Jaakko Lappalainen jkklapp

## scraper.py
from lxml import html
import requests

# Set the number of pages to scrap
PAGES_TO_SCRAP = 15
# Base URL for the seach results.
BASE_PAGE = 'http://www.wegottickets.com/searchresults/page/'

# XPATH selector for the event links
EVENT_LINK_SELECTOR = '//a[@class="event_link"]'

## get_xlsx.py
#!/usr/bin/env python

import xml.etree.ElementTree as ET
import os
import urllib, urllib2
# Get the HTML
response = urllib2.urlopen('http://www.cuartopoder.es/multimedia/2014/10/11/gastos-de-los-exdirectivos-de-caja-madrid-uno-a-uno-con-las-tarjetas-negras-tabla/3403')
html = response.read()

# Parse the HTML looking for the links

## bc.html
<!DOCTYPE html>
<meta charset="utf-8">
<style>

span, strong {
  font-family: "Helvetica Neue", Helvetica, Arial;
  font-size: 14px;
}

text {

## see_data.html
<!DOCTYPE html>
<meta charset="utf-8">
<style>

body {
  font-family: "Helvetica Neue", Helvetica, Arial, sans-serif;
  margin: auto;
  position: relative;
  width: 960px;
}

## get_data.py
#!/usr/bin/env python

import os, sys, json

def get_dir_size(base_dir):
    total_size = 0
    for dirpath, dirnames, filenames in os.walk(base_dir):
        if '/.' in dirpath:
            continue
        for f in filenames:

## magneter
#!/usr/bin/env python

import time
import requests
import xmltodict
import sys
from lxml import etree


BASE_URL = 'http://thepiratebay.si/search/'

## bash_command_history.py
#!/usr/bin/env python
from os.path import expanduser
from itertools import groupby
import matplotlib.pyplot as plt
import numpy as np
from numpy import arange


def plotTagValues(data,tag):
	labels = data.keys()
	from lxml import html
	import requests

	# Set the number of pages to scrap
	PAGES_TO_SCRAP = 15
	# Base URL for the seach results.
	BASE_PAGE = 'http://www.wegottickets.com/searchresults/page/'

	# XPATH selector for the event links
	EVENT_LINK_SELECTOR = '//a[@class="event_link"]'
	#!/usr/bin/env python

	import xml.etree.ElementTree as ET
	import os
	import urllib, urllib2
	# Get the HTML
	response = urllib2.urlopen('http://www.cuartopoder.es/multimedia/2014/10/11/gastos-de-los-exdirectivos-de-caja-madrid-uno-a-uno-con-las-tarjetas-negras-tabla/3403')
	html = response.read()

	# Parse the HTML looking for the links
	<!DOCTYPE html>
	<meta charset="utf-8">
	<style>

	span, strong {
	font-family: "Helvetica Neue", Helvetica, Arial;
	font-size: 14px;
	}

	text {
	#!/usr/bin/env python

	import os, sys, json

	def get_dir_size(base_dir):
	total_size = 0
	for dirpath, dirnames, filenames in os.walk(base_dir):
	if '/.' in dirpath:
	continue
	for f in filenames:
	#!/usr/bin/env python

	import time
	import requests
	import xmltodict
	import sys
	from lxml import etree


	BASE_URL = 'http://thepiratebay.si/search/'
	#!/usr/bin/env python
	from os.path import expanduser
	from itertools import groupby
	import matplotlib.pyplot as plt
	import numpy as np
	from numpy import arange


	def plotTagValues(data,tag):
	labels = data.keys()