import gzip,re
file = "/arcs/some.arc.gz"
ARC_PATTERN = re.compile("(^.*:[^ ]*)\\s([0-9.]+)\\s(\\d+)\\s(\\S+)\\s(\\d+)$")
def readchunk(fp):
meta = ARC_PATTERN.match(fp.readline()).groups()
page = fp.read(long(meta[4])+1)
return (meta,page)
def main():
f = gzip.open(file,'rb')
print readchunk(f)
print readchunk(f)
if __name__ == '__main__':
main()
windows下注意加rb,不然会坑。