Skip to content

Instantly share code, notes, and snippets.

View christopherkullenberg's full-sized avatar

Christopher Kullenberg christopherkullenberg

50 followers · 9 following
View GitHub Profile
@christopherkullenberg
christopherkullenberg / swepubscraper.py
Created December 29, 2015 18:28
from urllib.request import urlopen
counter = 1
while True:
url = 'http://libris.kb.se/xsearch?d=swepub&hitlist&q=l%C3%A4ros%C3%A4te%3agu&f=ext&spell=true&hist=true&n=200&format=json&start=' + str(counter)
print ("Fetching: " + url)
data = urlopen(url).read()
if not data.find(b'"identifier"') >= 0:
print("No more records!")
@christopherkullenberg
christopherkullenberg / swepubjsonparser.py
Created December 29, 2015 22:05
import json
from os import listdir
for filename in listdir("GU20151228json/"): #alla filer i en katalog
with open("GU20151228json/" + filename) as currentFile:
jsondata = json.load(currentFile)
print(jsondata)
@christopherkullenberg
christopherkullenberg / swepubxmlparser.py
Created December 30, 2015 13:07
Question concering XML
"""
Data structure: http://libris.kb.se/xsearch?d=swepub&hitlist&q=l%C3%A4ros%C3%A4te%3agu&f=ext&spell=true&hist=true&n=200&p=1
Trying to access only the value after "code="u">" in:
<datafield tag="700" ind1="1" ind2=" ">
<subfield code="a">Alvestad, Torgeir,</subfield>
<subfield code="d">1960-,</subfield>
<subfield code="u">Göteborgs universitet, Institutionen för pedagogik och didaktik, University of Gothenburg, Department of Education</subfield>
<subfield code="4">edt</subfield>
<subfield code="0">(SwePub:chalmers.se)xalvto</subfield>
</datafield>
@christopherkullenberg
christopherkullenberg / tweetTSVtoGEXF.py
Created January 3, 2016 20:46
import csv
from os import listdir
import re
from gexf import *
gexf = Gexf("Twitter Mentions Network", "Test")
graph = gexf.addGraph("directed", "static", "Twitter network")
@christopherkullenberg
christopherkullenberg / Swepub to gexf.py
Last active January 18, 2016 19:15
swepubgexf.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")
@christopherkullenberg
christopherkullenberg / facescraper.py
Created April 10, 2016 09:02
#-*- 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
@christopherkullenberg
christopherkullenberg / facebooksok.py
Created April 10, 2016 09:19
#!/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
@christopherkullenberg
christopherkullenberg / index.html
Created April 10, 2016 09:21
<html>
<head>
<meta charset="utf-8" />
<link rel="stylesheet" href="style.css">
<title>Facescraper</title>
</head>
<body>
@christopherkullenberg
christopherkullenberg / almedalenparser.py
Created July 2, 2016 06:55
Parse html of almedalsveckan.info
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" })
@christopherkullenberg
christopherkullenberg / colorconverter.py
Created August 29, 2016 19:53
'''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'''