3 # urlwatch is a minimalistic URL watcher written in Python
5 # Copyright (c) 2008 Thomas Perl <thp@thpinfo.com>
8 # Redistribution and use in source and binary forms, with or without
9 # modification, are permitted provided that the following conditions
11 # 1. Redistributions of source code must retain the above copyright
12 # notice, this list of conditions and the following disclaimer.
13 # 2. Redistributions in binary form must reproduce the above copyright
14 # notice, this list of conditions and the following disclaimer in the
15 # documentation and/or other materials provided with the distribution.
16 # 3. The name of the author may not be used to endorse or promote products
17 # derived from this software without specific prior written permission.
19 # THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
20 # IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
21 # OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
22 # IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
23 # INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
24 # NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
25 # DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
26 # THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
27 # (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
28 # THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
31 """Watch web pages and arbitrary URLs for changes"""
35 __author__
= 'Thomas Perl <thp@thpinfo.com>'
36 __copyright__
= 'Copyright 2008 Thomas Perl'
38 __homepage__
= 'http://thpinfo.com/2008/urlwatch/'
41 user_agent
= '%s/%s (+http://thpinfo.com/2008/urlwatch/info.html)' % (pkgname
, __version__
)
43 # Configuration section
44 display_errors
= False
48 # File and folder paths
52 urlwatch_dir
= os
.path
.expanduser(os
.path
.join('~', '.'+pkgname
))
53 urls_txt
= os
.path
.join(urlwatch_dir
, 'urls.txt')
54 cache_dir
= os
.path
.join(urlwatch_dir
, 'cache')
55 scripts_dir
= os
.path
.join(urlwatch_dir
, 'lib')
56 hooks_py
= os
.path
.join(scripts_dir
, 'hooks.py')
58 # Check if we are installed in the system already
59 (prefix
, bindir
) = os
.path
.split(os
.path
.dirname(os
.path
.abspath(sys
.argv
[0])))
62 # Assume we are installed in system
63 examples_dir
= os
.path
.join(prefix
, 'share', pkgname
, 'examples')
65 # Assume we are not yet installed
66 examples_dir
= os
.path
.join(prefix
, bindir
, 'examples')
67 sys
.path
.append(os
.path
.join(prefix
, bindir
, 'lib'))
69 urls_txt_example
= os
.path
.join(examples_dir
, 'urls.txt.example')
70 hooks_py_example
= os
.path
.join(examples_dir
, 'hooks.py.example')
83 log
= logging
.getLogger(pkgname
)
84 log
.setLevel(logging
.DEBUG
)
86 class NullHandler(logging
.Handler
):
87 def emit(self
, record
):
90 log
.addHandler(NullHandler())
92 def foutput(type, url
, content
=None, summary
=None, c
='*', n
=line_length
):
93 """Format output messages
95 Returns a snippet of a specific message type (i.e. 'changed') for
96 a specific URL and an optional (possibly multi-line) content.
98 The parameter "summary" (if specified) should be a list variable
99 that gets one item appended for the summary of the changes.
101 The return value is a list of strings (one item per line).
103 summary_txt
= ': '.join((type.upper(), url
))
105 if summary
is not None:
107 summary
.append(summary_txt
)
109 summary
.append('%s (%d bytes)' % (summary_txt
, len(str(content
))))
111 result
= [c
*n
, summary_txt
]
112 if content
is not None:
113 result
+= [c
*n
, str(content
)]
114 result
+= [c
*n
, '', '']
119 if __name__
== '__main__':
120 start
= datetime
.datetime
.now()
123 parser
= optparse
.OptionParser(usage
='%%prog [options]\n\n%s' % __doc__
.strip(), version
=pkgname
+' '+__version__
)
124 parser
.add_option('-v', '--verbose', action
='store_true', dest
='verbose', help='Show debug/log output')
125 parser
.add_option('', '--urls', dest
='urls', metavar
='FILE', help='Read URLs from the specified file')
126 parser
.add_option('', '--hooks', dest
='hooks', metavar
='FILE', help='Use specified file as hooks.py module')
127 parser
.add_option('-e', '--display-errors', action
='store_true', dest
='display_errors', help='Include HTTP errors (404, etc..) in the output')
129 parser
.set_defaults(verbose
=False, display_errors
=False)
131 (options
, args
) = parser
.parse_args(sys
.argv
)
134 # Enable logging to the console
135 console
= logging
.StreamHandler()
136 console
.setLevel(logging
.DEBUG
)
137 formatter
= logging
.Formatter('%(asctime)s %(levelname)s: %(message)s')
138 console
.setFormatter(formatter
)
139 log
.addHandler(console
)
140 log
.info('turning on verbose logging mode')
142 if options
.display_errors
:
143 log
.info('turning display of errors ON')
144 display_errors
= True
147 if os
.path
.isfile(options
.urls
):
148 urls_txt
= options
.urls
149 log
.info('using %s as urls.txt' % options
.urls
)
151 log
.error('%s is not a file' % options
.urls
)
152 print 'Error: %s is not a file' % options
.urls
156 if os
.path
.isfile(options
.hooks
):
157 hooks_py
= options
.hooks
158 log
.info('using %s as hooks.py' % options
.hooks
)
160 log
.error('%s is not a file' % options
.hooks
)
161 print 'Error: %s is not a file' % options
.hooks
164 # Created all needed folders
165 for needed_dir
in (urlwatch_dir
, cache_dir
, scripts_dir
):
166 if not os
.path
.isdir(needed_dir
):
167 os
.makedirs(needed_dir
)
169 # Check for required files
170 if not os
.path
.isfile(urls_txt
):
171 log
.warning('not a file: %s' % urls_txt
)
172 urls_txt_fn
= os
.path
.join(os
.path
.dirname(urls_txt
), os
.path
.basename(urls_txt_example
))
173 hooks_py_fn
= os
.path
.join(os
.path
.dirname(hooks_py
), os
.path
.basename(hooks_py_example
))
174 print 'Error: You need to create a urls.txt file first.'
176 print 'Place it in %s' % (urls_txt
)
177 print 'An example is available in %s' % (urls_txt_fn
)
179 if not options
.hooks
:
180 print 'You can also create %s' % (hooks_py
)
181 print 'An example is available in %s' % (hooks_py_fn
)
183 if os
.path
.exists(urls_txt_example
) and not os
.path
.exists(urls_txt_fn
):
184 shutil
.copy(urls_txt_example
, urls_txt_fn
)
185 if not options
.hooks
and os
.path
.exists(hooks_py_example
) and not os
.path
.exists(hooks_py_fn
):
186 shutil
.copy(hooks_py_example
, hooks_py_fn
)
190 'User-agent': user_agent
,
197 if os
.path
.exists(hooks_py
):
198 log
.info('using hooks.py from %s' % hooks_py
)
199 hooks
= imp
.load_source('hooks', hooks_py
)
200 if hasattr(hooks
, 'filter'):
201 log
.info('found and enabled filter function from hooks.py')
202 filter = hooks
.filter
204 log
.warning('hooks.py has no filter function - ignoring')
205 filter = lambda x
, y
: y
207 log
.info('not using hooks.py (file not found)')
208 filter = lambda x
, y
: y
210 for url
in (x
for x
in open(urls_txt
).read().splitlines() if not (x
.startswith('#') or x
.strip()=='')):
211 log
.info('processing URL: %s' % url
)
212 filename
= os
.path
.join(cache_dir
, sha
.new(url
).hexdigest())
214 request
= urllib2
.Request(url
, None, headers
)
215 data
= filter(url
, urllib2
.urlopen(request
).read())
216 if os
.path
.exists(filename
):
217 log
.info('%s exists - creating unified diff' % filename
)
218 old_data
= open(filename
).read()
219 diff
= ''.join(difflib
.unified_diff(old_data
.splitlines(1), data
.splitlines(1)))
221 log
.info('%s has changed - adding diff' % url
)
222 details
+= foutput('changed', url
, diff
, summary
)
224 log
.info('%s has not changed' % url
)
226 log
.info('%s does not exist - url is considered "new"' % filename
)
227 details
+= foutput('new', url
, None, summary
)
228 log
.info('writing current content of %s to %s' % (url
, filename
))
229 open(filename
, 'w').write(data
)
230 except urllib2
.HTTPError
, error
:
231 log
.error('got HTTPError while loading url: %s' % error
)
233 details
+= foutput('error', url
, error
, summary
)
234 except urllib2
.URLError
, error
:
235 log
.error('got URLError while loading url: %s' % error
)
237 details
+= foutput('error', url
, error
, summary
)
240 end
= datetime
.datetime
.now()
244 log
.info('printing summary with %d items' % len(summary
))
245 print '-'*line_length
246 print 'summary: %d changes' % (len(summary
),)
248 for id, line
in enumerate(summary
):
249 print '%02d. %s' % (id+1, line
)
250 print '-'*line_length
253 log
.info('summary is too short - not printing')
255 log
.info('printing details with %d items' % len(details
))
256 print '\n'.join(details
)
258 print '%s %s, %s' % (pkgname
, __version__
, __copyright__
)
259 print 'Website: %s' % (__homepage__
,)
260 print 'watched %d URLs in %d seconds\n' % (count
, (end
-start
).seconds
)
262 log
.info('no details collected - not printing')