Author: duncan
Date: Tue Jul 31 17:27:50 2007
New Revision: 9784
Log:
Fixes for imdb search when the name contains numbers only
Modified:
branches/rel-1/freevo/freevo_config.py
branches/rel-1/freevo/setup.py
branches/rel-1/freevo/src/helpers/imdb.py
branches/rel-1/freevo/src/util/fxdimdb.py
Modified: branches/rel-1/freevo/freevo_config.py
==============================================================================
--- branches/rel-1/freevo/freevo_config.py (original)
+++ branches/rel-1/freevo/freevo_config.py Tue Jul 31 17:27:50 2007
@@ -696,8 +696,8 @@
# list of regexp to be ignored on a disc label
IMDB_REMOVE_FROM_LABEL = ('season[\._ -][0-9]+', 'disc[\._ -][0-9]+',
'd[\._ -][0-9]+', 'german')
-# list of regexp to be ignored on a filename
-IMDB_REMOVE_FROM_NAME = ['^[0-9_]+']
+# list of regexp to be ignored on a filename, match TV_RECORDMASK
+IMDB_REMOVE_FROM_NAME = ['^[0-9]+-[0-9]+[ _][0-9]+\.[0-9]+[ _]']
# list of words to ignore when searching based on a filename
IMDB_REMOVE_FROM_SEARCHSTRING = ('the', 'a')
Modified: branches/rel-1/freevo/setup.py
==============================================================================
--- branches/rel-1/freevo/setup.py (original)
+++ branches/rel-1/freevo/setup.py Tue Jul 31 17:27:50 2007
@@ -44,7 +44,7 @@
def initialize_options (self):
pass
-
+
def finalize_options (self):
pass
@@ -93,7 +93,7 @@
# the normal one doesn't work
continue
os.system('mv "%s" "%s"' % (source, dest))
-
+
def run (self):
"""
download and install the runtime + current mmpython
@@ -110,7 +110,7 @@
os.path.walk('mmpython-%s' % version.mmpython, self.mmpython_install,
None)
os.system('rm -rf mmpython-%s' % version.mmpython)
-
+
# check if everything is in place
if (len(sys.argv) < 2 or sys.argv[1].lower() not in ('i18n', '--help',
'--help-commands')):
if os.path.isdir('.svn'):
Modified: branches/rel-1/freevo/src/helpers/imdb.py
==============================================================================
--- branches/rel-1/freevo/src/helpers/imdb.py (original)
+++ branches/rel-1/freevo/src/helpers/imdb.py Tue Jul 31 17:27:50 2007
@@ -144,10 +144,14 @@
usage()
filename = search_arg
- print "searching " + filename
- for result in fxd.searchImdb(filename):
+ print "Searching IMDB for '%s'..." % filename
+ results = fxd.searchImdb(filename)
+ _debug_('%r' % results)
+ if len(results) == 0:
+ print 'No results'
+ for result in results:
if result[3]:
- print '%s %s (%s, %s)' % result
+ print '%s %s (%s) %s' % result
else:
print '%s %s (%s)' % (result[0], result[1], result[2])
sys.exit(0)
@@ -155,10 +159,14 @@
if task == 'guess':
filename = search_arg
- print "searching " + filename
- for result in fxd.guessImdb(filename):
+ print "Searching IMDB for '%s'..." % filename
+ results = fxd.guessImdb(filename)
+ if len(results) == 0:
+ print 'No results'
+ _debug_('%r' % results)
+ for result in results:
if result[3]:
- print '%s %s (%s, %s)' % result
+ print '%s %s (%s) %s' % result
else:
print '%s %s (%s)' % (result[0], result[1], result[2])
sys.exit(0)
Modified: branches/rel-1/freevo/src/util/fxdimdb.py
==============================================================================
--- branches/rel-1/freevo/src/util/fxdimdb.py (original)
+++ branches/rel-1/freevo/src/util/fxdimdb.py Tue Jul 31 17:27:50 2007
@@ -129,8 +129,9 @@
Search for name and returns an id list with tuples:
(id , name, year, type)"""
- url = 'http://us.imdb.com/Tsearch?title=%s&restrict=Movies+and+TV' %
urllib.quote(name)
- url = 'http://www.imdb.com/find?s=tt;site=aka;q=%s' %
urllib.quote(name)
+ _debug_('searching imdb for "%s"' % (name))
+ url = 'http://us.imdb.com/Tsearch?title=%s&restrict=Movies+and+TV' %
urllib.quote(str(name))
+ url = 'http://www.imdb.com/find?s=tt;site=aka;q=%s' %
urllib.quote(str(name))
_debug_('url="%s"' % (url))
req = urllib2.Request(url, txdata, txheaders)
@@ -142,8 +143,7 @@
raise FxdImdb_Net_Error("IMDB unreachable : " + error)
return None
- if config.DEBUG:
- _debug_('response.url="%s"' % (response.geturl()))
+ _debug_('response.url="%s"' % (response.geturl()))
m=re.compile('/title/tt([0-9]*)/')
idm = m.search(response.geturl())
@@ -154,15 +154,17 @@
data = self.parsesearchdata(response)
response.close()
+ _debug_('imdb_id_list has %s items' % (len(self.imdb_id_list)))
if len(self.imdb_id_list) > 20:
- # too much results, check if there are stupid results in the
- # list
+ # too many results, check if there are stupid results in the list
words = []
# make a list of all words (no numbers) in the search string
for p in re.split('[\._ -]', searchstring):
- if p and not p[0] in '0123456789':
- words.append(p)
+ #XXX this is incorrect for number only searches
+ #if p and not p[0] in '0123456789':
+ # words.append(p)
+ words.append(p)
# at least one word has to be in the result
new_list = []
@@ -174,6 +176,7 @@
new_list.append(result)
appended = True
self.imdb_id_list = new_list
+ _debug_('imdb_id_list has now %s items' % (len(self.imdb_id_list)))
return self.imdb_id_list
@@ -666,7 +669,8 @@
#print item.parent.findChildren(text=re.compile('[^ ]'))
self.imdb_id_list += [ ( id, name, year, type ) ]
- _debug_(self.imdb_id_list)
+ for item in self.imdb_id_list:
+ _debug_('%r' % (item,), 2)
return self.imdb_id_list
def findepisode(self, results):
@@ -793,7 +797,7 @@
for (k,v) in self.info.items():
_debug_('items=%s:%s' % (k, v))
_debug_('id="%s", dvd="%s"' % (id, dvd))
- _debug_(self.info)
+ _debug_(self.info, 2)
# Add impawards.com poster URLs.
self.impawardsimages(self.info['title'], self.info['year'])
-------------------------------------------------------------------------
This SF.net email is sponsored by: Splunk Inc.
Still grepping through log files to find problems? Stop.
Now Search log events and configuration files using AJAX and a browser.
Download your FREE copy of Splunk now >> http://get.splunk.com/
_______________________________________________
Freevo-cvslog mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/freevo-cvslog
