anjesh

{
  "id": 3055235,
  "regNumber": "14/00001",
  "purchaseQuarter": "III,IV",
  "tenderType": {
    "id": 7,
    "created": "01.12.2008",
    "endDate": null,
    "mdValue": "Cerere a ofertelor de preţuri",
    "ruValue": "Запрос ценовых оферт",

anjesh

faqs=document.querySelectorAll('.rule')
for(var i=0;i<faqs.length;i++) {   
    var faq = faqs[i];
    var divs = faq.getElementsByTagName('div');
    console.log(divs[0].outerText.trim())
    console.log("==")
    console.log(divs[3].outerText.trim())
    console.log("--------------------------------------")
}

anjesh

# coding=utf-8

# convert the count in the column into multiple rows
# e.g.
# a,b,c,2,1
# becomes
# a,b,c,Male
# a,b,c,Male
# a,b,c,FeMale

anjesh

from nltk.corpus import stopwords
from nltk.stem import PorterStemmer
from nltk.tokenize import WordPunctTokenizer, PunktWordTokenizer
import string
from os import listdir
from os.path import isfile, join
import logging

logger = logging.getLogger(__name__)

anjesh

ogr2ogr -f "kml" Baglung.kml NPL_adm4.shp -sql "select NAME_2 AS ZONE,NAME_3 AS DISTRICT, NAME_4 AS VDC from NPL_adm4 where NAME_3='Baglung'"
ogr2ogr -f "kml" Mustang.kml NPL_adm4.shp -sql "select NAME_2 AS ZONE,NAME_3 AS DISTRICT, NAME_4 AS VDC from NPL_adm4 where NAME_3='Mustang'"
ogr2ogr -f "kml" Myagdi.kml NPL_adm4.shp -sql "select NAME_2 AS ZONE,NAME_3 AS DISTRICT, NAME_4 AS VDC from NPL_adm4 where NAME_3='Myagdi'"
ogr2ogr -f "kml" Parbat.kml NPL_adm4.shp -sql "select NAME_2 AS ZONE,NAME_3 AS DISTRICT, NAME_4 AS VDC from NPL_adm4 where NAME_3='Parbat'"
ogr2ogr -f "kml" Bhaktapur.kml NPL_adm4.shp -sql "select NAME_2 AS ZONE,NAME_3 AS DISTRICT, NAME_4 AS VDC from NPL_adm4 where NAME_3='Bhaktapur'"
ogr2ogr -f "kml" Dhading.kml NPL_adm4.shp -sql "select NAME_2 AS ZONE,NAME_3 AS DISTRICT, NAME_4 AS VDC from NPL_adm4 where NAME_3='Dhading'"
ogr2ogr -f "kml" Kathmandu.kml NPL_adm4.shp -sql "select NAME_2 AS ZONE,NAME_3 AS DISTRICT, NAME_4 AS VDC from NPL_adm4 where NAME_3='Kathmandu'"
ogr2ogr -f "kml" Kavrepala

anjesh

ogr2ogr -f "GeoJSON" Baglung.json NPL_adm4.shp -sql "select NAME_2 AS ZONE,NAME_3 AS DISTRICT, NAME_4 AS VDC from NPL_adm4 where NAME_3='Baglung'"
ogr2ogr -f "GeoJSON" Mustang.json NPL_adm4.shp -sql "select NAME_2 AS ZONE,NAME_3 AS DISTRICT, NAME_4 AS VDC from NPL_adm4 where NAME_3='Mustang'"
ogr2ogr -f "GeoJSON" Myagdi.json NPL_adm4.shp -sql "select NAME_2 AS ZONE,NAME_3 AS DISTRICT, NAME_4 AS VDC from NPL_adm4 where NAME_3='Myagdi'"
ogr2ogr -f "GeoJSON" Parbat.json NPL_adm4.shp -sql "select NAME_2 AS ZONE,NAME_3 AS DISTRICT, NAME_4 AS VDC from NPL_adm4 where NAME_3='Parbat'"
ogr2ogr -f "GeoJSON" Bhaktapur.json NPL_adm4.shp -sql "select NAME_2 AS ZONE,NAME_3 AS DISTRICT, NAME_4 AS VDC from NPL_adm4 where NAME_3='Bhaktapur'"
ogr2ogr -f "GeoJSON" Dhading.json NPL_adm4.shp -sql "select NAME_2 AS ZONE,NAME_3 AS DISTRICT, NAME_4 AS VDC from NPL_adm4 where NAME_3='Dhading'"
ogr2ogr -f "GeoJSON" Kathmandu.json NPL_adm4.shp -sql "select NAME_2 AS ZONE,NAME_3 AS DISTRICT, NAME_4 AS VDC from NPL_adm4 where NAME_3='Kat

anjesh

"""
Basically breaks down the row containing the locations (separated by \n) into multiple rows

e.g. location field contain the following text and the script gives 4 rows for that, and copies the same id and title in all 4 rows
" - Banke (Nepalgunj)
 - Dhanusa (Janakpur)
 - Rupandehi (Bhairahawa)
 - Sunsari (Inaruwa)"

anjesh

# csvfix to be installed

# All CRS projects zip files available at http://stats.oecd.org/Index.aspx?datasetcode=CRS1# export > related files

# here 2011 is used as an example, for other years, you have to update the command content below

wget "http://stats.oecd.org/FileView2.aspx?IDFile=d79d2d4e-f15a-41de-83f8-b61a8f5c227a" -O CRS-2011.zip
unzip CRS-2011.zip

# there's some binary characters which needs to be removed before transformation

anjesh

curl -XDELETE http://localhost:9200/testcompany/

curl -XPUT 'http://localhost:9200/testcompany/'

curl -XPUT 'http://localhost:9200/testcompany/activity1/_mapping' -d '{
    "activity" : {
        "properties" : {
            "organization" : {"analyzer": "keyword", "type": "string"}
        }
    }