datamarket 0.7.107__tar.gz → 0.7.108__tar.gz

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.

Potentially problematic release.


This version of datamarket might be problematic. Click here for more details.

Files changed (35) hide show
  1. {datamarket-0.7.107 → datamarket-0.7.108}/PKG-INFO +1 -1
  2. {datamarket-0.7.107 → datamarket-0.7.108}/pyproject.toml +1 -1
  3. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/interfaces/proxy.py +12 -0
  4. {datamarket-0.7.107 → datamarket-0.7.108}/LICENSE +0 -0
  5. {datamarket-0.7.107 → datamarket-0.7.108}/README.md +0 -0
  6. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/__init__.py +0 -0
  7. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/exceptions/__init__.py +0 -0
  8. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/exceptions/main.py +0 -0
  9. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/interfaces/__init__.py +0 -0
  10. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/interfaces/alchemy.py +0 -0
  11. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/interfaces/aws.py +0 -0
  12. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/interfaces/azure.py +0 -0
  13. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/interfaces/drive.py +0 -0
  14. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/interfaces/ftp.py +0 -0
  15. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/interfaces/nominatim.py +0 -0
  16. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/interfaces/peerdb.py +0 -0
  17. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/interfaces/tinybird.py +0 -0
  18. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/params/__init__.py +0 -0
  19. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/params/nominatim.py +0 -0
  20. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/utils/__init__.py +0 -0
  21. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/utils/airflow.py +0 -0
  22. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/utils/alchemy.py +0 -0
  23. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/utils/main.py +0 -0
  24. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/utils/nominatim.py +0 -0
  25. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/utils/playwright/__init__.py +0 -0
  26. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/utils/playwright/async_api.py +0 -0
  27. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/utils/playwright/sync_api.py +0 -0
  28. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/utils/selenium.py +0 -0
  29. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/utils/soda.py +0 -0
  30. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/utils/strings/__init__.py +0 -0
  31. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/utils/strings/normalization.py +0 -0
  32. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/utils/strings/obfuscation.py +0 -0
  33. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/utils/strings/standardization.py +0 -0
  34. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/utils/typer.py +0 -0
  35. {datamarket-0.7.107 → datamarket-0.7.108}/src/datamarket/utils/types.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.3
2
2
  Name: datamarket
3
- Version: 0.7.107
3
+ Version: 0.7.108
4
4
  Summary: Utilities that integrate advanced scraping knowledge into just one library.
5
5
  License: GPL-3.0-or-later
6
6
  Author: DataMarket
@@ -1,6 +1,6 @@
1
1
  [tool.poetry]
2
2
  name = "datamarket"
3
- version = "0.7.107"
3
+ version = "0.7.108"
4
4
  description = "Utilities that integrate advanced scraping knowledge into just one library."
5
5
  authors = ["DataMarket <techsupport@datamarket.es>"]
6
6
  license = "GPL-3.0-or-later"
@@ -1,3 +1,6 @@
1
+ ########################################################################################################################
2
+ # IMPORTS
3
+
1
4
  import logging
2
5
  import random
3
6
  import time
@@ -10,12 +13,18 @@ from stem.control import Controller
10
13
 
11
14
  from datamarket.exceptions import EnsureNewIPTimeoutError, NoWorkingProxiesError
12
15
 
16
+ ########################################################################################################################
17
+ # SETUP
18
+
13
19
  logger = logging.getLogger(__name__)
14
20
  logging.getLogger("stem").setLevel(logging.WARNING)
15
21
 
16
22
  PROXY_ROTATION_INTERVAL = timedelta(minutes=10)
17
23
  PROXY_ROTATION_TIMEOUT_SECONDS = int(PROXY_ROTATION_INTERVAL.total_seconds())
18
24
 
25
+ ########################################################################################################################
26
+ # CLASSES
27
+
19
28
 
20
29
  class ProxyInterface:
21
30
  """
@@ -249,7 +258,9 @@ class ProxyInterface:
249
258
  # Handle both timedelta and numeric seconds for backward compatibility
250
259
  if proxy_rotation_interval:
251
260
  retrying = tenacity.Retrying(
261
+ wait=tenacity.wait_fixed(cooldown_seconds),
252
262
  stop=tenacity.stop_after_delay(proxy_rotation_interval),
263
+ before_sleep=tenacity.before_sleep_log(logger, logging.INFO),
253
264
  reraise=True,
254
265
  )
255
266
  entry = retrying(_find_working_entry)
@@ -321,6 +332,7 @@ class ProxyInterface:
321
332
  raise NoWorkingProxiesError("No working proxies available")
322
333
 
323
334
  def _wait_for_new_ip(self, entry, baseline, timeout, interval, check_timeout):
335
+ logger.info("Refreshing proxy IP...")
324
336
  start = time.time()
325
337
  while time.time() - start < timeout:
326
338
  host, port, user, pwd = entry
File without changes
File without changes