ismasan

package main

import (
	"fmt"
	"net/http"
	"time"
)

var urls = []string{
	"http://pulsoconf.co/",

racitup

from bs4 import BeautifulSoup, NavigableString, Tag

def html_to_text(html):
    "Creates a formatted text email message as a string from a rendered html template (page)"
    soup = BeautifulSoup(html, 'html.parser')
    # Ignore anything in head
    body, text = soup.body, []
    for element in body.descendants:
        # We use type and not isinstance since comments, cdata, etc are subclasses that we don't want
        if type(element) == NavigableString:

antonydevanchi

#!/usr/bin/env bash

# Ahalai-mahalai

FLAG="GET_RCV_SMS_LOCAL"
PAGE="1"

# Krible-krable

XMLRESPONSE=$(curl -sL -XPOST 'http://10.0.0.1/xml_action.cgi?method=set&module=duster&file=message' \

spikeekips

# -*- coding: utf-8 -*-

"""
################################################################################
Dump ElasticSearch index for inserting BULK
################################################################################

requires `rawes`.

for more details, run `-h` to show help message.

monkut

# referecing: # https://www.digitalocean.com/community/tutorials/how-to-install-apache-kafka-on-ubuntu-14-04 # https://chongyaorobin.wordpress.com/2015/07/08/step-by-step-of-install-apache-kafka-on-ubuntu-standalone-mode/

1. Add 'kafka' user:

$ sudo useradd kafka -m

2. Install Java:

mattetti

package main

import (
	"fmt"
	"net/http"
	"time"
)

var urls = []string{
	"https://splice.com/",

wshayes

# https://stackoverflow.com/a/13530258/886938

import multiprocessing as mp
import time

fn = 'c:/temp/temp.txt'

def worker(arg, q):
    '''stupidly simulates long running process'''
    start = time.clock()

neu5ron

domain_regex = r'(([\da-zA-Z])([_\w-]{,62})\.){,127}(([\da-zA-Z])[_\w-]{,61})?([\da-zA-Z]\.((xn\-\-[a-zA-Z\d]+)|([a-zA-Z\d]{2,})))'

#Python
domain_regex = '{0}$'.format(domain_regex)
valid_domain_name_regex = re.compile(domain_regex, re.IGNORECASE)
self.domain_name = self.domain_name.lower().strip().encode('ascii')
if re.match(valid_domain_name_regex, self.domain_name ):
    return True
else:
    return False

fgregg

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import os
import csv
import tempfile
import time
import logging
import optparse
import itertools

snakers4

import gc
import gzip
import time
import json
import shutil
import os,sys
import tldextract
import collections
import pandas as pd
from tqdm import tqdm