Parallel execution optimization (#1897)

* Connection failure fix: removed futures, added semaphores

* Additional fixes

* Tqdm replace to alive_progress, poetry update

* Self-check mode fix, tests fixes

* Sites checks fixes (#1896)

* Fixed incorrect site names, added method to compare sites
This commit is contained in:
Soxoj
2024-11-26 13:55:12 +01:00
committed by GitHub
parent b370bc4c44
commit 324c118530
10 changed files with 1301 additions and 1134 deletions
+5 -3
View File
@@ -3,7 +3,7 @@ import json
import random
import re
import tqdm.asyncio
import alive_progress
from mock import Mock
import requests
@@ -181,7 +181,7 @@ if __name__ == '__main__':
raw_maigret_data = json.dumps({site.name: site.json for site in sites_subset})
new_sites = []
for site in tqdm.asyncio.tqdm(urls):
for site in alive_progress.alive_it(urls):
site_lowercase = site.lower()
domain_raw = URL_RE.sub('', site_lowercase).strip().strip('/')
@@ -271,7 +271,9 @@ if __name__ == '__main__':
future = asyncio.ensure_future(check_coro)
tasks.append(future)
for f in tqdm.asyncio.tqdm.as_completed(tasks, timeout=TIMEOUT):
with alive_progress(len(tasks), title='Checking sites') as progress:
for f in asyncio.as_completed(tasks):
progress()
try:
loop.run_until_complete(f)
except asyncio.exceptions.TimeoutError: