Patch by Martin Panter.
### connect and send the server a path
req = urllib.request.urlopen('http://www.some-server.out-there'
'/cgi-bin/some-cgi-script', data=qs)
- msg, hdrs = req.read(), req.info()
+ with req:
+ msg, hdrs = req.read(), req.info()
Note that in general for percent-encoded POST operations, query strings must be
quoted using :func:`urllib.parse.urlencode`. For example, to send
The simplest way to use urllib.request is as follows::
import urllib.request
- response = urllib.request.urlopen('http://python.org/')
- html = response.read()
+ with urllib.request.urlopen('http://python.org/') as response:
+ html = response.read()
If you wish to retrieve a resource via URL and store it in a temporary location,
you can do so via the :func:`~urllib.request.urlretrieve` function::
import urllib.request
req = urllib.request.Request('http://www.voidspace.org.uk')
- response = urllib.request.urlopen(req)
- the_page = response.read()
+ with urllib.request.urlopen(req) as response:
+ the_page = response.read()
Note that urllib.request makes use of the same Request interface to handle all URL
schemes. For example, you can make an FTP request like so::
data = urllib.parse.urlencode(values)
data = data.encode('utf-8') # data should be bytes
req = urllib.request.Request(url, data)
- response = urllib.request.urlopen(req)
- the_page = response.read()
+ with urllib.request.urlopen(req) as response:
+ the_page = response.read()
Note that other encodings are sometimes required (e.g. for file upload from HTML
forms - see `HTML Specification, Form Submission
data = urllib.parse.urlencode(values)
data = data.encode('utf-8')
req = urllib.request.Request(url, data, headers)
- response = urllib.request.urlopen(req)
- the_page = response.read()
+ with urllib.request.urlopen(req) as response:
+ the_page = response.read()
The response also has two useful methods. See the section on `info and geturl`_
which comes after we have a look at what happens when things go wrong.
# Retrieve a single page and report the url and contents
def load_url(url, timeout):
- conn = urllib.request.urlopen(url, timeout=timeout)
- return conn.readall()
+ with urllib.request.urlopen(url, timeout=timeout) as conn:
+ return conn.read()
# We can use a with statement to ensure threads are cleaned up promptly
with concurrent.futures.ThreadPoolExecutor(max_workers=5) as executor:
it. ::
>>> import urllib.request
- >>> f = urllib.request.urlopen('http://www.python.org/')
- >>> print(f.read(300))
+ >>> with urllib.request.urlopen('http://www.python.org/') as f:
+ ... print(f.read(300))
+ ...
b'<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">\n\n\n<html
xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">\n\n<head>\n
>>> import urllib.request
>>> req = urllib.request.Request(url='https://localhost/cgi-bin/test.cgi',
... data=b'This data is passed to stdin of the CGI')
- >>> f = urllib.request.urlopen(req)
- >>> print(f.read().decode('utf-8'))
+ >>> with urllib.request.urlopen(req) as f:
+ ... print(f.read().decode('utf-8'))
+ ...
Got Data: "This data is passed to stdin of the CGI"
The code for the sample CGI used in the above example is::
import urllib.request
DATA=b'some data'
req = urllib.request.Request(url='http://localhost:8080', data=DATA,method='PUT')
- f = urllib.request.urlopen(req)
+ with urllib.request.urlopen(req) as f:
+ pass
print(f.status)
print(f.reason)
>>> import urllib.request
>>> import urllib.parse
>>> params = urllib.parse.urlencode({'spam': 1, 'eggs': 2, 'bacon': 0})
- >>> f = urllib.request.urlopen("http://www.musi-cal.com/cgi-bin/query?%s" % params)
- >>> print(f.read().decode('utf-8'))
+ >>> url = "http://www.musi-cal.com/cgi-bin/query?%s" % params
+ >>> with urllib.request.urlopen(url) as f:
+ ... print(f.read().decode('utf-8'))
+ ...
The following example uses the ``POST`` method instead. Note that params output
from urlencode is encoded to bytes before it is sent to urlopen as data::
>>> request = urllib.request.Request("http://requestb.in/xrbl82xr")
>>> # adding charset parameter to the Content-Type header.
>>> request.add_header("Content-Type","application/x-www-form-urlencoded;charset=utf-8")
- >>> f = urllib.request.urlopen(request, data)
- >>> print(f.read().decode('utf-8'))
+ >>> with urllib.request.urlopen(request, data) as f:
+ ... print(f.read().decode('utf-8'))
+ ...
The following example uses an explicitly specified HTTP proxy, overriding
environment settings::
>>> import urllib.request
>>> proxies = {'http': 'http://proxy.example.com:8080/'}
>>> opener = urllib.request.FancyURLopener(proxies)
- >>> f = opener.open("http://www.python.org")
- >>> f.read().decode('utf-8')
+ >>> with opener.open("http://www.python.org") as f:
+ ... f.read().decode('utf-8')
+ ...
The following example uses no proxies at all, overriding environment settings::
>>> import urllib.request
>>> opener = urllib.request.FancyURLopener({})
- >>> f = opener.open("http://www.python.org/")
- >>> f.read().decode('utf-8')
+ >>> with opener.open("http://www.python.org/") as f:
+ ... f.read().decode('utf-8')
+ ...
Legacy interface
from URLs and :mod:`smtplib` for sending mail::
>>> from urllib.request import urlopen
- >>> for line in urlopen('http://tycho.usno.navy.mil/cgi-bin/timer.pl'):
- ... line = line.decode('utf-8') # Decoding the binary data to text.
- ... if 'EST' in line or 'EDT' in line: # look for Eastern Time
- ... print(line)
+ >>> with urlopen('http://tycho.usno.navy.mil/cgi-bin/timer.pl') as response:
+ ... for line in response:
+ ... line = line.decode('utf-8') # Decoding the binary data to text.
+ ... if 'EST' in line or 'EDT' in line: # look for Eastern Time
+ ... print(line)
<BR>Nov. 25, 09:43:32 PM EST
projects / python / commitdiff