lawlesst

import sys
from pymarc import Record, MARCReader

reader = MARCReader(file(sys.argv[1]))

print "ALT LOOKUP, Provider, URL"



for rec in reader:

lawlesst

#!/usr/bin/env python

import sys
from pymarc import Field, Reader, Record, MARCWriter

import xlrd

#script timer
import time
start_time = time.time()

lawlesst

#pass in elementree tree obj
#pass call linked_value('245', subfields=['a', 'c'])

def linked_fields(self):
  linked_fields = []
  for field in self.var_fields:
    rec_tag = field.findtext('MARCINFO/MARCTAG')
    if '880' == rec_tag:
      linked_fields.append((field.findall('MARCSUBFLD'), field))

lawlesst

from xml.etree.ElementTree import ElementTree
import urllib

source_url = 'http://etd.lib.montana.edu/etd/view/locations-markers.php'

source = urllib.urlopen(source_url)
tree = ElementTree()
doc = tree.parse(source)

print'<?xml version="1.0" encoding="UTF-8"?>'

lawlesst

"""
Search Summon API with Python.
See Dough Chesnut's Code4Lib mailing list post: http://serials.infomotions.com/code4lib/archive/2010/201010/2408.html
"""
import httplib2
import urllib
from datetime import datetime
import hmac
import base64
import hashlib

lawlesst

import xlrd, sys
from pymarc import Field, Reader, Record, MARCWriter

#script timer
import time
start_time = time.time()

"""Script that reads data from an Excel sheet and converts the records to MARC format.  
   Sample incoming data is in Chinese, UTF 8.  Would work for other languages as well.

lawlesst

class Accession(models.Model):
    """Sample for recording library statistics.  
       Use indexes for faster query time.."""
    number = models.CharField(max_length=15, primary_key=True)
    created = models.DateField(db_index=True)
    acquisition_method = models.CharField(max_length=50, db_index=True)
    format = models.CharField(max_length=50, db_index=True)
    location = models.CharField(max_length=50, db_index=True)
    volumes = models.IntegerField()

lawlesst

import sys
import csv

csv_file = csv.DictReader(open(sys.argv[1]))

for row in csv_file:
    print row['bluebook'], row['journal']

lawlesst

September 25, 2015

Steps to run ldf-server on Heroku with an HDT backend.

• Read the Node troubleshooting guide from Heroku for background.
• Run the commands in the Start with a Blank Slate section of the guide.
• Add package.json to your git repository if it isn't already.
• For my project, I had to explicitly add hdt - 1.2.2 as a dependendency.

package.json

lawlesst

petl

Python ETL

• Documentation: https://petl.readthedocs.org/en/latest/index.html
• Source: https://github.com/alimanfoo/petl
• Mailing list: http://groups.google.com/group/python-etl

Many in the VIVO community use Python for data manipulation and transformation tasks (ETL). petl is a framework for reading data from various sources, transforming it, and passing it along to another source.