community.general/library/get_url

#!/usr/bin/python

# (c) 2012, Jan-Piet Mens <jpmens () gmail.com>
#
# This file is part of Ansible
#
# Ansible is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# Ansible is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with Ansible.  If not, see <http://www.gnu.org/licenses/>.
#
# see examples/playbooks/get_url.yml

import shutil
import datetime
import tempfile

HAS_URLLIB2=True
try:
    import urllib2
except ImportError: 
    HAS_URLLIB2=False
HAS_URLPARSE=True

try:
    import urlparse
    import socket
except ImportError: 
    HAS_URLPARSE=False

# ==============================================================
# url handling

def url_filename(url):
    fn = os.path.basename(urlparse.urlsplit(url)[2])
    if fn == '':
        return 'index.html'
    return fn

def url_do_get(module, url, dest):
    """
    Get url and return request and info
    Credits: http://stackoverflow.com/questions/7006574/how-to-download-file-from-ftp
    """

    USERAGENT = 'ansible-httpget'
    info = dict(url=url)
    r = None
    actualdest = None

    if os.path.isdir(dest):
        urlfilename = url_filename(url)
        actualdest = "%s/%s" % (dest, urlfilename)
        module.params['path'] = actualdest
    else:
         actualdest = dest
    info['daisychain_args'] = module.params
    info['actualdest'] = actualdest

    request = urllib2.Request(url)
    request.add_header('User-agent', USERAGENT)

    if os.path.exists(actualdest):
        t = datetime.datetime.utcfromtimestamp(os.path.getmtime(actualdest))
        tstamp = t.strftime('%a, %d %b %Y %H:%M:%S +0000')
        request.add_header('If-Modified-Since', tstamp)

    try:
        r = urllib2.urlopen(request)
        info.update(r.info())
        info.update(dict(msg="OK (%s bytes)" % r.headers.get('Content-Length', 'unknown'), status=200))
    except urllib2.HTTPError, e:
        # Must not fail_json() here so caller can handle HTTP 304 unmodified
        info.update(dict(msg=str(e), status=e.code))
        return r, info
    except urllib2.URLError, e:
        code = getattr(e, 'code', -1)
        module.fail_json(msg="Request failed: %s" % str(e), status_code=code)

    return r, info

def url_get(module, url, dest):
    """
    Download url and store at dest. 
    If dest is a directory, determine filename from url.
    Return (tempfile, info about the request)
    """

    req, info = url_do_get(module, url, dest)

    # TODO: should really handle 304, but how? src file could exist (and be newer) but empty
    if info['status'] == 304:
        module.exit_json(url=url, dest=info.get('actualdest', dest), changed=False, msg=info.get('msg', ''))

    # create a temporary file and copy content to do md5-based replacement
    if info['status'] != 200:
        module.fail_json(msg="Request failed", status_code=info['status'], response=info['msg'], url=url)
    actualdest = info['actualdest']

    fd, tempname = tempfile.mkstemp()
    f = os.fdopen(fd, 'wb')
    try:
        shutil.copyfileobj(req, f)
    except Exception, err:
        os.remove(tempname)
        module.fail_json(msg="failed to create temporary content file: %s" % str(err))
    f.close()
    req.close()
    return tempname, info

# ==============================================================
# main

def main():
    
    # does this really happen on non-ancient python? 
    if not HAS_URLLIB2:
        module.fail_json(msg="urllib2 is not installed")
    if not HAS_URLPARSE:
        module.fail_json(msg="urlparse is not installed")

    module = AnsibleModule(
        # not checking because of daisy chain to file module
        check_invalid_arguments = False,
        argument_spec = dict(
            url = dict(required=True),
            dest = dict(required=True),
        )
    )
    
    url  = module.params['url']
    dest = os.path.expanduser(module.params['dest'])
    
    # download to tmpsrc
    tmpsrc, info = url_get(module, url, dest)
    md5sum_src   = None
    md5sum_dest  = None
    dest         = info['actualdest']
    
    # raise an error if there is no tmpsrc file
    if not os.path.exists(tmpsrc):
        os.remove(tmpsrc)
        module.fail_json(msg="Request failed", status_code=info['status'], response=info['msg'])
    if not os.access(tmpsrc, os.R_OK):
        os.remove(tmpsrc)
        module.fail_json( msg="Source %s not readable" % (tmpsrc))
    md5sum_src = module.md5(tmpsrc)
     
    # check if there is no dest file
    if os.path.exists(dest):
        # raise an error if copy has no permission on dest
        if not os.access(dest, os.W_OK):
            os.remove(tmpsrc)
            module.fail_json( msg="Destination %s not writable" % (dest))
        if not os.access(dest, os.R_OK):
            os.remove(tmpsrc)
            module.fail_json( msg="Destination %s not readable" % (dest))
        md5sum_dest = module.md5(dest)
    else:
        if not os.access(os.path.dirname(dest), os.W_OK):
            os.remove(tmpsrc)
            module.fail_json( msg="Destination %s not writable" % (os.path.dirname(dest)))
    
    if md5sum_src != md5sum_dest:
        try:
            shutil.copyfile(tmpsrc, dest)
        except Exception, err:
            os.remove(tmpsrc)
            module.fail_json(msg="failed to copy %s to %s: %s" % (tmpsrc, dest, str(err))) 
        changed = True
    else:
        changed = False
    
    os.remove(tmpsrc)

    # Mission complete
    module.exit_json(url=url, dest=dest, src=tmpsrc, md5sum=md5sum_src, 
        changed=changed, msg=info.get('msg',''), 
        daisychain="file", daisychain_args=info.get('daisychain_args',''))

# this is magic, see lib/ansible/module_common.py
#<<INCLUDE_ANSIBLE_MODULE_COMMON>>
main()