abstract-webtools 0.1.6.60__py3-none-any.whl → 0.1.6.62__py3-none-any.whl

abstract_webtools/abstract_usurpit.py

@@ -53,12 +53,14 @@ def save_page(url, content,output_dir):
     with open(page_full_path, 'w', encoding='utf-8') as f:
         f.write(content)
     print(f"Saved page: {page_full_path}")
-def save_asset(asset_url, base_url,output_dir,downloaded_assets,session):
+def save_asset(asset_url, base_url,output_dir,downloaded_assets=None,session=None):
     """
     Download and save assets like images, CSS, JS files.
     """
+    session=requests.Session()
+    downloaded_assets = downloaded_assets or set()
     asset_url = normalize_url(asset_url, base_url)
-    if asset_url in downloaded_assets:
+    if asset_url in list(downloaded_assets):
         return
     downloaded_assets.add(asset_url)
 
@@ -102,18 +104,18 @@ class usurpManager():
             "Access-Control-Allow-Origin": "*"})
 
     def process_page(self,url, depth, base_domain):
-        """
-        Process a single page: download assets, save HTML, and crawl links.
-        """
-        print(url)
-        if url in self.visited_pages or depth > self.MAX_DEPTH:
-            return
-        self.visited_pages.add(url)
-        
-        try:
+            """
+            Process a single page: download assets, save HTML, and crawl links.
+            """
+            print(url)
+            if url in self.visited_pages or depth > self.MAX_DEPTH:
+                return
+            self.visited_pages.add(url)
+            
+     
             # Fetch the page content
             response = self.session.get(url)
-            response.raise_for_status()
+            #response.raise_for_status()
             content = response.text
 
             # Use your get_soup_mgr function to get the soup and attributes
@@ -150,8 +152,6 @@ class usurpManager():
                     time.sleep(self.WAIT_BETWEEN_REQUESTS)
                     self.process_page(normalized_link, depth + 1, base_domain)
 
-        except Exception as e:
-            print(f"Failed to process page {url}: {e}")
 
     def main(self):
         # Ensure output directory exists
@@ -163,7 +163,7 @@ class usurpManager():
         self.process_page(self.BASE_URL, 0, base_domain)
         print("Website copying completed.")
 def test_download(url=None,directory=None):
-    url=url or 'https://algassert.com/quantum/2016/01/07/Delayed-Choice-Quantum-Erasure.html'
+    url=url or 'https://www.youtube.com/watch?v=jRGrNDV2mKc&list=RDMMjRGrNDV2mKc&start_radio=1'
     output_dir= directory or os.path.join(os.getcwd(),'testit')
     os.makedirs(output_dir,exist_ok=True)
     site_mgr = usurpManager(url,output_dir)

{abstract_webtools-0.1.6.60.dist-info → abstract_webtools-0.1.6.62.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: abstract_webtools
-Version: 0.1.6.60
+Version: 0.1.6.62
 Summary: Abstract Web Tools is a Python package that provides various utility functions for web scraping tasks. It is built on top of popular libraries such as `requests`, `BeautifulSoup`, and `urllib3` to simplify the process of fetching and parsing web content.
 Home-page: https://github.com/AbstractEndeavors/abstract_essentials/tree/main/abstract_webtools
 Author: putkoff

{abstract_webtools-0.1.6.60.dist-info → abstract_webtools-0.1.6.62.dist-info}/RECORD

@@ -1,6 +1,6 @@
 abstract_webtools/__init__.py,sha256=zNMp-9f0Q6BXWxR-tgHrEqKP8GeXw9z7VYzbqIeEydo,132
 abstract_webtools/abstract_userpit.py,sha256=Rg_0Orx79rxqEePt6Sf-evGslPq5KLlTiL-P2w1u6ng,6462
-abstract_webtools/abstract_usurpit.py,sha256=AAqelbqntBsRZUxPJ0XiGO4xqsmR-y-LbQwn8sDevPo,7131
+abstract_webtools/abstract_usurpit.py,sha256=7PDUb5LNETjvU1rhfJaToKLIKmSXRkcJAmM4wOX7PsQ,7170
 abstract_webtools/abstract_webtools.py,sha256=3NzGmJlZvrdVtEcUi2K5iUgWr1822IBPhIN9us2e2t0,3859
 abstract_webtools/big_user_agent_list.py,sha256=5ZkrUWmfzYL5yaULREslh9ZiRQeITbSjqZlp2KQON3w,131923
 abstract_webtools/main.py,sha256=_I7pPXPkoLZOoYGLQDrSLGhGuQt6-PVyXEHZSmglk2g,1329
@@ -37,7 +37,7 @@ abstract_webtools/managers/soupManager/soupManager.py,sha256=U3_o189-OWoBRaSCe2s
 abstract_webtools/managers/urlManager/__init__.py,sha256=gaJCHeK91Z-eYsBnxgdhbIUten1-gbx-zqx70R6ag-Y,26
 abstract_webtools/managers/urlManager/urlManager.py,sha256=vCFuLADmv3h7icaaoAsImGqb_49VizPY_ZvMl-C7PYk,7756
 abstract_webtools/managers/videos/Heather brooke swallo from condom.mp4,sha256=h-bKFLAHt7pGLGu4EcMvSSox7BPRK0Nga3u813iMVKQ,8335544
-abstract_webtools-0.1.6.60.dist-info/METADATA,sha256=eOy8Kvm6ipb8jVKRoEyTLtaZrrHSxwYb1tHQP7_PJb0,16029
-abstract_webtools-0.1.6.60.dist-info/WHEEL,sha256=1tXe9gY0PYatrMPMDd6jXqjfpz_B-Wqm32CPfRC58XU,91
-abstract_webtools-0.1.6.60.dist-info/top_level.txt,sha256=2DMJ7RmjTcjCsa-uwAV0K6eXXlIIkFDEjBLg_uyCmCI,18
-abstract_webtools-0.1.6.60.dist-info/RECORD,,
+abstract_webtools-0.1.6.62.dist-info/METADATA,sha256=4cXNFpklULNRdmmGoI0kw6KQm9IcokPKehfHwScitCc,16029
+abstract_webtools-0.1.6.62.dist-info/WHEEL,sha256=1tXe9gY0PYatrMPMDd6jXqjfpz_B-Wqm32CPfRC58XU,91
+abstract_webtools-0.1.6.62.dist-info/top_level.txt,sha256=2DMJ7RmjTcjCsa-uwAV0K6eXXlIIkFDEjBLg_uyCmCI,18
+abstract_webtools-0.1.6.62.dist-info/RECORD,,