materialy.wsgi

#!/usr/bin/python
# -*- coding: utf-8 -*-

import time
import pysqlite2.dbapi2 as sqlite3
import urllib 

import PyRSS2Gen
from lxml import html
import MySQLdb

db_config = {'user':'some_user','passwd':'some_password','db':'some_db'}
#from config import db_config

frequency = 30 #for caching purposes
xpath_contains = "contains(., 'semestr 2') and contains(., 'anie,')" + \
	    "and not(contains(., 'niestacjonarne'))"

def get_usage():
  return """
  Skrypt uruchamiamy podajac mu ID profilu pracownika, np: <br />
  http://jakis-serwer/katalog/materialy.wsgi?123
	 """
  

def try_from_cache(url):
  now = int(time.time())
  conn = MySQLdb.connect(**db_config)
  c = conn.cursor()
  c.execute("create table IF NOT EXISTS `cache`  (url VARCHAR(256) CHARA" + \
  "CTER SET utf8 COLLATE utf8_unicode_ci UNIQUE, value BLOB, lasttime BLOB);")
  query = c.execute("SELECT * FROM cache WHERE url = %s", (url,) )
  entry = c.fetchone()
  if entry:
    if now - int(entry[2]) < frequency:
      ret = entry[1]
    else:
      ret = urllib.urlopen(url).read()#.decode('iso8859-2')#.encode('utf-8')
      c.execute("UPDATE cache SET lasttime = %s, value = %s" \
		+ "WHERE url = %s", (now,ret,url))
      conn.commit()
  else:
    ret = urllib.urlopen(url).read()#.decode('iso8859-2')#.encode('utf-8')
    c.execute("INSERT INTO cache VALUES (%s,%s,%s)", (url,ret,now))
    conn.commit()
  return ret

def application(environ, start_response):
  
  try:
    lecturer_id = int(environ["QUERY_STRING"])
  except:
    start_response('200 OK', [('Content-type','text/html')])
    return get_usage()
    
  filelist_url = "http://zarzadzanie.uni.lodz.pl/Stronag%C5%82%C3%B3wna/" + \
		 "WyszukiwanieMateria%C5%82%C3%B3w/tabid/167/ctl/results/" + \
		 "mid/552/language/pl-PL/Default.aspx%suid="+str(lecturer_id)
      
  page = try_from_cache(filelist_url)
  page = page.decode('utf8')
  
  materials_id = "dnn_ctr552_Results_TabContainer2_TabPanel4_grvWykladowca"
  xpath_str = "//table[@id='%s']//*[%s]//td" % (materials_id, xpath_contains)
  tree = html.fromstring(page)
  entries = tree.xpath(xpath_str)

  if len(entries)>0:
    rss_title = entries[0][1][0].text
  else:
    rss_title = "WZ UŁ - materiały".decode('utf8')
  
  rss = PyRSS2Gen.RSS2(
    title = rss_title,
    link = "http://deetah.jogger.pl",
    description = "Kanał RSS zawiera najnowsze materiały od wybranych "
        "wykładowców Wydziału Zarządzania Uniwersytetu Łódzkiego.".decode('utf-8'),
  )
  
  for entry in reversed(entries):
  
    file_name = entry[4].text
    lecturer = entry[1][0].text
    file_title = entry[1][1].text or file_name
    #subject = entry[1][0].tail.split(', ')[1]
    
    rss_title = '[%s] %s' % (lecturer, file_title)
    
    profile_url = "http://zarzadzanie.uni.lodz.pl/tabid/173/" + \
	      "language/pl-PL/Default.aspx?uid="+str(environ["QUERY_STRING"])
    rss_description = ((u'<b>Nazwa pliku: </b>%s<br /><b>Wykładowca: </b>' + \
         '<a href="%s">%s</a><br />') % (file_name, profile_url, lecturer) \
         ).decode('utf8')
    
    rss.items.append(PyRSS2Gen.RSSItem(
	title = rss_title, link = filelist_url, description = rss_description,
	guid = PyRSS2Gen.Guid( rss_title ),
    ))
    
  start_response('200 OK', [('Content-type','application/rss+xml')])
  return rss.to_xml(encoding='iso-8859-2')
  
if __name__ == "__main__":
  print application({"QUERY_STRING":"137"},'')