Skip to content

Gzipped ARCs are now supported. #31

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

Open
jordan-dlh wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Gzipped ARCs are now supported. #31

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
10 changes: 9 additions & 1 deletion warc/arc.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@
import StringIO
import warnings

from . import gzip2
from .utils import CaseInsensitiveDict

ARC1_HEADER_RE = re.compile('(?P<url>\S*)\s(?P<ip_address>\S*)\s(?P<date>\S*)\s(?P<content_type>\S*)\s(?P<length>\S*)')
Expand Down Expand Up @@ -206,7 +207,7 @@ def __str__(self):


class ARCFile(object):
def __init__(self, filename=None, mode=None, fileobj=None, version = None, file_headers = {}):
def __init__(self, filename=None, mode=None, fileobj=None, compress=None, version = None, file_headers = {}):
"""
Initialises a file like object that can be used to read or
write Arc files. Works for both version 1 or version 2.
Expand Down Expand Up @@ -251,6 +252,13 @@ def __init__(self, filename=None, mode=None, fileobj=None, version = None, file_
"""
if fileobj is None:
fileobj = __builtin__.open(filename, mode or "rb")
mode = fileobj.mode
# initiaize compress based on filename, if not already specified
if compress is None and filename and filename.endswith(".gz"):
compress = True

if compress:
fileobj = gzip2.GzipFile(fileobj=fileobj, mode=mode)
self.fileobj = fileobj

if version != None and int(version) not in (1, 2):
Expand Down