ettorerizza

import re

def changeSeparator(value):
    regex = re.compile(r'("(?:[^"]|"")*"|[^,"\n\r]*)(,|\r?\n|\r)')

    return re.sub(regex, r"\1|||", value)

ettorerizza

#!/usr/bin/env python
# encoding: utf-8

import tweepy 
import csv

# Twitter API credentials
consumer_key = ""
consumer_secret = ""

ettorerizza

import subprocess
import json

json_file = subprocess.run("wdtaxonomy Q634 -f json", shell=True, stdout=subprocess.PIPE).stdout.decode('utf8')

print(json.loads(json_file))

ettorerizza

# List unique values in a DataFrame column
# h/t @makmanalp for the updated syntax!
df['Column Name'].unique()

# Convert Series datatype to numeric (will error if column has non-numeric values)
# h/t @makmanalp
pd.to_numeric(df['Column Name'])

# Convert Series datatype to numeric, changing non-numeric values to NaN
# h/t @makmanalp for the updated syntax!

ettorerizza

for i in *.pdf; do echo $i && pdfinfo "$i" | grep "^Pages:"; done

//pour compter le total de pages

for i in *.pdf; do pdfinfo "$i" | grep "^Pages:"; done | awk '{s+=$2} END {print s}'

ettorerizza

from pywikibot.data import api
import pywikibot
import pprint

def search_entities(site, itemtitle):
     params = { 'action' :'wbsearchentities', 
                'format' : 'json',
                'language' : 'en',
                'type' : 'item',
                'search': itemtitle}

ettorerizza

from google import google


def search_google(query, num_page):
    """
    Search Google using the scraper https://github.com/abenassi/Google-Search-API
    Return the titles of the links and their descriptions.
    Other elements can be :
    name # The title of the link
    link # The external link

ettorerizza

from rosette.api import API, DocumentParameters, RosetteException

def rosette(text):
    """ Run the example """
    # Create an API instance
    api = API(user_key="YOUR_KEY",
              service_url="https://api.rosette.com/rest/v1/")
    params = DocumentParameters()
    params["content"] = text
    params["genre"] = "social-media"

ettorerizza

# -*- coding: utf-8 -*-
""" 
Test du Stanford NER tagger avec les modèles CRF d'Europeana
entrainés sur des journaux :
http://lab.kbresearch.nl/static/html/eunews.html
La fonction est lente --> songer au multiprocessing
"""

from nltk.tag import StanfordNERTagger
from nltk.tokenize import word_tokenize

ettorerizza

library(jqr)

data <- readr::read_file("tweets.json")

data %>% keys()

data %>% jq("{id: .id, hashtag: .entities.hashtags[].text}", 
  "[.id, .hashtag]") %>% jsonlite::toJSON()

stri <- "--h"