Has some errors:
#========================================================
# Get filenames of the apps directory as bytestrings
path = os.listdir( b'/home/nikos/public_html/data/apps/' )
# iterate over all filenames in the apps directory
for filename in path:
# Grabbing just the filename from path
try:
# Is this name encoded in utf-8?
filename.decode('utf-8')
except UnicodeDecodeError:
# Decoding from UTF-8 failed, which means that the name is not
valid utf-8
# It appears that this filename is encoded in greek-iso, so
decode from that and re-encode to utf-8
new_filename = filename.decode('iso-8859-7').encode('utf-8')
# rename filename form greek bytestreams --> utf-8 bytestreams
old_path = b'/home/nikos/public_html/data/apps/' + b'filename')
new_path = b'/home/nikos/public_html/data/apps/' +
b'new_filename')
os.rename( old_path, new_path )
#========================================================
# Get filenames of the apps directory as unicode
path = os.listdir( '/home/nikos/public_html/data/apps/' )
# Load'em
for filename in path:
try:
# Check the presence of a file against the database and insert
if it doesn't exist
cur.execute('''SELECT url FROM files WHERE url = %s''',
(filename,) )
data = cur.fetchone() #filename is unique, so should
only be one
if not data:
# First time for file; primary key is automatic, hit is
defaulted
cur.execute('''INSERT INTO files (url, host, lastvisit)
VALUES (%s, %s, %s)''', (filename, host, lastvisit) )
except pymysql.ProgrammingError as e:
print( repr(e) )
#========================================================
path = os.listdir( '/home/nikos/public_html/data/apps/' )
filenames = ()
# Build a set of 'path/to/filename' based on the objects of path dir
for filename in path
filenames.add( filename )
# Delete spurious
cur.execute('''SELECT url FROM files''')
data = cur.fetchall()
# Check database's filenames against path's filenames
for filename in data:
if filename not in filenames
cur.execute('''DELETE FROM files WHERE url = %s''', (filename,)
)
-------------------------------
The only problem now is the bytestrings:
ni...@superhost.gr [~/www/cgi-bin]# [Thu Jun 06 23:50:42 2013] [error] [client
79.103.41.173] File "files.py", line 78
[Thu Jun 06 23:50:42 2013] [error] [client 79.103.41.173] old_path =
b'/home/nikos/public_html/data/apps/' + b'filename')
[Thu Jun 06 23:50:42 2013] [error] [client 79.103.41.173]
^
[Thu Jun 06 23:50:42 2013] [error] [client 79.103.41.173] SyntaxError: invalid
syntax
Dont know how to add a bytestremed path to a bytestream filename
--
http://mail.python.org/mailman/listinfo/python-list
