fabianvf

GET _search
{
  "query": {
    "match_all": {}
  }
}

DELETE website

PUT website

fabianvf

- name: Install lxml requirements
  apt: "pkg={{ item }} state=present update_cache=yes"
  sudo: yes
  with_items:
    - python-dev
    - libxml2
    - libxml2-dev
    - libxslt1-dev
    - lib32z1-dev
    - libssl-dev

fabianvf

### Keybase proof

I hereby claim:

  * I am fabianvf on github.
  * I am fabianvf (https://keybase.io/fabianvf) on keybase.
  * I have a public key whose fingerprint is 0D2E 3DAC 3091 715B 7687  2B45 A87E 7040 BF11 F6F0

To claim this, I am signing this object:

fabianvf

# Install elasticsearch
wget https://download.elasticsearch.org/elasticsearch/elasticsearch/elasticsearch-1.4.2.deb
sudo dpkg -i elasticsearch-1.4.2.deb

# Install the wikipedia river
/usr/share/elasticsearch/bin/plugin -i elasticsearch/elasticsearch-river-wikipedia/2.4.1

# Start elasticsearch
sudo service elasticsearch start

fabianvf

{

    "title": "Scrapi",
    "services": 

{

    "query": 

{

fabianvf

import requests

response = requests.get('https://osf.io/api/v1/search/', params={
    'q': 'test AND category:project'  # Full lucene syntax accepted: http://lucene.apache.org/core/2_9_4/queryparsersyntax.html
})

results = response.json()

fabianvf

# coding: utf-8

import json
import requests

HEADERS = {
    'Content-type': 'application/json'
}
URL = 'https://osf.io/api/v1/search/'

fabianvf

{
  "collectionTime": "2014-03-14T00:00:00Z",
  "creationDate": "2014-09-12",
  "creator": [
    {
      "name": "Roger Danger Ebert",
      "sameAs": [
        "/wrgr2/",
        "DAE"
      ],

fabianvf

import os
import json

from scrapi.processing.base import BaseProcessor


class StorageProcessor(BaseProcessor):
    NAME = 'storage'

    def process_raw(self, raw):

fabianvf

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {