def update_archive_data(import_path=None, resume=None):
"""The main ArchiveBox entrancepoint. Everything starts here."""
check_dependencies()
# Step 1: Load list of links from the existing index
# merge in and dedupe new links from import_path
all_links, new_links = load_links_index(out_dir=OUTPUT_DIR,
import_path=import_path)
# Step 2: Write updated index with deduped old and new links back to disk
write_links_index(out_dir=OUTPUT_DIR, links=all_links)
# Step 3: Run the archive methods for each link
links = new_links if ONLY_NEW else all_links
log_archiving_started(len(links), resume)
idx, link = 0, 0
try:
for idx, link in enumerate(links_after_timestamp(links, resume)):
link_dir = os.path.join(ARCHIVE_DIR, link['timestamp'])
archive_link(link_dir, link)
except KeyboardInterrupt:
log_archiving_paused(len(links), idx, link and link['timestamp'])
raise SystemExit(0)
except:
print()
raise
log_archiving_finished(len(links))
# Step 4: Re-write links index with updated titles, icons, and resources
all_links, _ = load_links_index(out_dir=OUTPUT_DIR)
write_links_index(out_dir=OUTPUT_DIR, links=all_links, finished=True)
def update_archive_data(import_path=None, resume=None):
"""Main entrance point
"""
# step 1: load list of links form existing index
# merge in and dedupe new links from import path
all_links, new_links = load_links_index(out_dir=OUTPUT_DIR,
import_path=import_path)
# step 2: write updated index with deduped old and new links back to disk
write_links_index(out_dir=OUTPUT_DIR, links=all_links)
# step 3: run the archive methods for each link
links = new_links if ONLY_NEW else all_links
log_archiving_started(len(links), resume)
# important note here - iterate through (if keyboard interrupt print out the stop)
idx, link = 0, 0
try:
for idx, link in enumerate(links_after_timestamp(links, resume)):
links_dir = os.path.join(ARCHIVE_DIR, link['timestamp'])
archive_link(link_dir, link)
except KeyboardInterrupt:
log_archiving_paused(len(links), idx, link and link['timestamp'])
raise SystemExit(0)
except:
print()
raise
log_archiving_finished(len(links))
# Step 4: Re-write links index with updated titles, icons, and resources
all_links, _ = load_links_index(out_dir=OUTPUT_DIR)
write_links_index(out_dir=OUTPUT_DIR, links=all_links, finished=True)
def y_main(url):
### Handle CLI arguments
# ./archive bookmarks.html
# ./archive 1523422111.234
resume = None
### Set up output folder
if not os.path.exists(OUTPUT_DIR):
os.makedirs(OUTPUT_DIR)
### Handle ingesting urls from a remote file/feed
# (e.g. if an RSS feed URL is used as the import path)
if url and any(
url.startswith(s) for s in ('http://', 'https://', 'ftp://')):
import_path = save_remote_source(url)
### Run the main archive update process
"""The main ArchiveBox entrancepoint. Everything starts here."""
links = [{
'url': url,
'timestamp': str(datetime.now().timestamp()),
'title': None,
'tags': '',
'sources': [import_path]
}]
log_archiving_started(len(links), resume)
idx, link = 0, 0
try:
for idx, link in enumerate(links_after_timestamp(links, resume)):
link_dir = os.path.join(ARCHIVE_DIR, link['timestamp'])
archive_link(link_dir, link)
except KeyboardInterrupt:
log_archiving_paused(len(links), idx, link and link['timestamp'])
raise SystemExit(0)
except:
print()
raise
log_archiving_finished(len(links))
# Step 4: Re-write links index with updated titles, icons, and resources
all_links, _ = load_links_index(out_dir=OUTPUT_DIR)
write_links_index(out_dir=OUTPUT_DIR, links=all_links, finished=True)
