fmasanori

import requests
import json
import pymongo

connection = pymongo.MongoClient("mongodb://localhost")
db = connection.bnmp
mandados_mongoDB = db.mandados

cabeçalho = {
    'Host': 'www.cnj.jus.br',

fmasanori

https://gist.github.com/fmasanori/ee2b554ee6e05f298d5014bcbf730fd7
Cats
Abdul Abel Abelarda Abelardo Abelhinha Abigail Abner Abu Acacia Ace Acerola Adda Adonis Adrik Adry Afrodite Agapi Agostinho Agripina(o) Aiara Aícha Aika(o) Aiki Aila Aileen Aima Aimee Aislan Aiwa Akan Akaya Akenaton Akesa Alanis Alec Alecrim Aleetza Alef Alegria Aleluia Alemã Alemão Aleska Alex Alf Alfa Alface Algodão Alice Alicia Alika Alina Alisson Alita Alladim Alma Almôndega Aloha Alone Alpha Alphi Alvinha Amapola Amaral Amarula Amaya Ambar Amber Ameli Amendoim Amie Amiga(o) Amigão Amiguinha(o) Amin Amira Amon Amor Amora Amoreko Amoroso Amy Anakin Anda Andie Andora Andy Angel Angra Angus Anjinha Anjinho Anúbis Anukh Apache Apagão Aphou Apiá Apoena Apolo  Apple April Aquiles Arã Arabi Aragon Aramis Aranha Arashi Archie Arena Aretha Argos Ariadne Ariel Ariela Arine Aristóteles Arkan Armani Aroeira Aron  Arrepio Arteira Artemis Arthur Aruan Aruane Aruck Aruska Ashley Aska Asla Aslam Aspen Asrama Assombroso Aster Asterix Asthar Astolfo As

fmasanori

f = open('UFRJ.txt')
dic = {}
for linha in f:
  id_servidor, nome, valor = linha.strip().split(',')
  dic[id_servidor] = [nome, float(valor)]
f.close()

def salário(a): return a[1][1]
maiores = sorted(dic.items(), key=salário, reverse=True)
for f in maiores[:50]:

fmasanori

import requests
from bs4 import BeautifulSoup as bs

u = 'http://www.portaldatransparencia.gov.br/servidores/OrgaoLotacao-ListaServidores.asp?CodOS=15000&DescOS=MINISTERIO%20DA%20EDUCACAO&CodOrg=26245&DescOrg=UNIVERSIDADE%20FEDERAL%20DO%20RIO%20DE%20JANEIRO&Pagina='
base = 'http://www.portaldatransparencia.gov.br/'

def extrai_valor(u):
    j = u.find('=') + 1
    k = u.find('&', j)
    id_servidor = u[j: k]

fmasanori

import os
import csv

linhas = 0
def extrai_valores(t):
  k = 1
  while True:
    j = k
    k = t.find(' ', k)
    k += 1 

fmasanori

import PyPDF2
import os
import os.path

def traduz(f):
  pdfFileObj = open(f, 'rb')
  try:
    pdfReader = PyPDF2.PdfFileReader(pdfFileObj)
  except:
    print (f, 'corrompido')

fmasanori

import requests
from bs4 import BeautifulSoup as bs
from urllib.request import urlretrieve
u1 = 'https://www.al.sp.gov.br/alesp/pesquisa-proposicoes/?direction=acima&lastPage=5167&currentPage='
u2 = '&act=detalhe&idDocumento=&rowsPerPage=10&currentPageDetalhe=1&tpDocumento=&method=search&text=&natureId=4005&legislativeNumber=&legislativeYear=&natureIdMainDoc=loa&anoDeExercicio=&legislativeNumberMainDoc=&legislativeYearMainDoc=&strInitialDate=01%2F01%2F2010&strFinalDate=31%2F12%2F2014&author=&supporter=&politicalPartyId=&tipoDocumento=&stageId=&strVotedInitialDate=&strVotedFinalDate='
base = 'https://www.al.sp.gov.br'
def baixa_pdf(u, nome):
    url = base + u
    fim = nome.find('-') - 1
    nome = nome.replace('/', '-')

fmasanori

#!/usr/bin/env python

"""
Converts PDF text content (though not images containing text) to plain text, html, xml or "tags".
"""
import sys
import logging
import six
import pdfminer.settings
pdfminer.settings.STRICT = False

fmasanori

import requests
from bs4 import BeautifulSoup as bs
import string

pets = []
for pet in ('Gatos', 'Caes'):
  for letra in string.ascii_uppercase:
    for k in (1, 2, 3):
      u = 'https://www.bayerpet.com.br/%s/lista-nomes/%s%s' %(pet, letra, str(k))
      p = requests.get(u)

fmasanori

#Laura Maia e Letícia Barreto
import requests
from bs4 import BeautifulSoup
url='https://pt.wikipedia.org/wiki/Os_100_livros_do_s%C3%A9culo_segundo_Le_Monde'
soup = BeautifulSoup(requests.get(url).text, 'html.parser')

nome=[nome.string.strip()
      for nome in soup.findAll('i')]

ranking=[rank.string