abstract-webtools 0.1.6.8__tar.gz → 0.1.6.10__tar.gz

{abstract_webtools-0.1.6.8/src/abstract_webtools.egg-info → abstract_webtools-0.1.6.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: abstract_webtools
-Version: 0.1.6.8
+Version: 0.1.6.10
 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-0.1.6.8 → abstract_webtools-0.1.6.10}/setup.py

@@ -4,7 +4,7 @@ with open("README.md", "r", encoding="utf-8") as fh:
     long_description = fh.read()
 setuptools.setup(
     name='abstract_webtools',
-    version='0.1.6.08',
+    version='0.1.6.10',
     author='putkoff',
     author_email='partners@abstractendeavors.com',
     description='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.',

{abstract_webtools-0.1.6.8 → abstract_webtools-0.1.6.10}/src/abstract_webtools/managers/crawlManager.py

@@ -19,7 +19,7 @@ class crawlManager():
         attrs = 'href','src'
         unique_classes, images=discover_classes_and_images(self,tag_name,class_name_1,class_name_2,class_value,attrs)
         return unique_classes, images
-    def extract_links_from_url(self):
+    def extract_links_from_url(self,url=None):
         """
         Extracts all href and src links from a given URL's source code.
 
@@ -29,6 +29,8 @@ class crawlManager():
         Returns:
             dict: Dictionary containing image links and external links under the parent page.
         """
+        url = url or self.url_mgr.url
+        soup_mgr = get_soup_mgr(url=url)
         agg_js = {'images':[],'external_links':[]}
         
         if self.response != None:
@@ -36,7 +38,7 @@ class crawlManager():
             href_links,src_links='',''
             links = [href_links,src_links]
             for i,each in enumerate(attrs):
-                 links[i]= [a[attr[i]] for a in get_find_all_with_attributes(self, attrs[i])]
+                 links[i]= [a[attr[i]] for a in soup_mgr.get_find_all_with_attributes(attrs[i])]
             # Convert all links to absolute links
             absolute_links = [(url, link) for link in links[0] + links[1]]
             # Separate images and external links

{abstract_webtools-0.1.6.8 → abstract_webtools-0.1.6.10/src/abstract_webtools.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: abstract_webtools
-Version: 0.1.6.8
+Version: 0.1.6.10
 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