Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Skip early when downloading existing file #650

Merged
merged 1 commit into from
May 28, 2024
Merged

Skip early when downloading existing file #650

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
51 changes: 26 additions & 25 deletions internetarchive/files.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -226,6 +226,25 @@ def download(# noqa: max-complexity=38

parent_dir = os.path.dirname(file_path)

# Check if we should skip...
if not return_responses and os.path.exists(file_path.encode('utf-8')):
if ignore_existing:
msg = f'skipping {file_path}, file already exists.'
log.info(msg)
if verbose:
print(f' {msg}', file=sys.stderr)
return
elif checksum:
with open(file_path, 'rb') as fp:
md5_sum = utils.get_md5(fp)

if md5_sum == self.md5:
msg = f'skipping {file_path}, file already exists based on checksum.'
log.info(msg)
if verbose:
print(f' {msg}', file=sys.stderr)
return

# Retry loop
while True:
try:
Expand Down Expand Up @@ -256,35 +275,17 @@ def download(# noqa: max-complexity=38

response.raise_for_status()

# Check if we should skip...
if not return_responses and os.path.exists(file_path.encode('utf-8')):
if ignore_existing:
msg = f'skipping {file_path}, file already exists.'
log.info(msg)
if verbose:
print(f' {msg}', file=sys.stderr)
return
elif checksum:
with open(file_path, 'rb') as fp:
md5_sum = utils.get_md5(fp)

if md5_sum == self.md5:
msg = f'skipping {file_path}, file already exists based on checksum.'
# Check if we should skip based on last modified time...
if not fileobj and not return_responses and os.path.exists(file_path.encode('utf-8')):
st = os.stat(file_path.encode('utf-8'))
if st.st_mtime == last_mod_mtime:
if self.name == f'{self.identifier}_files.xml' or (st.st_size == self.size):
msg = (f'skipping {file_path}, file already exists based on '
'length and date.')
log.info(msg)
if verbose:
print(f' {msg}', file=sys.stderr)
return
elif not fileobj:
st = os.stat(file_path.encode('utf-8'))
if st.st_mtime == last_mod_mtime:
if self.name == f'{self.identifier}_files.xml' \
or (st.st_size == self.size):
msg = (f'skipping {file_path}, file already exists based on '
'length and date.')
log.info(msg)
if verbose:
print(f' {msg}', file=sys.stderr)
return

elif return_responses:
return response
Expand Down