#!/usr/bin/python
import sys
sys.stderr = sys.stdout
print 'Content-Type:text/html'
print
import cgi
import types
from urllib import urlencode
import urllib2
from xml.sax import make_parser
# configuration options:
# encoding:
ENC = 'iso-8859-1'
#XML parser: 'DOM' or 'SAX'
PARSER = 'DOM'
# attributes to be requested:
ATTRS_SHOWN = 'author title'
# You may want to specify search engine URL directly,
# or it may be compiled using collectionID field
# sent along with the query.
# If you use collectionID, then leave DEF_engine variable blank
# (i.e. equal to empty string, '')
# CollectionID will be used to compile an URL like this:
# http://www.insuma.de/cgi-bin/[collectionID]/web2xml.py
# You should define default collectionID value
# (for the script not to fail in case collectionID is
# absent for some reason).
# If you use collectionID, your script will be able to handle
# queries to different collections (depending on what collectionID
# is specified). Usually, collectioID is an integer, but the sample
# collection is identified by 'xml' string:
# DEF_engine = ''
# DEF_collectionID = 'xml'
# On the other hand, this feature is rarely useful
# and may lead to some problems. So, if you have no reason for
# using collectionID, you'd better specify search engine URL here:
DEF_engine = 'http://www.insuma.de/cgi-bin/xml/web2xml.py'
# Remember that either DEF_engine or DEF_collectionID should always
# be present (and non-empty)! (And if DEF_engine is set, then
# DEF_collectionID doesn't matter at all.)
#default values:
DEF_entries = '10'
DEF_start_after = '1'
# (they're strings and not integers due to the way we use them.)
DEF_hilight = 'on'
DEF_ranking = 'on'
try:
data = cgi.parse()
except:
print "Can't parse sent data!"
sys.exit()
query = unicode(data.get('query', [''])[0], ENC)
entries = int(data.get('show_max', [DEF_entries])[0])
start_after = int(data.get('start_after', [DEF_start_after])[0])
hilight = data.get('highlighting', [DEF_hilight])[0]
ranking = data.get('ranking', [DEF_ranking])[0]
if hilight <> 'on': hilight = 'off'
if ranking <> 'on': ranking = 'off'
# (they're either 'on' or 'off', nothing else.)
# the search engine URL isn't hardcoded in configuration:
if not DEF_engine:
collectionID = data.get('collectionID', [DEF_collectionID])[0]
if collectionID <> DEF_collectionID:
try:
# is it integer?
collectionID = int(collectionID)
except:
collectionID = DEF_collectionID
if type(collectionID) == type(1):
collectionID = str(collectionID)
ENGINE = 'http://www.insuma.de/cgi-bin/' + collectionID + '/web2xml.py'
else: ENGINE = DEF_engine
print '''
Test search page
Insuma found you!
''' % (entries, hilight, ranking)
########## Here the query to the server is compiled: #################
# If you want to use the script for complicated queries,
# this block should be certainly replaced with something else
# (it may be an example from the tutorial or code you write yourself).
# And don't forget, that you will probably use not only single
# QUERY variable, but a number of variables, depending on your
# search form. So you will need also make changes in other parts
# of the script:
# 1) Getting CGI-variables;
# 2) Printing search form;
# 3) Printing page navigation (print_pager() function).
if query == '':
print 'Enter a search query, please!'
print ''
sys.exit()
if ranking == 'on':
ATTRS_SHOWN += ' score'
if hilight == 'on':
ATTRS_SHOWN += ' summary'
xml_query = """
""" %(entries, start_after, ATTRS_SHOWN, query, query, query)
########################################################################
##### Here the POST message is formed:
data = """--TeRMiNaToR
Content-Disposition: form-data; name="xml_query"
Content-Type: text/xml
""" + xml_query.encode(ENC) + """
--TeRMiNaToR--"""
##### Now the message is sent and the answer is retrieved:
request = urllib2.Request(ENGINE)
request.add_header('Content-type', 'multipart/form-data; boundary="TeRMiNaToR"')
request.add_data(data)
# If you go via a proxy, uncomment this
# request.set_proxy('www-cache.informatik.uni-tuebingen.de:3128', 'http')
try:
answer = urllib2.urlopen(request)
# uncomment the next two lines to see raw output
# print answer.read()
# sys.exit(0)
except urllib2.HTTPError, a:
print a.read()
sys.exit()
except urllib2.URLError:
print "Can't connect to the search engine!