spider now also collects js/css files and puts the in the template

dev.cfg

@@ -5,7 +5,7 @@
 # oilarchive/config/app.cfg
 
 # DATABASE
-sqlobject.dburi="notrans_mysql://root@localhost/oil"
+sqlobject.dburi="notrans_mysql://root@localhost/oil?sqlobject_encoding=utf-8&use_unicode=1&charset=utf8"
 
 # SERVER
 

oilarchive/controllers.py

@@ -1,6 +1,7 @@
 # -*- Mode: Python; -*-
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=2:sts=2:ts=2
+import time 
 
 from turbogears import controllers, expose, validate, error_handler
 from model import *
@@ -99,10 +100,38 @@ class Api:
     sname = sortname(name)
     return dict(sortname = sname, name = name)
 
+
+class ArchiveJavascript:
+  @expose()
+  def default(self, name):
+    name = name.split('.')[0]
+    archive = Archive.byHashId(name)
+    response.headerMap['Content-Type'] = "application/x-javascript"
+    secs = 60*60*24*30
+    secs = 60
+    expires = cherrypy.lib.httptools.HTTPDate(time.gmtime(time.mktime(time.gmtime()) + secs))
+    cherrypy.response.headerMap["Expires"] = expires
+    return archive.js
+    
+class ArchiveStyleSheet:
+  @expose()
+  def default(self, name):
+    name = name.split('.')[0]
+    archive = Archive.byHashId(name)
+    response.headerMap['Content-Type'] = "text/css"
+    secs = 60*60*24*30
+    secs = 60
+    expires = cherrypy.lib.httptools.HTTPDate(time.gmtime(time.mktime(time.gmtime()) + secs))
+    cherrypy.response.headerMap["Expires"] = expires
+    return archive.css
+
 class Root(controllers.RootController):
+  
   view = View()
   admin = Admin()
   api = Api()
+  js = ArchiveJavascript()
+  css = ArchiveStyleSheet()
   
   @expose(template=".templates.login")
   def login(self, forward_url=None, previous_url=None, *args, **kw):

oilarchive/model.py

@@ -5,6 +5,7 @@
 from datetime import datetime
 import time
 from urllib import quote
+import urlparse
 import md5
 
 from turbogears.database import PackageHub
@@ -118,8 +119,8 @@ class ArchiveItem(SQLObject):
     self.updateHashID()
 
   def updateHashID(self):
-    salt = '%s/%s/%s' % (self.archive.archiveName, self.author, self.title)
-    self.hashID = md5.new(salt).hexdigest()
+    salt = u'%s/%s' % (self.archive.archiveName, self.archiveItemId)
+    self.hashID = md5.new(salt.encode('utf-8')).hexdigest()
 
 
 class Archive(SQLObject):
@@ -130,9 +131,16 @@ class Archive(SQLObject):
   pubDate = DateTimeCol(default=datetime.now)
   modDate = DateTimeCol(default=datetime.now)
   created = DateTimeCol(default=datetime.now)
+  initialized = BoolCol(default = False)
+  css = UnicodeCol(default='')
+  js = UnicodeCol(default='')
+  
+  hashId = UnicodeCol(alternateID = True, length=128)
   
   def _get_pubDateTimestamp(self):
+    if self.initialized:
       return int(time.mktime(self.pubDate.timetuple()))
+    return -1
     
   def _query_url(self, query):
     url = "%s?" % self.archiveUrl
@@ -142,6 +150,9 @@ class Archive(SQLObject):
   def _get_update_url(self):
     return self._query_url({'modDate': self.pubDateTimestamp})
     
+  def _get_files_url(self):
+    return self._query_url({'files': '1'})
+    
   def data_url(self, id):
     return self._query_url({'id': id})
     
@@ -149,14 +160,26 @@ class Archive(SQLObject):
     if url.find('://') > 0:
       return url
     if url.startswith('/'):
-      url = "%s/%s" % (self.archiveUrl.split('/')[0], url)
+      domain = "://".join(urlparse.urlsplit(self.archiveUrl)[0:2])
+      url = "%s%s" % (domain, url)
     else:
       url = "%s/%s" % (self.archiveUrl, url)
+    return url
     
   def update(self):
+    result = simplejson.loads(read_url(self.files_url))
+    if result.has_key('css'):
+      self.css = read_url(self.full_url(result['css']))
+    else:
+      self.css = ''
+    if result.has_key('js'):
+      self.js = read_url(self.full_url(result['js']))
+    else:
+      self.js = ''
     result = simplejson.loads(read_url(self.update_url))
     items = result.get('items', [])
     for id in items:
+      print "updating / adding ", id
       data = jsonLoadArchiveItem(read_url(self.data_url(id)))
       q = ArchiveItem.select(AND(
             ArchiveItem.q.archiveItemId == id, 
@@ -165,6 +188,7 @@ class Archive(SQLObject):
         jsonImportArchiveItem(self, id, data)
       else:
         q[0].update(data)
+      self.initialized = True
 
   '''
     get list of all items from archive and remove those from ArchiveItem that
@@ -174,9 +198,11 @@ class Archive(SQLObject):
     url = self._query_url({'modDate': -1})
     result = simplejson.loads(read_url(url))
     archiveItems = result.get('items', [])
-    archivedItems = [i.archiveItemId for i in ArchiveItem.select(ArchiveItem.q.archiveID == self.id)]
-    removeItems = filter(lambda i: i not in archiveItems, archivedItems)
-    for i in removeItems: ArchiveItem.delete(i)
+    archivedItems = {}
+    for i in ArchiveItem.select(ArchiveItem.q.archiveID == self.id):
+      archivedItems[i.archiveItemId] = i.id
+    removeItems = filter(lambda i: i not in archiveItems, archivedItems.keys())
+    for i in removeItems: ArchiveItem.delete(archivedItems[i])
 
 class SortName(SQLObject):
   name =UnicodeCol(length=1000, alternateID=True)

oilarchive/oilspider.py

@@ -13,6 +13,10 @@ import md5
 def jsonLoadArchiveItem(data):
   json_array = simplejson.loads(data)
   json_array.pop('tg_flash', None)
+  if json_array.has_key('archiveURL'):
+    json_array['archiveUrl'] = json_array.pop('archiveURL')
+  if json_array.has_key('downloadURL'):
+    json_array['downloadUrl'] = json_array.pop('downloadURL')
   for key in ('relDate', 'pubDate', 'modDate'):
     json_array[key] = datetime.utcfromtimestamp(float(json_array[key]))
   for key in ('rights', 'size'):
@@ -24,9 +28,8 @@ def jsonLoadArchiveItem(data):
 def jsonImportArchiveItem(archive, archiveItemId, json_array):
   if isinstance(json_array, basestring):
     json_array = jsonLoadArchiveItem(json_array)
-  salt = '%s/%s/%s' % (archive.archiveName, json_array['author'], json_array['title'])
-  hashID = md5.new(salt).hexdigest()
-  
+  salt = u'%s/%s' % (archive.archiveName, archiveItemId)
+  hashID = md5.new(salt.encode('utf-8')).hexdigest()
   i = model.ArchiveItem(
     archiveID=archive.id,
     hashId = hashID,

oilarchive/templates/master.kid

@@ -5,7 +5,6 @@
 <head py:match="item.tag=='{http://www.w3.org/1999/xhtml}head'" py:attrs="item.items()">
     <meta content="text/html; charset=UTF-8" http-equiv="content-type" py:replace="''"/>
     <title py:replace="''">Your title goes here</title>
-    <meta py:replace="item[:]"/>
         <style type="text/css">
             #pageLogin
             {
@@ -15,11 +14,11 @@
             }
         </style>
         <style type="text/css" media="screen">
-@import "/static/css/style.css";
-@import "/static/css/archive.css";
-</style>
-<script src="/static/js/archive.js" />
-
+    @import "/static/css/style.css";
+    @import "/static/css/archive.css";
+    </style>
+    <script src="/static/js/archive.js" />
+    <meta py:replace="item[:]"/>
 </head>
 
 <body py:match="item.tag=='{http://www.w3.org/1999/xhtml}body'" py:attrs="item.items()">

oilarchive/templates/view.kid

@@ -2,11 +2,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml" xmlns:py="http://purl.org/kid/ns#"
     py:extends="'master.kid'">
 <head>
-<meta content="text/html; charset=utf-8" http-equiv="Content-Type" py:replace="''"/>
-<title>Oil Archive</title>
+  <meta content="text/html; charset=utf-8" http-equiv="Content-Type" py:replace="''"/>
+  <title>Oil21 - ${item.title}</title>
+  <style type="text/css" media="screen" py:if="item.archive.css">
+    @import "/css/${item.archive.hashId}.css";
+  </style>
+  <script py:if="item.archive.js" src="/js/${item.archive.hashId}.js" />
 </head>
 <body>
-
 <div class="item">
   <img class="itemIcon" src="/view/${item.hashId}/icon.png" />
   <div class="author">${item.author}</div>