mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-13 06:34:25 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

new generic_html parser for extracting hrefs

Browse source
This commit is contained in:
Nick Sweeting 2020-08-18 08:29:05 -04:00
parent a682a9c478
commit 15efb2d5ed
5 changed files with 106 additions and 39 deletions
Download patch file Download diff file Expand all files Collapse all files

6
archivebox/main.py
View file

@ -548,7 +548,7 @@ def add(urls: Union[str, List[str]],
# save verbatim args to sources
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, root_url=None)
# If we're going one level deeper, download each link and look for more links
new_links_depth = []
@ -556,9 +556,9 @@ def add(urls: Union[str, List[str]],
log_crawl_started(new_links)
for new_link in new_links:
downloaded_file = save_file_as_source(new_link.url, filename=f'{new_link.timestamp}-crawl-{new_link.domain}.txt', out_dir=out_dir)
new_links_depth += parse_links_from_source(downloaded_file)
new_links_depth += parse_links_from_source(downloaded_file, root_url=new_link.url)
imported_links = new_links + new_links_depth
imported_links = list({link.url: link for link in (new_links + new_links_depth)}.values())
all_links, new_links = dedupe_links(all_links, imported_links)
write_main_index(links=all_links, out_dir=out_dir, finished=not new_links)