abstract-webtools 0.1.4.11__py3-none-any.whl → 0.1.4.12__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/abstract_webtools.py +10 -3
- {abstract_webtools-0.1.4.11.dist-info → abstract_webtools-0.1.4.12.dist-info}/METADATA +1 -1
- {abstract_webtools-0.1.4.11.dist-info → abstract_webtools-0.1.4.12.dist-info}/RECORD +6 -6
- {abstract_webtools-0.1.4.11.dist-info → abstract_webtools-0.1.4.12.dist-info}/LICENSE +0 -0
- {abstract_webtools-0.1.4.11.dist-info → abstract_webtools-0.1.4.12.dist-info}/WHEEL +0 -0
- {abstract_webtools-0.1.4.11.dist-info → abstract_webtools-0.1.4.12.dist-info}/top_level.txt +0 -0
@@ -517,7 +517,7 @@ class SafeRequest:
|
|
517
517
|
self.wait_between_requests()
|
518
518
|
|
519
519
|
for _ in range(self.max_retries):
|
520
|
-
|
520
|
+
try:
|
521
521
|
response = self.session.get(url=self.url_manager.correct_url, timeout=10) # 10 seconds timeout
|
522
522
|
if response.status_code == 200:
|
523
523
|
self.last_request_time = get_time_stamp()
|
@@ -525,10 +525,17 @@ class SafeRequest:
|
|
525
525
|
elif response.status_code == 429:
|
526
526
|
logging.warning(f"Rate limited by {self.url_manager.correct_url}. Retrying...")
|
527
527
|
get_sleep(5) # adjust this based on the server's rate limit reset time
|
528
|
+
except requests.Timeout as e:
|
529
|
+
logging.error(f"Request to {cleaned_url} timed out: {e}")
|
530
|
+
except requests.ConnectionError:
|
531
|
+
logging.error(f"Connection error for URL {cleaned_url}.")
|
532
|
+
except requests.Timeout:
|
533
|
+
logging.error(f"Request timeout for URL {cleaned_url}.")
|
534
|
+
except requests.RequestException as e:
|
535
|
+
logging.error(f"Request exception for URL {cleaned_url}: {e}")
|
536
|
+
|
528
537
|
logging.error(f"Failed to retrieve content from {self.url_manager.correct_url} after {self.max_retries} retries.")
|
529
538
|
return None
|
530
|
-
|
531
|
-
|
532
539
|
@staticmethod
|
533
540
|
def is_valid_url(url):
|
534
541
|
"""
|
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.1
|
2
2
|
Name: abstract-webtools
|
3
|
-
Version: 0.1.4.
|
3
|
+
Version: 0.1.4.12
|
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
|
@@ -1,11 +1,11 @@
|
|
1
1
|
abstract_webtools/__init__.py,sha256=2SWEfdPDHqqjUYsOQYlaOHF644ZYcO160nWKiAjga4w,34
|
2
2
|
abstract_webtools/abstract_crawler.py,sha256=e8jVVv1_EB8poqlrdQaJ19z9Z0t8un5uc-DKnj1Ud5s,8002
|
3
|
-
abstract_webtools/abstract_webtools.py,sha256=
|
3
|
+
abstract_webtools/abstract_webtools.py,sha256=sjrsbUa4AkFD80usyU2D2Ez966N_kDt_j4hf2-c7AkQ,40159
|
4
4
|
abstract_webtools/abstract_webtools2.py,sha256=dlhhgmUTaN_NgkT6GcJMVBLuXjmW38gAOeCrKxYqytk,30685
|
5
5
|
abstract_webtools/grab_source_gui.py,sha256=w7vDsEu1IfOIzcsfWeP2IpdS3yhFA_x5IVIeLFlfppw,14708
|
6
6
|
abstract_webtools/main.py,sha256=_I7pPXPkoLZOoYGLQDrSLGhGuQt6-PVyXEHZSmglk2g,1329
|
7
|
-
abstract_webtools-0.1.4.
|
8
|
-
abstract_webtools-0.1.4.
|
9
|
-
abstract_webtools-0.1.4.
|
10
|
-
abstract_webtools-0.1.4.
|
11
|
-
abstract_webtools-0.1.4.
|
7
|
+
abstract_webtools-0.1.4.12.dist-info/LICENSE,sha256=g3WEJFiVS27HyCGRTwKSsMLyciMaGFdWcZGOe1QalZk,3877
|
8
|
+
abstract_webtools-0.1.4.12.dist-info/METADATA,sha256=d4kh-bQrfhjqlmyDnxiyoGbm7xAvsVR7ot5yOmiMcNY,8963
|
9
|
+
abstract_webtools-0.1.4.12.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
|
10
|
+
abstract_webtools-0.1.4.12.dist-info/top_level.txt,sha256=2DMJ7RmjTcjCsa-uwAV0K6eXXlIIkFDEjBLg_uyCmCI,18
|
11
|
+
abstract_webtools-0.1.4.12.dist-info/RECORD,,
|
File without changes
|
File without changes
|
File without changes
|