Initial project files

19 files changed, 298 insertions, 0 deletions

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..0d20b64
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1 @@
+*.pyc
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..ae68d10
--- /dev/null
+++ b/README.md
@@ -0,0 +1,3 @@
+# NewsDiff
+
+A tool for scraping, parsing, archiving and analyzing mainstream media content.
diff --git a/manage.py b/manage.py
new file mode 100755
index 0000000..10f171e
--- /dev/null
+++ b/manage.py
@@ -0,0 +1,10 @@
+#!/usr/bin/env python
+import os
+import sys
+
+if __name__ == "__main__":
+    os.environ.setdefault("DJANGO_SETTINGS_MODULE", "newsdiff.settings")
+
+    from django.core.management import execute_from_command_line
+
+    execute_from_command_line(sys.argv)
diff --git a/newsdiff/__init__.py b/newsdiff/__init__.py
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/newsdiff/__init__.py
diff --git a/newsdiff/core/__init__.py b/newsdiff/core/__init__.py
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/newsdiff/core/__init__.py
diff --git a/newsdiff/core/admin.py b/newsdiff/core/admin.py
new file mode 100644
index 0000000..8c38f3f
--- /dev/null
+++ b/newsdiff/core/admin.py
@@ -0,0 +1,3 @@
+from django.contrib import admin
+
+# Register your models here.
diff --git a/newsdiff/core/migrations/0001_initial.py b/newsdiff/core/migrations/0001_initial.py
new file mode 100644
index 0000000..b32e267
--- /dev/null
+++ b/newsdiff/core/migrations/0001_initial.py
@@ -0,0 +1,59 @@
+# -*- coding: utf-8 -*-
+from south.utils import datetime_utils as datetime
+from south.db import db
+from south.v2 import SchemaMigration
+from django.db import models
+
+
+class Migration(SchemaMigration):
+
+    def forwards(self, orm):
+        # Adding model 'HaaretzArticle'
+        db.create_table(u'core_haaretzarticle', (
+            (u'id', self.gf('django.db.models.fields.AutoField')(primary_key=True)),
+            ('url', self.gf('django.db.models.fields.CharField')(max_length=200)),
+            ('title', self.gf('django.db.models.fields.CharField')(max_length=140)),
+            ('subtitle', self.gf('django.db.models.fields.CharField')(max_length=300)),
+            ('text', self.gf('django.db.models.fields.TextField')()),
+            ('date', self.gf('django.db.models.fields.DateTimeField')()),
+        ))
+        db.send_create_signal(u'core', ['HaaretzArticle'])
+
+        # Adding model 'HaaretzImage'
+        db.create_table(u'core_haaretzimage', (
+            (u'id', self.gf('django.db.models.fields.AutoField')(primary_key=True)),
+            ('article', self.gf('django.db.models.fields.related.ForeignKey')(to=orm['core.HaaretzArticle'])),
+            ('origin_url', self.gf('django.db.models.fields.CharField')(max_length=200)),
+            ('image', self.gf('django.db.models.fields.files.ImageField')(max_length=100)),
+        ))
+        db.send_create_signal(u'core', ['HaaretzImage'])
+
+
+    def backwards(self, orm):
+        # Deleting model 'HaaretzArticle'
+        db.delete_table(u'core_haaretzarticle')
+
+        # Deleting model 'HaaretzImage'
+        db.delete_table(u'core_haaretzimage')
+
+
+    models = {
+        u'core.haaretzarticle': {
+            'Meta': {'object_name': 'HaaretzArticle'},
+            'date': ('django.db.models.fields.DateTimeField', [], {}),
+            u'id': ('django.db.models.fields.AutoField', [], {'primary_key': 'True'}),
+            'subtitle': ('django.db.models.fields.CharField', [], {'max_length': '300'}),
+            'text': ('django.db.models.fields.TextField', [], {}),
+            'title': ('django.db.models.fields.CharField', [], {'max_length': '140'}),
+            'url': ('django.db.models.fields.CharField', [], {'max_length': '200'})
+        },
+        u'core.haaretzimage': {
+            'Meta': {'object_name': 'HaaretzImage'},
+            'article': ('django.db.models.fields.related.ForeignKey', [], {'to': u"orm['core.HaaretzArticle']"}),
+            u'id': ('django.db.models.fields.AutoField', [], {'primary_key': 'True'}),
+            'image': ('django.db.models.fields.files.ImageField', [], {'max_length': '100'}),
+            'origin_url': ('django.db.models.fields.CharField', [], {'max_length': '200'})
+        }
+    }
+
+    complete_apps = ['core']
\ No newline at end of file
diff --git a/newsdiff/core/migrations/__init__.py b/newsdiff/core/migrations/__init__.py
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/newsdiff/core/migrations/__init__.py
diff --git a/newsdiff/core/models.py b/newsdiff/core/models.py
new file mode 100644
index 0000000..0bbb0b2
--- /dev/null
+++ b/newsdiff/core/models.py
@@ -0,0 +1,16 @@
+from django.db import models
+from django.utils.timezone import now as tz_now
+
+
+class HaaretzArticle(models.Model):
+    url = models.CharField(max_length=200)
+    title = models.CharField(max_length=140)
+    subtitle = models.CharField(max_length=300)
+    text = models.TextField()
+    date = models.DateTimeField()
+
+
+class HaaretzImage(models.Model):
+    article = models.ForeignKey(HaaretzArticle)
+    origin_url = models.CharField(max_length=200)
+    image = models.ImageField(upload_to='images/haaretz')
diff --git a/newsdiff/core/tests.py b/newsdiff/core/tests.py
new file mode 100644
index 0000000..7ce503c
--- /dev/null
+++ b/newsdiff/core/tests.py
@@ -0,0 +1,3 @@
+from django.test import TestCase
+
+# Create your tests here.
diff --git a/newsdiff/core/views.py b/newsdiff/core/views.py
new file mode 100644
index 0000000..91ea44a
--- /dev/null
+++ b/newsdiff/core/views.py
@@ -0,0 +1,3 @@
+from django.shortcuts import render
+
+# Create your views here.
diff --git a/newsdiff/settings/__init__.py b/newsdiff/settings/__init__.py
new file mode 100644
index 0000000..33b81ad
--- /dev/null
+++ b/newsdiff/settings/__init__.py
@@ -0,0 +1,11 @@
+import os
+
+if 'EC2' in os.environ:
+    from .ec2 import *
+if 'HEROKU' in os.environ:
+    from .heroku import *
+else:
+    try:
+        from .local import *
+    except ImportError:
+        from .base import *
diff --git a/newsdiff/settings/base.py b/newsdiff/settings/base.py
new file mode 100644
index 0000000..e6ca023
--- /dev/null
+++ b/newsdiff/settings/base.py
@@ -0,0 +1,115 @@
+from unipath import FSPath as Path
+
+PROJECT_DIR = Path(__file__).absolute().ancestor(2)
+
+DEBUG = False
+TEMPLATE_DEBUG = DEBUG
+
+ADMINS = (
+    ('Yuval Adam', 'yuv.adm@gmail.com'),
+)
+
+MANAGERS = ADMINS
+
+ALLOWED_HOSTS = []
+
+TIME_ZONE = 'Etc/UTC'
+LANGUAGE_CODE = 'en-us'
+SITE_ID = 1
+USE_I18N = True
+USE_L10N = True
+USE_TZ = True
+
+MEDIA_ROOT = ''
+MEDIA_URL = ''
+STATIC_ROOT = ''
+STATIC_URL = '/static/'
+
+STATICFILES_DIRS = (
+    PROJECT_DIR.child('static'),
+)
+
+STATICFILES_FINDERS = (
+    'django.contrib.staticfiles.finders.FileSystemFinder',
+    'django.contrib.staticfiles.finders.AppDirectoriesFinder',
+#    'django.contrib.staticfiles.finders.DefaultStorageFinder',
+)
+
+SECRET_KEY = '65p2-o63(df#q7qq_pcj#y#l(bi#%ls)!-60lr$ric)6pb%tux'
+
+TEMPLATE_LOADERS = (
+    'django.template.loaders.filesystem.Loader',
+    'django.template.loaders.app_directories.Loader',
+#     'django.template.loaders.eggs.Loader',
+)
+
+TEMPLATE_CONTEXT_PROCESSORS = (
+    'django.contrib.auth.context_processors.auth',
+    'django.core.context_processors.debug',
+    'django.core.context_processors.i18n',
+    'django.core.context_processors.media',
+    'django.core.context_processors.request',
+    'django.core.context_processors.static',
+    'django.core.context_processors.tz',
+    'django.contrib.messages.context_processors.messages',
+)
+
+MIDDLEWARE_CLASSES = (
+    'django.middleware.common.CommonMiddleware',
+    'django.contrib.sessions.middleware.SessionMiddleware',
+    'django.middleware.csrf.CsrfViewMiddleware',
+    'django.contrib.auth.middleware.AuthenticationMiddleware',
+    'django.contrib.messages.middleware.MessageMiddleware',
+    # 'django.middleware.clickjacking.XFrameOptionsMiddleware',
+)
+
+ROOT_URLCONF = 'newsdiff.urls'
+
+WSGI_APPLICATION = 'newsdiff.wsgi.application'
+
+TEMPLATE_DIRS = (
+    PROJECT_DIR.child('templates'),
+)
+
+INSTALLED_APPS = (
+    'django.contrib.auth',
+    'django.contrib.contenttypes',
+    'django.contrib.sessions',
+    'django.contrib.sites',
+    'django.contrib.messages',
+    'django.contrib.staticfiles',
+    'django.contrib.admin',
+
+    'south',
+    'storages',
+
+    'newsdiff.core'
+)
+
+SITE_ID = 1
+
+SESSION_SERIALIZER = 'django.contrib.sessions.serializers.JSONSerializer'
+
+LOGGING = {
+    'version': 1,
+    'disable_existing_loggers': False,
+    'filters': {
+        'require_debug_false': {
+            '()': 'django.utils.log.RequireDebugFalse'
+        }
+    },
+    'handlers': {
+        'mail_admins': {
+            'level': 'ERROR',
+            'filters': ['require_debug_false'],
+            'class': 'django.utils.log.AdminEmailHandler'
+        }
+    },
+    'loggers': {
+        'django.request': {
+            'handlers': ['mail_admins'],
+            'level': 'ERROR',
+            'propagate': True,
+        },
+    }
+}
diff --git a/newsdiff/settings/ec2.py b/newsdiff/settings/ec2.py
new file mode 100644
index 0000000..4e1a293
--- /dev/null
+++ b/newsdiff/settings/ec2.py
@@ -0,0 +1,5 @@
+from .base import *
+
+ENV = 'ec2'
+
+DEFAULT_FILE_STORAGE = 'storages.backends.s3boto.S3BotoStorage'
diff --git a/newsdiff/settings/heroku.py b/newsdiff/settings/heroku.py
new file mode 100644
index 0000000..738d7bb
--- /dev/null
+++ b/newsdiff/settings/heroku.py
@@ -0,0 +1,5 @@
+from .base import *
+
+ENV = 'heroku'
+
+DEFAULT_FILE_STORAGE = 'storages.backends.s3boto.S3BotoStorage'
diff --git a/newsdiff/settings/local.py b/newsdiff/settings/local.py
new file mode 100644
index 0000000..95b64c1
--- /dev/null
+++ b/newsdiff/settings/local.py
@@ -0,0 +1,24 @@
+from .base import *
+
+ENV = 'local'
+
+DEBUG = True
+TEMPLATE_DEBUG = DEBUG
+
+DATABASES = {
+    'default': {
+        'ENGINE': 'django.db.backends.postgresql_psycopg2',
+        'NAME': 'newsdiff',
+        'USER': 'newsdiff',
+        'PASSWORD': 'newsdiff',
+        'HOST': '',
+        'PORT': '',
+    }
+}
+
+MEDIA_ROOT = PROJECT_DIR.child('media')
+MEDIA_URL = '/media/'
+
+EMAIL_BACKEND = 'django.core.mail.backends.console.EmailBackend'
+
+CELERY_ALWAYS_EAGER = True  # Makes all celery tasks run synchronously
diff --git a/newsdiff/urls.py b/newsdiff/urls.py
new file mode 100644
index 0000000..f523ec9
--- /dev/null
+++ b/newsdiff/urls.py
@@ -0,0 +1,12 @@
+from django.conf.urls import patterns, include, url
+
+from django.contrib import admin
+admin.autodiscover()
+
+urlpatterns = patterns('',
+    # Examples:
+    # url(r'^$', 'newsdiff.views.home', name='home'),
+    # url(r'^blog/', include('blog.urls')),
+
+    url(r'^admin/', include(admin.site.urls)),
+)
diff --git a/newsdiff/wsgi.py b/newsdiff/wsgi.py
new file mode 100644
index 0000000..abf4c8a
--- /dev/null
+++ b/newsdiff/wsgi.py
@@ -0,0 +1,14 @@
+"""
+WSGI config for newsdiff project.
+
+It exposes the WSGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/1.6/howto/deployment/wsgi/
+"""
+
+import os
+os.environ.setdefault("DJANGO_SETTINGS_MODULE", "newsdiff.settings")
+
+from django.core.wsgi import get_wsgi_application
+application = get_wsgi_application()
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..9f89c2d
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,14 @@
+Django==1.6
+PIL==1.1.7
+South==0.8.4
+Unipath==1.0
+amqp==1.3.3
+anyjson==0.3.3
+billiard==3.3.0.11
+celery==3.1.6
+django-reversion==1.8.0
+django-storages==1.1.8
+kombu==3.0.7
+psycopg2==2.5.1
+pytz==2013.8
+wsgiref==0.1.2