abstract-webtools 0.1.6.151__py3-none-any.whl → 0.1.6.152__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/url_grabber.py +3 -27
- {abstract_webtools-0.1.6.151.dist-info → abstract_webtools-0.1.6.152.dist-info}/METADATA +1 -1
- {abstract_webtools-0.1.6.151.dist-info → abstract_webtools-0.1.6.152.dist-info}/RECORD +5 -5
- {abstract_webtools-0.1.6.151.dist-info → abstract_webtools-0.1.6.152.dist-info}/WHEEL +0 -0
- {abstract_webtools-0.1.6.151.dist-info → abstract_webtools-0.1.6.152.dist-info}/top_level.txt +0 -0
abstract_webtools/url_grabber.py
CHANGED
@@ -2,10 +2,7 @@ from abstract_gui import make_component,sg
|
|
2
2
|
import inspect
|
3
3
|
import re
|
4
4
|
from . import UserAgentManager,UrlManager,SafeRequest,SoupManager,LinkManager,CipherManager,requests,ssl,BeautifulSoup,HTTPAdapter,PoolManager,ssl_
|
5
|
-
<<<<<<< HEAD
|
6
|
-
=======
|
7
5
|
from .managers import *
|
8
|
-
>>>>>>> ba4baf2 (Deploy version 0.1.6.147 at 2025-09-07 09:40:38 UTC)
|
9
6
|
window = None
|
10
7
|
|
11
8
|
def get_attrs(values):
|
@@ -29,11 +26,8 @@ def get_attrs(values):
|
|
29
26
|
else:
|
30
27
|
tags_js['attribute']=tags_js['attribute'][0]
|
31
28
|
return tags_js
|
32
|
-
|
33
|
-
def get_user_agent_manager(user_agent=None):
|
34
|
-
=======
|
29
|
+
|
35
30
|
def get_user_agent_mgr(user_agent=None):
|
36
|
-
>>>>>>> ba4baf2 (Deploy version 0.1.6.147 at 2025-09-07 09:40:38 UTC)
|
37
31
|
return UserAgentManager(user_agent=user_agent)
|
38
32
|
def get_cipher_list():
|
39
33
|
return CipherManager().get_default_ciphers()
|
@@ -140,13 +134,10 @@ def process_url(window,values):
|
|
140
134
|
if temp_url:
|
141
135
|
valid='valid'
|
142
136
|
response_code = SafeRequest(url=temp_mgr).response.status_code
|
143
|
-
<<<<<<< HEAD
|
144
|
-
=======
|
145
137
|
temp_url=urlManager(url=warn_url).url
|
146
138
|
if temp_url:
|
147
139
|
valid='valid'
|
148
140
|
response_code = requestManager(url=temp_mgr).response.status_code
|
149
|
-
>>>>>>> ba4baf2 (Deploy version 0.1.6.147 at 2025-09-07 09:40:38 UTC)
|
150
141
|
warn = 'success'
|
151
142
|
warn_url = temp_mgr
|
152
143
|
update_status(window,warn,warn_url,response_code,valid)
|
@@ -169,9 +160,7 @@ def update_source_code(url_manager,request_manager,soup_manager,link_manager,val
|
|
169
160
|
if parse_type != soup_manager.parse_type:
|
170
161
|
soup_manager.update_parse_type(parse_type=parse_type)
|
171
162
|
all_tags=soup_manager.get_all_tags_and_attribute_names()
|
172
|
-
<<<<<<< HEAD
|
173
163
|
window['-SOURCECODE-'].update(value=soup_manager.soup)
|
174
|
-
=======
|
175
164
|
window['-SOURCECODE-'].update(value=soup_manager.soupdef update_url(url_mgr,request_mgr,soup_mgr,link_mgr,values,cipher_list=get_cipher_list(),user_agent=get_user_agents()[0]):
|
176
165
|
ciphers = CipherManager(cipher_list=cipher_list).ciphers_string
|
177
166
|
request_mgr = requestManager(url_mgr=url_mgr,ciphers=ciphers,user_agent=get_user_agents()[0])
|
@@ -189,7 +178,6 @@ def update_source_code(url_mgr,request_mgr,soup_mgr,link_mgr,values):
|
|
189
178
|
soup_mgr.update_parse_type(parse_type=parse_type)
|
190
179
|
all_tags=soup_mgr.get_all_tags_and_attribute_names()
|
191
180
|
window['-SOURCECODE-'].update(value=soup_mgr.soup)
|
192
|
-
>>>>>>> ba4baf2 (Deploy version 0.1.6.147 at 2025-09-07 09:40:38 UTC)
|
193
181
|
if values['-SOUP_TAG-'] != all_tags['tags']:
|
194
182
|
window['-SOUP_TAG-'].update(values=all_tags['tags'],value=all_tags['tags'][0])
|
195
183
|
if values['-SOUP_ATTRIBUTE-'] != all_tags['attributes']:
|
@@ -204,9 +192,7 @@ def url_grabber_while(window,initial_url="www.example.com"):
|
|
204
192
|
request_manager = SafeRequest(url_manager=url_manager)
|
205
193
|
soup_manager= SoupManager(url_manager=url_manager,request_manager=request_manager)
|
206
194
|
link_manager= LinkManager(url_manager=url_manager,request_manager=request_manager,soup_manager=soup_manager)
|
207
|
-
|
208
|
-
=======
|
209
|
-
return url_mgr,request_mgr,soup_mgr,link_mgr
|
195
|
+
return url_mgr,request_mgr,soup_mgr,link_mgr
|
210
196
|
def url_grabber_while(window,initial_url="www.example.com"):
|
211
197
|
return_data=None
|
212
198
|
url_grab = False
|
@@ -214,7 +200,6 @@ def url_grabber_while(window,initial_url="www.example.com"):
|
|
214
200
|
request_mgr = requestManager(url_mgr=url_mgr)
|
215
201
|
soup_mgr= SoupManager(url_mgr=url_mgr,request_mgr=request_mgr)
|
216
202
|
link_mgr= LinkManager(url_mgr=url_mgr,request_mgr=request_mgr,soup_mgr=soup_mgr)
|
217
|
-
>>>>>>> ba4baf2 (Deploy version 0.1.6.147 at 2025-09-07 09:40:38 UTC)
|
218
203
|
while True:
|
219
204
|
event, values = window.read()
|
220
205
|
if event == sg.WINDOW_CLOSED:
|
@@ -230,9 +215,7 @@ def url_grabber_while(window,initial_url="www.example.com"):
|
|
230
215
|
url_grab=True
|
231
216
|
if event == 'get soup':
|
232
217
|
tags_js = get_attrs(values)
|
233
|
-
all_desired=soup_manager.find_tags_by_attributes(tag=tags_js['tag'], attr=tags_js['attribute'],attr_values=tags_js['
|
234
|
-
<<<<<<< HEAD
|
235
|
-
=======
|
218
|
+
all_desired=soup_manager.find_tags_by_attributes(tag=tags_js['tag'], attr=tags_js['attribute'],attr_values=tags_js['inputHEAD
|
236
219
|
if urlManager(url=url).url:
|
237
220
|
if url != url_mgr.url or url == initial_url:
|
238
221
|
url_mgr = urlManager(url=url)
|
@@ -243,16 +226,12 @@ def url_grabber_while(window,initial_url="www.example.com"):
|
|
243
226
|
if event == 'get soup':
|
244
227
|
tags_js = get_attrs(values)
|
245
228
|
all_desired=soup_mgr.find_tags_by_attributes(tag=tags_js['tag'], attr=tags_js['attribute'],attr_values=tags_js['input'])
|
246
|
-
>>>>>>> ba4baf2 (Deploy version 0.1.6.147 at 2025-09-07 09:40:38 UTC)
|
247
229
|
window['-FIND_ALL_OUTPUT-'].update(value=all_desired)
|
248
230
|
if event == '-CUSTOMUA-':
|
249
231
|
window['-SOURCECODE-'].update(disabled=values['-CUSTOMUA-'])
|
250
232
|
if not values['-CUSTOMUA-']:
|
251
233
|
window['-USERAGENT-'].update(value=user_agent_manager.user_agent_header)
|
252
|
-
<<<<<<< HEAD
|
253
|
-
=======
|
254
234
|
window['-USERAGENT-'].update(value=user_agent_mgr.user_agent_header)
|
255
|
-
>>>>>>> ba4baf2 (Deploy version 0.1.6.147 at 2025-09-07 09:40:38 UTC)
|
256
235
|
window['-USERAGENT-'].update(disabled=True)
|
257
236
|
else:
|
258
237
|
window['-USERAGENT-'].update(disabled=False)
|
@@ -263,15 +242,12 @@ def url_grabber_while(window,initial_url="www.example.com"):
|
|
263
242
|
if parse_type != soup_manager.parse_type:
|
264
243
|
soup_manager.update_parse_type(parse_type=parse_type)
|
265
244
|
window['-SOURCECODE-'].update(value=soup_manager.soup)
|
266
|
-
<<<<<<< HEAD
|
267
|
-
=======
|
268
245
|
window['-FIND_ALL_OUTPUT-'].update(value=soup_mgr.extract_text_sections())
|
269
246
|
if event == 'Action':
|
270
247
|
parse_type = values['-parse_type-']
|
271
248
|
if parse_type != soup_mgr.parse_type:
|
272
249
|
soup_mgr.update_parse_type(parse_type=parse_type)
|
273
250
|
window['-SOURCECODE-'].update(value=soup_mgr.soup)
|
274
|
-
>>>>>>> ba4baf2 (Deploy version 0.1.6.147 at 2025-09-07 09:40:38 UTC)
|
275
251
|
elif event == 'Send Soup':
|
276
252
|
return_data = values['-FIND_ALL_OUTPUT-']
|
277
253
|
break
|
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.4
|
2
2
|
Name: abstract_webtools
|
3
|
-
Version: 0.1.6.
|
3
|
+
Version: 0.1.6.152
|
4
4
|
Summary: Utilities for fetching/parsing web content with requests/urllib3/BS4 and helpers.
|
5
5
|
Home-page: https://github.com/AbstractEndeavors/abstract_webtools
|
6
6
|
Author: putkoff
|
@@ -8,7 +8,7 @@ abstract_webtools/find_dirs.py,sha256=BlE4ruzMABqmv03NcutZ1j5N3pCc-Q4uNEAMpNolZC
|
|
8
8
|
abstract_webtools/k2s_downloader.py,sha256=t0tCKAfDNQGn9tKh3eg0XVU0bY-MmYITwJa3ANf7090,6988
|
9
9
|
abstract_webtools/main.py,sha256=_I7pPXPkoLZOoYGLQDrSLGhGuQt6-PVyXEHZSmglk2g,1329
|
10
10
|
abstract_webtools/soup_gui.py,sha256=n95YAps1R6DpMwR4UbthSqQby0C5WHUa9tsW-f2qpLg,5184
|
11
|
-
abstract_webtools/url_grabber.py,sha256=
|
11
|
+
abstract_webtools/url_grabber.py,sha256=XEMGEs3F2xYgevB1MV93ozsETbGBHzX3GYWLFCSdsI0,13596
|
12
12
|
abstract_webtools/url_grabber_new.py,sha256=xb23qo4anOY0Ax3CAfaHJ8s5VEz61Sinh-XpEDFW7Is,3621
|
13
13
|
abstract_webtools/managers/__init__.py,sha256=RXQAK5z9nYlocM91P2OC4jR352-MiqT5bAi4xZl7_FU,470
|
14
14
|
abstract_webtools/managers/allss.py,sha256=IBhlyRQHfK-BtwUnSEbIPqlI1MtZ8-XsdaHv0b91HQ0,269
|
@@ -47,7 +47,7 @@ abstract_webtools/managers/soupManager/soupManager.py,sha256=6vWYnZGuimStbNiuH_V
|
|
47
47
|
abstract_webtools/managers/urlManager/__init__.py,sha256=gaJCHeK91Z-eYsBnxgdhbIUten1-gbx-zqx70R6ag-Y,26
|
48
48
|
abstract_webtools/managers/urlManager/urlManager (Copy).py,sha256=vCFuLADmv3h7icaaoAsImGqb_49VizPY_ZvMl-C7PYk,7756
|
49
49
|
abstract_webtools/managers/urlManager/urlManager.py,sha256=vY4KQXtcrlC2YtlultxQpVe581l5kAuT5VGA0WrI16g,8945
|
50
|
-
abstract_webtools-0.1.6.
|
51
|
-
abstract_webtools-0.1.6.
|
52
|
-
abstract_webtools-0.1.6.
|
53
|
-
abstract_webtools-0.1.6.
|
50
|
+
abstract_webtools-0.1.6.152.dist-info/METADATA,sha256=gLddwg9EA2CHVqQiX9eyMwbe3ozu0z4ragCnLvt3Fp0,16573
|
51
|
+
abstract_webtools-0.1.6.152.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
52
|
+
abstract_webtools-0.1.6.152.dist-info/top_level.txt,sha256=2DMJ7RmjTcjCsa-uwAV0K6eXXlIIkFDEjBLg_uyCmCI,18
|
53
|
+
abstract_webtools-0.1.6.152.dist-info/RECORD,,
|
File without changes
|
{abstract_webtools-0.1.6.151.dist-info → abstract_webtools-0.1.6.152.dist-info}/top_level.txt
RENAMED
File without changes
|