Python I/O
Jump to navigation
Jump to search
Command-line arguments
Command line arguments are placed in the list sys.argv.
import sys
command = sys.argv[0]
firstArg = sys.argv[1]
secondArg = sys.argv[2]
There is also a getopt module.
More here: http://www.faqs.org/docs/diveintopython/kgp_commandline.html
Reading and writing files
output = open('/tmp/spam', 'w') # Create output file ('w' means write).
input = open('data', 'r') # Create input file ('r' means read).
S = input.read( ) # Read entire file into a single string.
S = input.read(N) # Read N bytes (1 or more).
S = input.readline( ) # Read next line (through end-line marker).
L = input.readlines( ) # Read entire file into list of line strings.
output.write(S) # Write string S into file.
output.writelines(L) # Write all line strings in list L into file.
output.close( ) # Manual close (done for you when file collected).
Manipulating files
See this page for more: http://docs.python.org/lib/os-file-dir.html
import os
os.access(fileName, os.F_OK) # returns True if file exists
os.access(fileName, os.R_OK) # returns True if file is readable
os.access(fileName, os.W_OK) # returns True if file is writeable
os.access(fileName, os.X_OK) # returns True if file is executable
os.getcwd() # return a path of current working directory
os.mkdir(newName) # create a directory
os.listdir(dirName) # directory listing
os.rename(oldName, newName) # move/rename a file
os.remove(fileName) # unlink a file
Parsing a text file line-by-line
for line in file('/tmp/test/txt', 'r'):
do something with line, like
args = line.strip().split()
print statement
print spam, ham # Print objects to sys.stdout; add a space between.
print spam, ham, # Same, but don't add newline at end of text.
print >> myfile, spam, ham # Send text to myfile.write, not to sys.stdout.write.
Formatted printing
x = 42
y = 3.14
z = "george"
print 'result = %d' % x # prints: result = 42
print 'answers are: %d %f' % (x,y) # prints: answers are: 42 3.14
print 'hello %s' % z # prints: hello george
urllib module for web access
import urllib
# open a url for reading
page = urlopen('http://www.python.org')
page.readline( ) # '<HTML>\012'
# download a page directly
urlretrieve('http://www.python.org/', 'wwwpython.html')
HTML parsing example
# extracts urls from a web page
import HTMLParser, urllib, urlparse
class LinksParser(HTMLParser.HTMLParser):
def __init__(self):
HTMLParser.HTMLParser.__init__(self)
self.seen = {}
def handle_starttag(self, tag, attributes):
if tag != 'a': return
for name, value in attributes:
if name == 'href' and value not in self.seen:
self.seen[value] = True
pieces = urlparse.urlparse(value)
if pieces[0] != 'http': return
print urlparse.urlunparse(pieces)
return
p = LinksParser( )
f = urllib.urlopen('http://www.python.org/index.html')
BUFSIZE = 8192
while True:
data = f.read(BUFSIZE)
if not data: break
p.feed(data)
p.close( )
XML parsing example
<catalog>
<book isbn="1-56592-724-9">
<title>The Cathedral & the Bazaar</title>
<author>Eric S. Raymond</author>
</book>
<book isbn="1-56592-051-1">
<title>Making TeX Work</title>
<author>Norman Walsh</author>
</book>
<!-- imagine more entries here... -->
</catalog>
import xml.sax, xml.sax.handler
class BookHandler(xml.sax.handler.ContentHandler):
def __init__(self):
self.inTitle = 0 # handle XML parser events
self.mapping = {} # a state machine model
def startElement(self, name, attributes):
if name == "book": # on start book tag
self.buffer = "" # save ISBN for dict key
self.isbn = attributes["isbn"]
elif name == "title": # on start title tag
self.inTitle = 1 # save title text to follow
def characters(self, data):
if self.inTitle: # on text within tag
self.buffer += data # save text if in title
def endElement(self, name):
if name == "title":
self.inTitle = 0 # on end title tag
self.mapping[self.isbn] = self.buffer # store title text in dict
parser = xml.sax.make_parser( )
handler = BookHandler( )
parser.setContentHandler(handler)
parser.parse('books.xml')
print handler.mapping
MySQL access
http://www.kitebird.com/articles/pydbapi.html
import MySQLdb
conn = MySQLdb.connect(host = "localhost", user = "barney", passwd = "xxxxxx", db = "bts")
cursor = conn.cursor()
cursor.execute("select the_date, close from stocks where issue = 'a'")
for row in cursor.fetchall():
print row
cursor.close()
conn.close()
If using INNODB tables, you need to throw in a commit statement for the connection before closing it:
conn = MySQLdb.connect(host = "localhost", user = "barney", passwd = "xxxxxx", db = "schedule")
cursor = conn.cursor()
cursor.execute("insert into users (name, pass) values ('Herman', '2909e93f30ac902891093')")
cursor.close()
conn.commit() <== don't forget this!
conn.close()
Windows Tip
When starting a command-line python script by clicking on it in Winodws, use the raw_input() function at the end to keep the window open. Hitting return will close it.
Send E-mail
import smtplib
import os
from email.MIMEMultipart import MIMEMultipart
from email.MIMEBase import MIMEBase
from email.MIMEText import MIMEText
from email.Utils import COMMASPACE, formatdate
from email import Encoders
def sendMail(send_from, send_to, subject, text, files=[], server="localhost"):
assert type(send_to)==list
assert type(files)==list
msg = MIMEMultipart()
msg['From'] = send_from
msg['To'] = COMMASPACE.join(send_to)
msg['Date'] = formatdate(localtime=True)
msg['Subject'] = subject
msg.attach( MIMEText(text) )
for f in files:
part = MIMEBase('application', "octet-stream")
part.set_payload( open(file,"rb").read() )
Encoders.encode_base64(part)
part.add_header('Content-Disposition', 'attachment; filename="%s"' % os.path.basename(f))
msg.attach(part)
smtp = smtplib.SMTP(server)
smtp.sendmail(send_from, send_to, msg.as_string())
smtp.close()