Christopher Kullenberg christopherkullenberg

## searchaltmedia.ipynb

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                christopherkullenberg
                / searchaltmedia.ipynb
            
            
              Created
              January 11, 2017 20:55
            
              
                Search Alt (Right) Media
              
          
      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## pdftotext2.py
from subprocess import Popen, PIPE, STDOUT
from nltk.tokenize import sent_tokenize #make sure to install the full corpus.
import re

aFile = '/home/christopher/Desktop/Introduction to Computation and Programming Using Python, Revised - Guttag, John V..pdf'

def pdftoText(filename):
    '''
    Input: a PDF file
    Output: output of pdftotext.

## pdftotext.py
def pdfparser(fn):
    import subprocess
    '''Requires pdftotext to be installed on the system. Please change directories
    accordingly.'''
    f = "upload/" + fn # fn is the filename. upload/ is a directory, pls change.
    cmd = 'python3 upload/pdf2txt.py -o %s.txt %s' % (f.split('.')[0], f)
    run = subprocess.Popen(cmd, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
    out, err = run.communicate()
    # display errors if they occur
    #if err:

## colorconverter.py
'''Use with Python3'''
import re
import struct
import textwrap

thefile = open('style.css', encoding="utf-8")
lines = thefile.readlines()

def colorchanger(hexnumber):
    '''Substitute hex colors according to Andrejs formula. Return RGB-strings for CSS'''

## almedalenparser.py
import urllib.request
import re
from bs4 import BeautifulSoup

with urllib.request.urlopen('http://www.almedalsveckan.info/event/user-view/38029') as event:
    html = event.read()
    soup = BeautifulSoup(html, 'html.parser')
    datadivs = soup.findAll("div", { "class" : "row clearfix" })
    for d in datadivs:
        leftdivs = d.findAll("div", { "class" : "leftcol" })

## index.html
<html>
<head>
    <meta charset="utf-8" />
    <link rel="stylesheet" href="style.css">
    <title>Facescraper</title>
</head>

<body>


## facebooksok.py
#!/usr/bin/env python3
# -*- coding: UTF-8 -*-
# Import modules for CGI handling and UTF-8 handling of input/output
import cgi, cgitb
import sys
import re
import os
import sqlite3
import numpy as np
import collections

## facescraper.py
#-*- coding: utf8 -*-
import json
from json import load
import sqlite3
import hmac
import hashlib
from facepy import GraphAPI
from django.core.serializers.json import DjangoJSONEncoder
import json

## Swepub to gexf.py
from os import listdir
from lxml import etree as ET
from gexf import *
from itertools import combinations
#import xml.etree.ElementTree as ET #Use this if you don't have lxml installed

# Open up a gexf file
gexf = Gexf("Author-Institution network", "GU")
graph = gexf.addGraph("undirected", "static", "Swepub network")
attribute_node = graph.addNodeAttribute("University", "default_value", "string")

## tweetTSVtoGEXF.py
import csv
from os import listdir
import re
from gexf import *


gexf = Gexf("Twitter Mentions Network", "Test")
graph = gexf.addGraph("directed", "static", "Twitter network")
	from subprocess import Popen, PIPE, STDOUT
	from nltk.tokenize import sent_tokenize #make sure to install the full corpus.
	import re

	aFile = '/home/christopher/Desktop/Introduction to Computation and Programming Using Python, Revised - Guttag, John V..pdf'

	def pdftoText(filename):
	'''
	Input: a PDF file
	Output: output of pdftotext.
	def pdfparser(fn):
	import subprocess
	'''Requires pdftotext to be installed on the system. Please change directories
	accordingly.'''
	f = "upload/" + fn # fn is the filename. upload/ is a directory, pls change.
	cmd = 'python3 upload/pdf2txt.py -o %s.txt %s' % (f.split('.')[0], f)
	run = subprocess.Popen(cmd, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
	out, err = run.communicate()
	# display errors if they occur
	#if err:
	'''Use with Python3'''
	import re
	import struct
	import textwrap

	thefile = open('style.css', encoding="utf-8")
	lines = thefile.readlines()

	def colorchanger(hexnumber):
	'''Substitute hex colors according to Andrejs formula. Return RGB-strings for CSS'''
	import urllib.request
	import re
	from bs4 import BeautifulSoup

	with urllib.request.urlopen('http://www.almedalsveckan.info/event/user-view/38029') as event:
	html = event.read()
	soup = BeautifulSoup(html, 'html.parser')
	datadivs = soup.findAll("div", { "class" : "row clearfix" })
	for d in datadivs:
	leftdivs = d.findAll("div", { "class" : "leftcol" })
	<html>
	<head>
	<meta charset="utf-8" />
	<link rel="stylesheet" href="style.css">
	<title>Facescraper</title>
	</head>

	<body>
	#!/usr/bin/env python3
	# -- coding: UTF-8 --
	# Import modules for CGI handling and UTF-8 handling of input/output
	import cgi, cgitb
	import sys
	import re
	import os
	import sqlite3
	import numpy as np
	import collections
	#-- coding: utf8 --
	import json
	from json import load
	import sqlite3
	import hmac
	import hashlib
	from facepy import GraphAPI
	from django.core.serializers.json import DjangoJSONEncoder
	import json
	from os import listdir
	from lxml import etree as ET
	from gexf import *
	from itertools import combinations
	#import xml.etree.ElementTree as ET #Use this if you don't have lxml installed

	# Open up a gexf file
	gexf = Gexf("Author-Institution network", "GU")
	graph = gexf.addGraph("undirected", "static", "Swepub network")
	attribute_node = graph.addNodeAttribute("University", "default_value", "string")
	import csv
	from os import listdir
	import re
	from gexf import *


	gexf = Gexf("Twitter Mentions Network", "Test")
	graph = gexf.addGraph("directed", "static", "Twitter network")