edsu

#!/usr/bin/env python

"""
Hack to look for user agent strings in typical Apache style log and 
count up the number of requests by bots vs non-bots. The list of bot
user agents comes from http://www.user-agents.org/ but has had some
agents added to it, since the user-agents.org list is pretty out of date, e.g.
no Bing?!
"""

edsu

#!/usr/bin/env python

"""
Script to go through all the OAI-PMH records in the PubMedCentral database and
print out a tab delimited list of record identifiers and a license url (if one
is included).

You'll need lxml installed to run this.
"""

edsu

def words(filename):
    for line in open(filename):
        words = line.split(' ')
        for word in words:
            yield word

for word in words('file.txt'):
    print word

edsu

from tastypie import fields
from tastypie.resources import ModelResource
from tastypie.authorization import DjangoAuthorization
from tastypie.authentication import ApiKeyAuthentication

from tasty.pie.models import Book, Author

class BookResource(ModelResource):
    authors = fields.ToManyField('tasty.pie.api.resources.AuthorResource', 'authors', full=True)
    class Meta:

edsu

from django.db import models

class Book(models.Model):
    title = models.CharField(max_length=15)

class Author(models.Model):
    name = models.CharField(max_length=255)
    book = models.ForeignKey('Book', related_name='authors')

edsu

class EssayAdmin(VersionAdmin, ManyToManyAdmin):
    form = EssayForm

    # helper to put LCCNs mentioned in an essay into the list display
    def lccns(obj):
        links = []
        for title in obj.subjects.all():
            a = '<a href="http://chroniclingamerica.loc.gov/lccn/%s>%s</a>' % (title.lccn, title.lccn)
            links.append(a)
        return mark_safe(', '.join(links))

edsu

class CampaignResource(ModelResource):
    work = fields.ForeignKey(WorkResource, 'work')

    class Meta:
        queryset = models.Campaign.objects.all()
        resource_name = 'campaign'
        excludes = ['amazon_receiver', 'paypal_receiver']

    def override_urls(self):
        return [

edsu

>>> import microdata
>>> import urllib
>>> html = urllib.urlopen('http://lx6.loc.gov').read()
>>> items = microdata.get_items(html)
>>> print len(items)
30
>>> print items[0].tweet_time
2011-02-15 06:00
>>> print items[0].json()
{

edsu

#!/usr/bin/env ruby

require 'rubygems'
require 'bagit'

bag = BagIt::Bag.new 'test-data'

edsu

ed@curry:~/Projects/bagit-ruby$ rake spec
(in /home/ed/Projects/bagit-ruby)
/usr/bin/ruby1.8 -S bundle exec rspec -fs --color spec/tag_info_spec.rb spec/manifest_spec.rb spec/validation_spec.rb spec/bagit_spec.rb spec/fetch_spec.rb

Tag Info Files
  bagit.txt