Mirrors/ArchiveBox
2
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox synced 2024-11-23 04:33:11 +00:00
Code Issues Projects Releases Packages Wiki Activity

Merge pull request #362 from cdvv7788/add-fix

Browse source 
Add fix
This commit is contained in:
Nick Sweeting 2020-07-13 16:04:28 -04:00 committed by GitHub
commit 175e6fa3d0
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 9 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
archivebox/index/__init__.py
View file

@ -292,7 +292,6 @@ def dedupe_links(existing_links: List[Link],
new_links: List[Link]) -> Tuple[List[Link], List[Link]]: new_links: List[Link]) -> Tuple[List[Link], List[Link]]:
from ..parsers import parse_links from ..parsers import parse_links
# merge existing links in out_dir and new links # merge existing links in out_dir and new links
all_links = validate_links(existing_links + new_links) all_links = validate_links(existing_links + new_links)
all_link_urls = {link.url for link in existing_links} all_link_urls = {link.url for link in existing_links}
@ -301,6 +300,11 @@ def dedupe_links(existing_links: List[Link],
link for link in new_links link for link in new_links
if link.url not in all_link_urls if link.url not in all_link_urls
] ]
all_links_deduped = {link.url: link for link in all_links}
for i in range(len(new_links)):
if new_links[i].url in all_links_deduped.keys():
new_links[i] = all_links_deduped[new_links[i].url]
log_deduping_finished(len(new_links)) log_deduping_finished(len(new_links))
return all_links, new_links return all_links, new_links

10
archivebox/main.py
View file

@ -520,18 +520,16 @@ def add(urls: Union[str, List[str]],
write_ahead_log = save_text_as_source('\n'.join(urls), filename='{ts}-import.txt', out_dir=out_dir) write_ahead_log = save_text_as_source('\n'.join(urls), filename='{ts}-import.txt', out_dir=out_dir)
new_links += parse_links_from_source(write_ahead_log) new_links += parse_links_from_source(write_ahead_log)
all_links, new_links = dedupe_links(all_links, new_links)
write_main_index(links=all_links, out_dir=out_dir, finished=not new_links)
# If we're going one level deeper, download each link and look for more links # If we're going one level deeper, download each link and look for more links
new_links_depth = []
if new_links and depth == 1: if new_links and depth == 1:
log_crawl_started(new_links) log_crawl_started(new_links)
for new_link in new_links: for new_link in new_links:
downloaded_file = save_file_as_source(new_link.url, filename='{ts}-crawl-{basename}.txt', out_dir=out_dir) downloaded_file = save_file_as_source(new_link.url, filename='{ts}-crawl-{basename}.txt', out_dir=out_dir)
new_links += parse_links_from_source(downloaded_file) new_links_depth += parse_links_from_source(downloaded_file)
all_links, new_links = dedupe_links(all_links, new_links) all_links, new_links = dedupe_links(all_links, new_links + new_links_depth)
write_main_index(links=all_links, out_dir=out_dir, finished=not new_links) write_main_index(links=all_links, out_dir=out_dir, finished=not new_links)
if index_only: if index_only:
return all_links return all_links