patrickvossler18

# -*- coding: utf-8 -*-
import requests
import json
from datetime import datetime
import csv
import time

class scraping:

    def __init__(self):

rvanbruggen

// this script uses the neo4j-shell-tools

// create personal nodes
import-cypher -d ; -i ./IMPORT/INPUT/PersonalNodes.csv -o ./IMPORT/OUTPUT/personalnodeout.csv create (n:url {id:{id}+1000,name:{name},type:{type}}) return n.name as name
 
// create indices
CREATE index on :url(name);  
CREATE index on :url(id);
CREATE index on :url(type);
 

marcgg

# Matches patterns such as:
#    https://www.facebook.com/my_page_id => my_page_id
#    http://www.facebook.com/my_page_id => my_page_id
#    http://www.facebook.com/#!/my_page_id => my_page_id
#    http://www.facebook.com/pages/Paris-France/Vanity-Url/123456?v=app_555 => 123456
#    http://www.facebook.com/pages/Vanity-Url/45678 => 45678
#    http://www.facebook.com/#!/page_with_1_number => page_with_1_number
#    http://www.facebook.com/bounce_page#!/pages/Vanity-Url/45678 => 45678
#    http://www.facebook.com/bounce_page#!/my_page_id?v=app_166292090072334 => my_page_id
#    http://www.facebook.com/my.page.is.great => my.page.is.great