#Script to extract to data from google cache This is a simple python script which retrieves content like your blog posts from googles cache, you can use this if your servers hard drive crashes or if a meteor hits your data center.
Remove the time.sleep code if you don't have more than 50 pages to retrieve.
##Original Source
| //myRunif.c | |
| #include <R.h> | |
| #include <Rinternals.h> | |
| SEXP myRunif( SEXP n, SEXP min, SEXP max ){ | |
| SEXP statsPackage; | |
| PROTECT( | |
| statsPackage = eval( lang2( install("getNamespace"), | |
| ScalarString(mkChar("stats")) ), |
| (ns pdfbox.core | |
| (:import [org.apache.pdfbox.pdmodel PDDocument] | |
| [org.apache.pdfbox.util PDFMarkedContentExtractor TextPosition] | |
| [java.util ArrayList])) | |
| (defn parse-pdf [filename] | |
| (let [pages (.getAllPages (.getDocumentCatalog (PDDocument/load filename))) | |
| textpool (ArrayList.) | |
| extract-text (proxy [PDFMarkedContentExtractor] [] | |
| (processTextPosition [text] |
| pi@raspberrypi ~ $ cat /etc/init/ssh_tunnel.conf | |
| #!upstart | |
| author "george" | |
| description "SSH Tunnel" | |
| start on stopped rc | |
| stop on shutdown |
| #Retrive old website from Google Cache. Optimized with sleep time, and avoid 504 error (Google block Ip send many request). | |
| #Programmer: Kien Nguyen - QTPros http://qtpros.info/kiennguyen | |
| #change search_site and search_term to match your requirement | |
| #Original: http://www.guyrutenberg.com/2008/10/02/retrieving-googles-cache-for-a-whole-website/ | |
| #!/usr/bin/python | |
| import urllib, urllib2 | |
| import re | |
| import socket |
| (ns noprompt.cypher | |
| (:require [clojure.string :as str] | |
| [clojurewerkz.neocons.rest.cypher :as cy] | |
| [clojure.walk :as walk]) | |
| (:import java.lang.StringBuilder)) | |
| ;; Example usage: | |
| (comment | |
| ;; Query: | |
| (start {:n (node [3 1])} |
| function interval(func, wait, times){ | |
| var interv = function(w, t){ | |
| return function(){ | |
| if(typeof t === "undefined" || t-- > 0){ | |
| setTimeout(interv, w); | |
| try{ | |
| func.call(null); | |
| } | |
| catch(e){ | |
| t = 0; |
| # Assuming an Ubuntu Docker image | |
| $ docker run -it <image> /bin/bash |
| ;; 1) first goto https://console.developers.google.com/start/api?id=gmail | |
| ;; -- to turn on gmail api for your account | |
| ;; 2) then create a oauth consent with app name | |
| ;; 3) then add oauth clientid and download to ./clientsecret.json | |
| ;; 4) boot run | |
| ;; -- when running first time a browser will open to accept authorizaton | |
| (set-env! :dependencies '[[com.google.apis/google-api-services-gmail "v1-rev34-1.21.0"] | |
| [com.google.api-client/google-api-client "1.20.0"] | |
| [com.google.oauth-client/google-oauth-client-jetty "1.20.0"]]) |
| import geocoder | |
| import requests | |
| import unicodecsv as csv | |
| import time | |
| container = {} | |
| g = geocoder.google("New Brunswick, Canada") | |
| url = "https://www.realtor.ca/api/Listing.svc/PropertySearch_Post" | |
| PropertySearchType = { |