truncus03.py

#coding: utf-8
__author__ = 'britodfbr'

from bs4 import BeautifulSoup
import inspect
import re
import requests
import os
import sys

def truncus03a(url='http://legis.senado.leg.br/legislacao/ListaTextoSigen.action?norma=483900&id=14310946&idBinario=15795498&mime=application/rtf',
               path='', filename=''):
    header = '<!DOCTYPE html>' \
             '<html lang="pt-br">' \
             '<head>' \
             '<meta http-equiv="Content-Type" content="text/html; charset=iso8859-1"/>' \
             '<link rel="stylesheet" href="../../../saj_projects/view/legis_3.css">' \
             '</head>' \
             '<body>' \
             '<header> ' \
                '<h3>Subchefia para Assuntos Jurídicos</h3> ' \
             '</header>'
    footer='<p class="dou">Este texto não substitui o publicado no DOU de 17.1.2018</p></body></html>'
    if not filename:
        filename = '{}.html'.format(inspect.stack()[0][3])

    if not path:
        path = ''
        #os.mkdir(path, 0o755)

    page = re.sub(r' style="[^"]+"', '', requests.get(url).text)
    page = re.sub(r'<span>|</span>', '', page)
    page = re.sub(r'EpgrafeAlt1|Epgrafe', 'epigrafe', page)
    page = re.sub(r'EmentaAlt2|Ementa', 'ementa', page)
    page = re.sub(r'Assinatura1Alt7|Assinatura1', 'presidente', page)
    page = re.sub(r'Assinatura2Alt8|Assinatura2', 'ministro', page)
    soup = BeautifulSoup(page, 'html.parser').find_all(id='conteudoPrincipal')
    caterva = soup[0].div.html.body

    container = caterva.find_all('div')[2]
    print(container)
    result = header + container.prettify() + footer
    print(BeautifulSoup(result, 'html.parser').prettify())
    #os.mkdir(path, 0o755)
    with open("{}{}".format(path, filename), 'w') as file:
        file.write(BeautifulSoup(result, 'html.parser').prettify())
        pass
    print('-' * 20)
    sys.exit(0)


if __name__ == '__main__':
    truncus03a()