abstract-webtools 0.1.5.95__py3-none-any.whl → 0.1.5.97__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.
- abstract_webtools/managers/crawlManager.py +1 -1
- abstract_webtools/managers/requestManager.py +2 -2
- {abstract_webtools-0.1.5.95.dist-info → abstract_webtools-0.1.5.97.dist-info}/METADATA +1 -1
- {abstract_webtools-0.1.5.95.dist-info → abstract_webtools-0.1.5.97.dist-info}/RECORD +7 -7
- {abstract_webtools-0.1.5.95.dist-info → abstract_webtools-0.1.5.97.dist-info}/LICENSE +0 -0
- {abstract_webtools-0.1.5.95.dist-info → abstract_webtools-0.1.5.97.dist-info}/WHEEL +0 -0
- {abstract_webtools-0.1.5.95.dist-info → abstract_webtools-0.1.5.97.dist-info}/top_level.txt +0 -0
|
@@ -56,7 +56,7 @@ class CrawlManager():
|
|
|
56
56
|
"""
|
|
57
57
|
all_urls=[self.url_mgr.url]
|
|
58
58
|
domain = self.url_mgr.domain
|
|
59
|
-
all_attribs = get_all_attribute_values(
|
|
59
|
+
all_attribs = get_all_attribute_values(url=self.url_mgr.url,url_mgr=self.url_mgr)
|
|
60
60
|
for href in all_attribs.get('href',[]):
|
|
61
61
|
if href == "" or href is None:
|
|
62
62
|
# href empty tag
|
|
@@ -341,10 +341,10 @@ class SafeRequestSingleton:
|
|
|
341
341
|
elif SafeRequestSingleton._instance.url != url or SafeRequestSingleton._instance.headers != headers or SafeRequestSingleton._instance.max_retries != max_retries or SafeRequestSingleton._instance.request_wait_limit != request_wait_limit:
|
|
342
342
|
SafeRequestSingleton._instance = SafeRequest(url,url_mgr=urlManagerSingleton,headers=headers,max_retries=max_retries,last_request_time=last_request_time,request_wait_limit=request_wait_limit)
|
|
343
343
|
return SafeRequestSingleton._instance
|
|
344
|
-
def get_req_mgr(url=None,url_mgr=None,source_code=None):
|
|
344
|
+
def get_req_mgr(url=None,url_mgr=None,source_code=None,req_mgr=None):
|
|
345
345
|
url = get_url(url=url,url_mgr=url_mgr)
|
|
346
346
|
url_mgr = get_url_mgr(url=url,url_mgr=url_mgr )
|
|
347
|
-
req_mgr = requestManager(url_mgr=url_mgr,url=url,source_code=source_code)
|
|
347
|
+
req_mgr = req_mgr or requestManager(url_mgr=url_mgr,url=url,source_code=source_code)
|
|
348
348
|
return req_mgr
|
|
349
349
|
def get_source(url=None,url_mgr=None,source_code=None):
|
|
350
350
|
# Placeholder for actual implementation.
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
2
|
Name: abstract_webtools
|
|
3
|
-
Version: 0.1.5.
|
|
3
|
+
Version: 0.1.5.97
|
|
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
|
|
@@ -7,13 +7,13 @@ 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=
|
|
10
|
+
abstract_webtools/managers/crawlManager.py,sha256=m5vuZsB7EndZ5DZQ7gXS_B4HsRfIURMrye42knp35BM,10668
|
|
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
|
|
14
14
|
abstract_webtools/managers/mySocketClient.py,sha256=-j1Q8Ds9RCSbjZdx3ZF9mVpgwxaO0BBssanUcpYVQoY,2045
|
|
15
15
|
abstract_webtools/managers/networkManager.py,sha256=Op2QDXrP-gmm0tCToe-Ryt9xuOtMppcN2KLKP1WZiu0,952
|
|
16
|
-
abstract_webtools/managers/requestManager.py,sha256=
|
|
16
|
+
abstract_webtools/managers/requestManager.py,sha256=YksYgRivMMuZNOzyL5vaoXv9MLhgYeuLxO_UJiqPGWw,17312
|
|
17
17
|
abstract_webtools/managers/seleniumManager.py,sha256=CtQQYtDrFfgp8ujC6i5SCe0b_hgIA1K68io0aO4igoM,3623
|
|
18
18
|
abstract_webtools/managers/soupManager.py,sha256=nFHalHxxDXNI2HhDg8ffZYF36LbJ-uWxx4JnRFa3Hhw,16542
|
|
19
19
|
abstract_webtools/managers/sslManager.py,sha256=C-QgQw9CW84uOE5kx2MPjC3RsLbE2JQqdwdTs0H4ecc,1370
|
|
@@ -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-0.1.5.
|
|
25
|
-
abstract_webtools-0.1.5.
|
|
26
|
-
abstract_webtools-0.1.5.
|
|
27
|
-
abstract_webtools-0.1.5.
|
|
28
|
-
abstract_webtools-0.1.5.
|
|
24
|
+
abstract_webtools-0.1.5.97.dist-info/LICENSE,sha256=g3WEJFiVS27HyCGRTwKSsMLyciMaGFdWcZGOe1QalZk,3877
|
|
25
|
+
abstract_webtools-0.1.5.97.dist-info/METADATA,sha256=5E14JgIpMfLL80bHASnjvFZ2G1dUSg1yaT9W36RFQvg,15858
|
|
26
|
+
abstract_webtools-0.1.5.97.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
|
|
27
|
+
abstract_webtools-0.1.5.97.dist-info/top_level.txt,sha256=2DMJ7RmjTcjCsa-uwAV0K6eXXlIIkFDEjBLg_uyCmCI,18
|
|
28
|
+
abstract_webtools-0.1.5.97.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|
|
File without changes
|