sandsfish

# For non-trivial scraping, better to use Scrapy or Beautiful Soup...
# - http://doc.scrapy.org/en/latest/intro/tutorial.html
# - http://www.crummy.com/software/BeautifulSoup/

import requests

r = requests.get("http://sacbee.com/search_results?aff=1100&q=robot")

r
# <Response [200]>

sandsfish

float time = 0;
float radius = 0;

void setup() {
  background(5);
  size(displayWidth,displayHeight, OPENGL);
  noStroke();
}

void draw() {

sandsfish

import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.client.HttpClient;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.HttpResponse;
import org.apache.http.HttpEntity;

// http://hc.apache.org/httpcomponents-client-ga/tutorial/html/fundamentals.html  -  Apache HttpClient
// https://forum.processing.org/topic/http-post-processing  -  Integration with Processing (different from above)
// https://code.google.com/p/processing/source/browse/trunk/processing/java/libraries/net/examples/HTTPClient/HTTPClient.pde?r=7950  -  Messy.
// https://github.com/francisli/processing-http  -  Unnecessary?

sandsfish

library(XML)

getMARCField = function(marc_doc, tag, code) { 
    xpath = paste("/m:collection/m:record/m:datafield[@tag='", tag, "']/m:subfield[@code='", code, "']", sep="")
    return(xpathApply(marc_doc, xpath, namespaces=c("m"), xmlValue)) 
}

vs = xmlRoot(xmlParse('vail-first-3500.xml'))
field100a = getMARCField(vs, '100', 'a')

sandsfish

#!/Users/sands/.rvm/rubies/ruby-1.8.7-p371-i386/bin/ruby
require 'rubygems'
require 'rdf'
require 'rdf/ntriples'
include RDF

repository = RDF::Repository.load("http://rdf.rubyforge.org/doap.nt")

# reports correct predicate URI...
#     DOAP.name:  http://usefulinc.com/ns/doap#name

sandsfish

# all_summary is the data here. in this case, just a lot of text records collapsed into on corpus string

# Prep data for NLTK Analysis
import nltk.collocations
tokens = nltk.word_tokenize(all_summary)
text = nltk.Text(tokens)

# Remove stop-words, convert to lower-case, remove all non-alpha characters
from nltk.corpus import stopwords
stopwords = stopwords.words('english')

sandsfish

     <div id="committee-members"><table id="att4" style="display">

                        <tbody><tr>

                            <td><input type="text" class="input-medium" id="committeeFirstName4" name="committeeFirstName4"></td>

                            <td><input type="text" class="span1" id="committeeMiddleInitial4" name="committeeMiddleInitial4"></td>

                            <td><input type="text" class="input-medium" id="committeeLastName4" name="committeeLastName4"></td>

sandsfish

package controllers;

import play.*;
import play.mvc.*;
import play.mvc.Http.Header;

import java.util.*;
import java.util.Map.Entry;

import org.tdl.vireo.model.RoleType;

sandsfish

package controllers;

import play.*;
import play.mvc.*;
import play.mvc.Http.Header;

import java.util.*;
import java.util.Map.Entry;

import org.tdl.vireo.model.RoleType;

sandsfish

# Processing Required to fulfill one embed request (672ms) + rendering time
#
# User load should not be necessary when feed is embedded from a page that is not on the site.
#
# Caching: should perhaps be done at the CompositeFeed level (which only needs to be refreshed if the config has changed)
# Caching: should also be done at the feeds/show (JavaScript) point to quickly serve processed text versions, which will
#          be updated at the Feed Refresh Interval.


Processing FeedsController#show to js (for -- at 2010-07-27 07:30:43) [GET]