Support for POST requests
[urlwatch.git] / lib / urlwatch / handler.py
blob7ec89f1f4ea8b3100efccbe79eb18822b19488a0
1 #!/usr/bin/python
2 # -*- coding: utf-8 -*-
4 # urlwatch is a minimalistic URL watcher written in Python
6 # Copyright (c) 2008-2011 Thomas Perl <thp.io/about>
7 # All rights reserved.
9 # Redistribution and use in source and binary forms, with or without
10 # modification, are permitted provided that the following conditions
11 # are met:
12 # 1. Redistributions of source code must retain the above copyright
13 # notice, this list of conditions and the following disclaimer.
14 # 2. Redistributions in binary form must reproduce the above copyright
15 # notice, this list of conditions and the following disclaimer in the
16 # documentation and/or other materials provided with the distribution.
17 # 3. The name of the author may not be used to endorse or promote products
18 # derived from this software without specific prior written permission.
20 # THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
21 # IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
22 # OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
23 # IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
24 # INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
25 # NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
26 # DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
27 # THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
28 # (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
29 # THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
32 try:
33 # Available in Python 2.5 and above and preferred if available
34 import hashlib
35 have_hashlib = True
36 except ImportError:
37 # "sha" is deprecated since Python 2.5 (throws a warning in Python 2.6)
38 # Thanks to Frank Palvölgyi for reporting the warning in Python 2.6
39 import sha
40 have_hashlib = False
42 import subprocess
43 import email.Utils
44 import urllib2
45 import os
46 import stat
47 import sys
48 import re
50 class JobBase(object):
51 def __init__(self, location):
52 self.location = location
54 def __str__(self):
55 return self.location
57 def get_guid(self):
58 if have_hashlib:
59 sha_hash = hashlib.new('sha1')
60 sha_hash.update(self.location)
61 return sha_hash.hexdigest()
62 else:
63 return sha.new(self.location).hexdigest()
65 def retrieve(self, timestamp=None, filter=None, headers=None, log=None):
66 raise Exception('Not implemented')
68 class ShellError(Exception):
69 """Exception for shell commands with non-zero exit code"""
71 def __init__(self, result):
72 Exception.__init__(self)
73 self.result = result
75 def __str__(self):
76 return '%s: Exit status %d' % (self.__class__.__name__, self.result)
79 def use_filter(filter, url, input):
80 """Apply a filter function to input from an URL"""
81 output = filter(url, input)
83 if output is None:
84 # If the filter does not return a value, it is
85 # assumed that the input does not need filtering.
86 # In this case, we simply return the input.
87 return input
89 return output
92 class ShellJob(JobBase):
93 def retrieve(self, timestamp=None, filter=None, headers=None, log=None):
94 process = subprocess.Popen(self.location, \
95 stdout=subprocess.PIPE, \
96 shell=True)
97 stdout_data, stderr_data = process.communicate()
98 result = process.wait()
99 if result != 0:
100 raise ShellError(result)
102 return use_filter(filter, self.location, stdout_data)
105 class UrlJob(JobBase):
106 CHARSET_RE = re.compile('text/(html|plain); charset=(.*)')
108 def retrieve(self, timestamp=None, filter=None, headers=None, log=None):
109 headers = dict(headers)
110 if timestamp is not None:
111 timestamp = email.Utils.formatdate(timestamp)
112 headers['If-Modified-Since'] = timestamp
114 if ' ' in self.location:
115 self.location, post_data = self.location.split(' ', 1)
116 log.info('Sending POST request to %s', self.location)
117 else:
118 post_data = None
120 request = urllib2.Request(self.location, post_data, headers)
121 response = urllib2.urlopen(request)
122 headers = response.info()
123 content = response.read()
124 encoding = None
126 # Determine content type via HTTP headers
127 content_type = headers.get('Content-type', '')
128 content_type_match = self.CHARSET_RE.match(content_type)
129 if content_type_match:
130 encoding = content_type_match.group(2)
132 if encoding is not None:
133 # Convert from specified encoding to utf-8
134 content_unicode = content.decode(encoding, 'ignore')
135 content = content_unicode.encode('utf-8')
137 return use_filter(filter, self.location, content)
140 def parse_urls_txt(urls_txt):
141 jobs = []
143 # Security checks for shell jobs - only execute if the current UID
144 # is the same as the file/directory owner and only owner can write
145 allow_shelljobs = True
146 shelljob_errors = []
147 current_uid = os.getuid()
149 dirname = os.path.dirname(urls_txt)
150 dir_st = os.stat(dirname)
151 if (dir_st.st_mode & (stat.S_IWGRP | stat.S_IWOTH)) != 0:
152 shelljob_errors.append('%s is group/world-writable' % dirname)
153 allow_shelljobs = False
154 if dir_st.st_uid != current_uid:
155 shelljob_errors.append('%s not owned by %s' % (dirname, os.getlogin()))
156 allow_shelljobs = False
158 file_st = os.stat(urls_txt)
159 if (file_st.st_mode & (stat.S_IWGRP | stat.S_IWOTH)) != 0:
160 shelljob_errors.append('%s is group/world-writable' % urls_txt)
161 allow_shelljobs = False
162 if file_st.st_uid != current_uid:
163 shelljob_errors.append('%s not owned by %s' % (urls_txt, os.getlogin()))
164 allow_shelljobs = False
166 for line in open(urls_txt).read().splitlines():
167 if line.strip().startswith('#') or line.strip() == '':
168 continue
170 if line.startswith('|'):
171 if allow_shelljobs:
172 jobs.append(ShellJob(line[1:]))
173 else:
174 print >>sys.stderr, '\n SECURITY WARNING - Cannot run shell jobs:\n'
175 for error in shelljob_errors:
176 print >>sys.stderr, ' ', error
177 print >>sys.stderr, '\n Please remove shell jobs or fix these problems.\n'
178 sys.exit(1)
179 else:
180 jobs.append(UrlJob(line))
182 return jobs