| 1 |
#!/usr/bin/python |
|---|
| 2 |
# |
|---|
| 3 |
# Copyright (c) 2009, Whispersoft s.r.l. |
|---|
| 4 |
# All rights reserved. |
|---|
| 5 |
# |
|---|
| 6 |
# Redistribution and use in source and binary forms, with or without |
|---|
| 7 |
# modification, are permitted provided that the following conditions are |
|---|
| 8 |
# met: |
|---|
| 9 |
# |
|---|
| 10 |
# * Redistributions of source code must retain the above copyright |
|---|
| 11 |
# notice, this list of conditions and the following disclaimer. |
|---|
| 12 |
# * Redistributions in binary form must reproduce the above |
|---|
| 13 |
# copyright notice, this list of conditions and the following disclaimer |
|---|
| 14 |
# in the documentation and/or other materials provided with the |
|---|
| 15 |
# distribution. |
|---|
| 16 |
# * Neither the name of Whispersoft s.r.l. nor the names of its |
|---|
| 17 |
# contributors may be used to endorse or promote products derived from |
|---|
| 18 |
# this software without specific prior written permission. |
|---|
| 19 |
# |
|---|
| 20 |
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS |
|---|
| 21 |
# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT |
|---|
| 22 |
# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR |
|---|
| 23 |
# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT |
|---|
| 24 |
# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, |
|---|
| 25 |
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT |
|---|
| 26 |
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, |
|---|
| 27 |
# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY |
|---|
| 28 |
# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
|---|
| 29 |
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE |
|---|
| 30 |
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
|---|
| 31 |
# |
|---|
| 32 |
import os |
|---|
| 33 |
import sys |
|---|
| 34 |
|
|---|
| 35 |
def process_wget_out(f, saved_lines): |
|---|
| 36 |
lines = open(f).readlines() |
|---|
| 37 |
save_lines = False |
|---|
| 38 |
for l in lines: |
|---|
| 39 |
if ( l.startswith('---response begin---') or |
|---|
| 40 |
l.startswith('---request begin---') ): |
|---|
| 41 |
save_lines = True |
|---|
| 42 |
elif ( l.startswith('---response end---') or |
|---|
| 43 |
l.startswith('---request end---' ) ): |
|---|
| 44 |
save_lines = False |
|---|
| 45 |
elif save_lines: |
|---|
| 46 |
saved_lines.append(l) |
|---|
| 47 |
|
|---|
| 48 |
|
|---|
| 49 |
def get_headers(f, fout): |
|---|
| 50 |
saved_lines = [] |
|---|
| 51 |
lines = open(f).readlines() |
|---|
| 52 |
for url in lines: |
|---|
| 53 |
url.strip(); |
|---|
| 54 |
print "Getting: %s" % url |
|---|
| 55 |
os.system("wget -d -o /tmp/hdrs1 -O /tmp/xxx_out '%s'" % url) |
|---|
| 56 |
os.unlink("/tmp/xxx_out"); |
|---|
| 57 |
process_wget_out("/tmp/hdrs1", saved_lines) |
|---|
| 58 |
fout.write(''.join(saved_lines)) |
|---|
| 59 |
|
|---|
| 60 |
if __name__ == "__main__": |
|---|
| 61 |
fout = open(sys.argv[2], "w") |
|---|
| 62 |
get_headers(sys.argv[1], fout) |
|---|
| 63 |
fout.close() |
|---|
