Skip to content

Bulk asynchronous downloader for multiple file hosts

refactor: named scrape tasks

NTFSvolume3cf68fd5010e
diff --git a/cyberdrop_dl/aio.py b/cyberdrop_dl/aio.py
index f0404b680..35da46546 100644
--- a/cyberdrop_dl/aio.py
+++ b/cyberdrop_dl/aio.py
@@ -62,6 +62,8 @@ class EagerTaskGroup(asyncio.TaskGroup):
return await coro
run = lazy()
+ run.__name__ = coro.__name__
+ run.__repr__ = coro.__repr__
else:
run = coro
diff --git a/cyberdrop_dl/crawlers/crawler.py b/cyberdrop_dl/crawlers/crawler.py
index 9ca35d76d..7714e75e6 100644
--- a/cyberdrop_dl/crawlers/crawler.py
+++ b/cyberdrop_dl/crawlers/crawler.py
@@ -448,7 +448,7 @@ class Crawler(HTTPMixin, HLSMixin, ABC):
lookup = url.path_qs if self.__url_config__.ignore_fragment else _path_qs_frag(url)
if lookup in self._scraped_items:
- logger.info(f"Skipping {url} as it has already been scrapped")
+ logger.info("Skipping %s as it has already been scrapped", url)
return
self._scraped_items.add(lookup)
diff --git a/cyberdrop_dl/scrape_mapper.py b/cyberdrop_dl/scrape_mapper.py
index f55bfdcbb..c83ab5727 100644
--- a/cyberdrop_dl/scrape_mapper.py
+++ b/cyberdrop_dl/scrape_mapper.py
@@ -304,12 +304,12 @@ class ScrapeMapper:
await crawler.__async_init__()
if crawler.__url_config__.trim:
scrape_item.url = remove_trailing_slash(scrape_item.url)
- self.task_mngr.scrape.create_task(crawler.run(scrape_item))
+ self.task_mngr.scrape.create_task(crawler.run(scrape_item), name=str(scrape_item.url))
return
if not self._real_debrid.disabled and self._real_debrid.api.is_supported(scrape_item.url):
logger.info(f"Using RealDebrid for unsupported URL: {scrape_item.url}")
- self.task_mngr.scrape.create_task(self._real_debrid.run(scrape_item))
+ self.task_mngr.scrape.create_task(self._real_debrid.run(scrape_item), name=str(scrape_item.url))
return
try: