abstract-webtools 0.1.6.8__py3-none-any.whl → 0.1.6.10__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -19,7 +19,7 @@ class crawlManager():
19
19
  attrs = 'href','src'
20
20
  unique_classes, images=discover_classes_and_images(self,tag_name,class_name_1,class_name_2,class_value,attrs)
21
21
  return unique_classes, images
22
- def extract_links_from_url(self):
22
+ def extract_links_from_url(self,url=None):
23
23
  """
24
24
  Extracts all href and src links from a given URL's source code.
25
25
 
@@ -29,6 +29,8 @@ class crawlManager():
29
29
  Returns:
30
30
  dict: Dictionary containing image links and external links under the parent page.
31
31
  """
32
+ url = url or self.url_mgr.url
33
+ soup_mgr = get_soup_mgr(url=url)
32
34
  agg_js = {'images':[],'external_links':[]}
33
35
 
34
36
  if self.response != None:
@@ -36,7 +38,7 @@ class crawlManager():
36
38
  href_links,src_links='',''
37
39
  links = [href_links,src_links]
38
40
  for i,each in enumerate(attrs):
39
- links[i]= [a[attr[i]] for a in get_find_all_with_attributes(self, attrs[i])]
41
+ links[i]= [a[attr[i]] for a in soup_mgr.get_find_all_with_attributes(attrs[i])]
40
42
  # Convert all links to absolute links
41
43
  absolute_links = [(url, link) for link in links[0] + links[1]]
42
44
  # Separate images and external links
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: abstract_webtools
3
- Version: 0.1.6.8
3
+ Version: 0.1.6.10
4
4
  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.
5
5
  Home-page: https://github.com/AbstractEndeavors/abstract_essentials/tree/main/abstract_webtools
6
6
  Author: putkoff
@@ -7,7 +7,7 @@ abstract_webtools/url_grabber.py,sha256=pnCCev7ZIuM-6cAGTLmK5HfzZg_AX-fLcRpB6ZE7
7
7
  abstract_webtools/url_grabber_new.py,sha256=Oh2Kc0gBScCo0xpopNsg8JE5lIbPuzZVKM5f5GoZmw0,3454
8
8
  abstract_webtools/managers/__init__.py,sha256=5aIpbdUsDWTrhPUAjfIKnG54OULqOKan9LBL5EIUllo,407
9
9
  abstract_webtools/managers/cipherManager.py,sha256=NHQGdR11eNSm-1H-GezD5dyQgsPTJwY5kczt8Sher2s,1621
10
- abstract_webtools/managers/crawlManager.py,sha256=vpNFw7ws-ce94XZc3yzvFOcAIknGX_LwAB5nTctxIQs,10645
10
+ abstract_webtools/managers/crawlManager.py,sha256=_Pci_Rm1jZzFjFle_PerkecrZZ_unBxcK2HPEmS98HM,10736
11
11
  abstract_webtools/managers/domainManager.py,sha256=95znOBv05W77mW_fbZAfl4RmlENDlYqhEOMkL02L220,3610
12
12
  abstract_webtools/managers/dynamicRateLimiter.py,sha256=gopQcQo50JG2D0KcyepNCIQ_1uDQEBIHBzWf4R2Wgy0,7617
13
13
  abstract_webtools/managers/linkManager.py,sha256=m6y9s8jknrTX8RtOAFKeHd4yd23G7Rgf0T7Sp7wmHUw,12180
@@ -21,8 +21,8 @@ abstract_webtools/managers/tlsAdapter.py,sha256=XZSMZz9EUOhv-h3_Waf6mjV1dA3oN_M_
21
21
  abstract_webtools/managers/urlManager.py,sha256=XqMrCM84BeWEfWtHc_8UFpT91ZtG-okzdKdCuC49vsA,8678
22
22
  abstract_webtools/managers/userAgentManager.py,sha256=33SB2p2FG7EYZl7l2iYm1U4gI9PcdkGTZHw5lg_Ogrw,1653
23
23
  abstract_webtools/managers/videoDownloader.py,sha256=6G_aLc05BTMUYUWc7iqYtHF_BaR7DnCNK_NJ-QnjsYY,10531
24
- abstract_webtools-0.1.6.8.dist-info/LICENSE,sha256=g3WEJFiVS27HyCGRTwKSsMLyciMaGFdWcZGOe1QalZk,3877
25
- abstract_webtools-0.1.6.8.dist-info/METADATA,sha256=i3hmyewNNN58whws97NoN3zL4PzfOyUZgPUw8YCVIHs,15857
26
- abstract_webtools-0.1.6.8.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
27
- abstract_webtools-0.1.6.8.dist-info/top_level.txt,sha256=2DMJ7RmjTcjCsa-uwAV0K6eXXlIIkFDEjBLg_uyCmCI,18
28
- abstract_webtools-0.1.6.8.dist-info/RECORD,,
24
+ abstract_webtools-0.1.6.10.dist-info/LICENSE,sha256=g3WEJFiVS27HyCGRTwKSsMLyciMaGFdWcZGOe1QalZk,3877
25
+ abstract_webtools-0.1.6.10.dist-info/METADATA,sha256=vVVUtiXTGSf_Z2RGB7qE2LBFPxOOG_7dNxoR_JeoXwY,15858
26
+ abstract_webtools-0.1.6.10.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
27
+ abstract_webtools-0.1.6.10.dist-info/top_level.txt,sha256=2DMJ7RmjTcjCsa-uwAV0K6eXXlIIkFDEjBLg_uyCmCI,18
28
+ abstract_webtools-0.1.6.10.dist-info/RECORD,,