mirrors/archon
1
0
Fork 0
mirror of https://github.com/coleam00/Archon.git synced 2025-12-24 02:39:17 -05:00
Code Issues Packages Projects Releases Wiki Activity

fix: Resolve syntax error from merge conflict resolution

Browse Source 
- Fixed duplicate else statement in crawling_service.py
- Corrected indentation for extracted links processing logic
- Syntax now validates successfully
This commit is contained in:
leex279
2025-09-20 09:33:47 +02:00
parent 8072066ee6
commit 2be44d1bf4
1 changed files with 16 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
python/src/server/services/crawling/crawling_service.py
View File

@@ -812,23 +812,23 @@ class CrawlingService:
start_progress=10,
end_progress=20,
)
else:
# Use normal batch crawling for non-discovery or when max_depth is 1
logger.info(f"Crawling {len(extracted_links)} extracted links from {url}")
batch_results = await self.crawl_batch_with_progress(
extracted_links,
max_concurrent=request.get('max_concurrent'), # None -> use DB settings
progress_callback=await self._create_crawl_progress_callback("crawling"),
)
# Combine original text file results with batch results
crawl_results.extend(batch_results)
crawl_type = "link_collection_with_crawled_links"
logger.info(f"Link collection crawling completed: {len(crawl_results)} total results (1 text file + {len(batch_results)} extracted links)")
else:
logger.info(f"No valid links found in link collection file: {url}")
logger.info(f"Text file crawling completed: {len(crawl_results)} results")
# Use normal batch crawling for non-discovery targets
logger.info(f"Crawling {len(extracted_links)} extracted links from {url}")
batch_results = await self.crawl_batch_with_progress(
extracted_links,
max_concurrent=request.get('max_concurrent'), # None -> use DB settings
progress_callback=await self._create_crawl_progress_callback("crawling"),
)
# Combine original text file results with batch results
crawl_results.extend(batch_results)
crawl_type = "link_collection_with_crawled_links"
logger.info(f"Link collection crawling completed: {len(crawl_results)} total results (1 text file + {len(batch_results)} extracted links)")
else:
logger.info(f"No valid links found in link collection file: {url}")
logger.info(f"Text file crawling completed: {len(crawl_results)} results")
elif self.url_handler.is_sitemap(url):
# Handle sitemaps