abstract-webtools 0.1.5.99__py3-none-any.whl → 0.1.6.0__py3-none-any.whl

abstract_webtools/managers/crawlManager.py

@@ -1,4 +1,21 @@
 from .soupManager import *
+
+def normalize_url(url, base_url):
+    """
+    Normalize and resolve relative URLs, ensuring proper domain and format.
+    """
+    # If URL starts with the base URL repeated, remove the extra part
+    if url.startswith(base_url):
+        url = url[len(base_url):]
+
+    # Resolve the URL against the base URL
+    normalized_url = urljoin(base_url, url.split('#')[0])
+
+    # Ensure only URLs belonging to the base domain are kept
+    if not normalized_url.startswith(base_url):
+        return None
+
+    return normalized_url
 class CrawlManager():
     def __init__(self,url=None,req_mgr=None,url_mgr=None,source_code=None,parse_type="html.parser"):
         self.url=url
@@ -56,7 +73,7 @@ class CrawlManager():
         """
         all_urls=[self.url_mgr.url]
         domain = self.url_mgr.domain
-        all_attribs = get_all_attribute_values(url=self.url_mgr.url,url_mgr=self.url_mgr)
+        all_attribs = get_attribs(self.url_mgr.url)
         for href in all_attribs.get('href',[]):
             if href == "" or href is None:
                 # href empty tag
@@ -146,7 +163,7 @@ class CrawlManager():
         # Fetch the title if available
         meta_tags = soup_mgr.find_all("meta")
         url = eatAll(str(url),['',' ','\n','\t','\\','/'])
-        attribs = get_all_attribute_values(url)
+        attribs = get_attribs(url)
         soup = get_soup(url)
         
         for meta_tag in meta_tags:
@@ -177,7 +194,7 @@ class CrawlManager():
                 string += f'  <url>\n    <loc>{url}</loc>\n'
                 preprocess=[]
                 self.get_new_source_and_url(url=url)
-                links = get_all_attribute_values(url)
+                links = get_attribs(url)
                 images = [link for link in links if link.lower().endswith(('.png', '.jpg', '.jpeg', '.gif', '.svg', '.webp'))]
 
                 for img in images:

{abstract_webtools-0.1.5.99.dist-info → abstract_webtools-0.1.6.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: abstract_webtools
-Version: 0.1.5.99
+Version: 0.1.6.0
 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-0.1.5.99.dist-info → abstract_webtools-0.1.6.0.dist-info}/RECORD

@@ -7,7 +7,7 @@ abstract_webtools/url_grabber.py,sha256=pnCCev7ZIuM-6cAGTLmK5HfzZg_AX-fLcRpB6ZE7
 abstract_webtools/url_grabber_new.py,sha256=Oh2Kc0gBScCo0xpopNsg8JE5lIbPuzZVKM5f5GoZmw0,3454
 abstract_webtools/managers/__init__.py,sha256=5aIpbdUsDWTrhPUAjfIKnG54OULqOKan9LBL5EIUllo,407
 abstract_webtools/managers/cipherManager.py,sha256=NHQGdR11eNSm-1H-GezD5dyQgsPTJwY5kczt8Sher2s,1621
-abstract_webtools/managers/crawlManager.py,sha256=m5vuZsB7EndZ5DZQ7gXS_B4HsRfIURMrye42knp35BM,10668
+abstract_webtools/managers/crawlManager.py,sha256=6i7mydDrJoFKLrw1hOLXAW782MSuj57IGaTS3Pwcy1k,11127
 abstract_webtools/managers/domainManager.py,sha256=95znOBv05W77mW_fbZAfl4RmlENDlYqhEOMkL02L220,3610
 abstract_webtools/managers/dynamicRateLimiter.py,sha256=gopQcQo50JG2D0KcyepNCIQ_1uDQEBIHBzWf4R2Wgy0,7617
 abstract_webtools/managers/linkManager.py,sha256=m6y9s8jknrTX8RtOAFKeHd4yd23G7Rgf0T7Sp7wmHUw,12180
@@ -21,8 +21,8 @@ abstract_webtools/managers/tlsAdapter.py,sha256=XZSMZz9EUOhv-h3_Waf6mjV1dA3oN_M_
 abstract_webtools/managers/urlManager.py,sha256=XqMrCM84BeWEfWtHc_8UFpT91ZtG-okzdKdCuC49vsA,8678
 abstract_webtools/managers/userAgentManager.py,sha256=33SB2p2FG7EYZl7l2iYm1U4gI9PcdkGTZHw5lg_Ogrw,1653
 abstract_webtools/managers/videoDownloader.py,sha256=6G_aLc05BTMUYUWc7iqYtHF_BaR7DnCNK_NJ-QnjsYY,10531
-abstract_webtools-0.1.5.99.dist-info/LICENSE,sha256=g3WEJFiVS27HyCGRTwKSsMLyciMaGFdWcZGOe1QalZk,3877
-abstract_webtools-0.1.5.99.dist-info/METADATA,sha256=D53IoHFui8dJQ6rBjjye2-Ujte-GcVlREwlh6-DMf6E,15858
-abstract_webtools-0.1.5.99.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
-abstract_webtools-0.1.5.99.dist-info/top_level.txt,sha256=2DMJ7RmjTcjCsa-uwAV0K6eXXlIIkFDEjBLg_uyCmCI,18
-abstract_webtools-0.1.5.99.dist-info/RECORD,,
+abstract_webtools-0.1.6.0.dist-info/LICENSE,sha256=g3WEJFiVS27HyCGRTwKSsMLyciMaGFdWcZGOe1QalZk,3877
+abstract_webtools-0.1.6.0.dist-info/METADATA,sha256=V7pW8-JWmyVtLlcEGXCc3jT4tcGas2vkkls4-NUFx6w,15857
+abstract_webtools-0.1.6.0.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
+abstract_webtools-0.1.6.0.dist-info/top_level.txt,sha256=2DMJ7RmjTcjCsa-uwAV0K6eXXlIIkFDEjBLg_uyCmCI,18
+abstract_webtools-0.1.6.0.dist-info/RECORD,,