Tools/Scripts/webkitpy/common/system/urlfetcher.py

# Copyright (C) 2011 Google Inc. All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
#
#     * Redistributions of source code must retain the above copyright
# notice, this list of conditions and the following disclaimer.
#     * Redistributions in binary form must reproduce the above
# copyright notice, this list of conditions and the following disclaimer
# in the documentation and/or other materials provided with the
# distribution.
#     * Neither the name of Google Inc. nor the names of its
# contributors may be used to endorse or promote products derived from
# this software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

"""Wrapper module for fetching URLs."""

import urllib


class UrlFetcher(object):
    """Class with restricted interface to fetch URLs (makes testing easier)"""
    def __init__(self, filesystem):
        self._filesystem = filesystem

    def fetch(self, url):
        """Fetches the contents of the URL as a string."""
        file_object = urllib.urlopen(url)
        content = file_object.read()
        file_object.close()
        return content

    def fetch_into_file(self, url):
        """Fetches the contents of the URL into a temporary file and return the filename.

        This is the equivalent of urllib.retrieve() except that we don't return any headers.
        """
        file_object, filename = self._filesystem.open_binary_tempfile('-fetched')
        contents = self.fetch(url)
        file_object.write(contents)
        file_object.close()
        return filename