abstract-webtools 0.1.6.1__tar.gz → 0.1.6.3__tar.gz

{abstract_webtools-0.1.6.1/src/abstract_webtools.egg-info → abstract_webtools-0.1.6.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: abstract_webtools
-Version: 0.1.6.1
+Version: 0.1.6.3
 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-0.1.6.1 → abstract_webtools-0.1.6.3}/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='0.1.6.01',
+    version='0.1.6.03',
     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-0.1.6.1 → abstract_webtools-0.1.6.3}/src/abstract_webtools/managers/crawlManager.py

@@ -73,7 +73,7 @@ class crawlManager():
         """
         all_urls=[self.url_mgr.url]
         domain = self.url_mgr.domain
-        all_attribs = get_attribs(self.url_mgr.url)
+        all_attribs = get_all_attribute_values(self.url_mgr.url)
         for href in all_attribs.get('href',[]):
             if href == "" or href is None:
                 # href empty tag
@@ -163,7 +163,7 @@ class crawlManager():
         # Fetch the title if available
         meta_tags = soup_mgr.find_all("meta")
         url = eatAll(str(url),['',' ','\n','\t','\\','/'])
-        attribs = get_attribs(url)
+        attribs = get_all_attribute_values(url)
         soup = get_soup(url)
         
         for meta_tag in meta_tags:
@@ -194,7 +194,7 @@ class crawlManager():
                 string += f'  <url>\n    <loc>{url}</loc>\n'
                 preprocess=[]
                 self.get_new_source_and_url(url=url)
-                links = get_attribs(url)
+                links = get_all_attribute_values(url)
                 images = [link for link in links if link.lower().endswith(('.png', '.jpg', '.jpeg', '.gif', '.svg', '.webp'))]
 
                 for img in images:
@@ -240,22 +240,22 @@ class crawlManager():
             for ext_link in links['external_links']:
                 print(f"\t{ext_link}")
 
-class CrawlManagerSingleton():
+class crawlManagerSingleton():
     _instance = None
     @staticmethod
     def get_instance(url=None,source_code=None,parse_type="html.parser"):
-        if CrawlManagerSingleton._instance is None:
-            CrawlManagerSingleton._instance = CrawlManager(url=url,parse_type=parse_type,source_code=source_code)
-        elif parse_type != CrawlManagerSingleton._instance.parse_type or url != CrawlManagerSingleton._instance.url  or source_code != CrawlManagerSingleton._instance.source_code:
-            CrawlManagerSingleton._instance = CrawlManager(url=url,parse_type=parse_type,source_code=source_code)
-        return CrawlManagerSingleton._instance
+        if crawlManagerSingleton._instance is None:
+            crawlManagerSingleton._instance = CrawlManager(url=url,parse_type=parse_type,source_code=source_code)
+        elif parse_type != crawlManagerSingleton._instance.parse_type or url != crawlManagerSingleton._instance.url  or source_code != crawlManagerSingleton._instance.source_code:
+            crawlManagerSingleton._instance = CrawlManager(url=url,parse_type=parse_type,source_code=source_code)
+        return crawlManagerSingleton._instance
 def get_crawl_mgr(url=None,req_mgr=None,url_mgr=None,source_code=None,parse_type="html.parser"):
     url = get_url(url=url,url_mgr=url_mgr)
     url_mgr = get_url(url=url,url_mgr=url_mgr)
     req_mgr=get_req_mgr(url=url,url_mgr=url_mgr,source_code=source_code)
     source_code = get_source(url=url,url_mgr=url_mgr,source_code=source_code,req_mgr=req_mgr)
     soup_mgr = get_soup_mgr(url=url,url_mgr=url_mgr,source_code=source_code,req_mgr=req_mgr,parse_type=parse_type)
-    crawl_mgr = CrawlManager(url=url,req_mgr=req_mgr,url_mgr=url_mgr,source_code=source_code,parse_type=parse_type)
+    crawl_mgr = crawlManager(url=url,req_mgr=req_mgr,url_mgr=url_mgr,source_code=source_code,parse_type=parse_type)
     return crawl_mgr
 def get_domain_crawl(url=None,req_mgr=None,url_mgr=None,source_code=None,parse_type="html.parser",max_depth=3, depth=1):
     crawl_mgr = get_crawl_mgr(url=url,req_mgr=req_mgr,url_mgr=url_mgr,source_code=source_code,parse_type=parse_type)

{abstract_webtools-0.1.6.1 → abstract_webtools-0.1.6.3/src/abstract_webtools.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: abstract_webtools
-Version: 0.1.6.1
+Version: 0.1.6.3
 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