| <?php | |
| /* | |
| * Check if given mail is valid using: | |
| * filter_var() | |
| * check MX record | |
| * verify is user exist using telnet and SMPT session | |
| * | |
| * I'm useing this helper in ajax respone so results are echo'ed as json | |
| */ |
| # -*- coding: utf-8 -*- | |
| """ | |
| common-crawl-cdx.py | |
| A simple example program to analyze the Common Crawl index. | |
| This is implemented as a single stream job which accesses S3 via HTTP, | |
| so that it can be easily be run from any laptop, but it could easily be | |
| converted to an EMR job which processed the 300 index files in parallel. |
Have an OpenVPN config file with inline certificates that you need to split up because the Ubuntu team haven't fixed that 2+ year old bug in Network Manger?
You've come to the right place!
This script will split the file out into it's respective certs/keys and output a replacement .ovpn file with cert/key paths.
| package main | |
| import "fmt" | |
| import "github.com/juju/utils/set" | |
| func jaccard(a, b set.Strings) float64 { | |
| return float64(a.Intersection(b).Size()) / float64(a.Union(b).Size()) | |
| } | |
| func ngrams(s string, n int) set.Strings { |
| #!/bin/sh | |
| # Setup encrypted disk image | |
| # For Ubuntu 14.04 LTS | |
| CRYPTFS_ROOT=/cryptfs | |
| apt-get update | |
| apt-get -y upgrade | |
| apt-get -y install cryptsetup |
This is a guide to implementing Getting Things Done (GTD) using [Simpletask][] by [Mark Janssen][].
Simpletask uses the [todo.txt][] syntax, but has sufficient differences and quirks of its own to be worth describing in detail---at least, that's the story I'm going with. I actually began this guide as an exploration of my own trusted system. Personal workflows are by definition eccentric; I have included only what seems to me to be broadly useful.
This implementation of GTD covers the "standard" classifications: next actions by context, projects, somedays, agendas by person and meeting, etc. In a departure from strict GTD, each entry in these lists is also tagged with an area of focus, interest or responsibility. I find that the ability to slice the system by this extra dimension is worth the additional complexity at the processing and organizing stages. Limitations, issues and workarounds are discussed at the end.
Before we begin, some words of wisdom
| var request = require('request'); | |
| var unzip = require('unzip'); | |
| var csv2 = require('csv2'); | |
| request.get('http://s3.amazonaws.com/alexa-static/top-1m.csv.zip') | |
| .pipe(unzip.Parse()) | |
| .on('entry', function (entry) { | |
| entry.pipe(csv2()).on('data', console.log); | |
| }) | |
| ; |
| 1033edge.com | |
| 11mail.com | |
| 123.com | |
| 123box.net | |
| 123india.com | |
| 123mail.cl | |
| 123qwe.co.uk | |
| 126.com | |
| 150ml.com | |
| 15meg4free.com |
| this worked very nice for a single page site | |
| ``` | |
| wget \ | |
| --recursive \ | |
| --page-requisites \ | |
| --convert-links \ | |
| [website] | |
| ``` | |
| wget options |
| import cv2.cv as cv | |
| import tesseract | |
| gray = cv.LoadImage('captcha.jpeg', cv.CV_LOAD_IMAGE_GRAYSCALE) | |
| cv.Threshold(gray, gray, 231, 255, cv.CV_THRESH_BINARY) | |
| api = tesseract.TessBaseAPI() | |
| api.Init(".","eng",tesseract.OEM_DEFAULT) | |
| api.SetVariable("tessedit_char_whitelist", "0123456789abcdefghijklmnopqrstuvwxyz") | |
| api.SetPageSegMode(tesseract.PSM_SINGLE_WORD) | |
| tesseract.SetCvImage(gray,api) | |
| print api.GetUTF8Text() |
