():
                         self.stop_client()
                         self.service.stop()

seleniumbase/undetected/cdp_driver/tab.py

@@ -1,7 +1,10 @@
 from __future__ import annotations
 import asyncio
+import base64
+import datetime
 import logging
 import pathlib
+import urllib.parse
 import warnings
 from typing import Dict, List, Union, Optional, Tuple
 from . import browser as cdp_browser
@@ -1133,9 +1136,6 @@ async def save_screenshot(
         :return: The path/filename of the saved screenshot.
         :rtype: str
         """
-        import urllib.parse
-        import datetime
-
         await self.sleep()  # Update the target's URL
         path = None
         if format.lower() in ["jpg", "jpeg"]:
@@ -1166,8 +1166,40 @@ async def save_screenshot(
                 "Most possible cause is the page "
                 "has not finished loading yet."
             )
-        import base64
+        data_bytes = base64.b64decode(data)
+        if not path:
+            raise RuntimeError("Invalid filename or path: '%s'" % filename)
+        path.write_bytes(data_bytes)
+        return str(path)
 
+    async def print_to_pdf(
+        self,
+        filename: Optional[PathLike] = "auto",
+    ) -> str:
+        """
+        Saves a webpage as a PDF.
+        :param filename: uses this as the save path
+        :type filename: PathLike
+        :return: The path/filename of the saved screenshot.
+        :rtype: str
+        """
+        await self.sleep()  # Update the target's URL
+        path = None
+        ext = ".pdf"
+        if not filename or filename == "auto":
+            parsed = urllib.parse.urlparse(self.target.url)
+            parts = parsed.path.split("/")
+            last_part = parts[-1]
+            last_part = last_part.rsplit("?", 1)[0]
+            dt_str = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
+            candidate = f"{parsed.hostname}__{last_part}_{dt_str}"
+            path = pathlib.Path(candidate + ext)  # noqa
+        else:
+            path = pathlib.Path(filename)
+        path.parent.mkdir(parents=True, exist_ok=True)
+        data, _ = await self.send(cdp.page.print_to_pdf())
+        if not data:
+            raise ProtocolException("Could not save PDF.")
         data_bytes = base64.b64decode(data)
         if not path:
             raise RuntimeError("Invalid filename or path: '%s'" % filename)