Created
March 8, 2019 21:14
-
-
Save pmarkun/12296625ccd1bcdc42032e0a0abdf6b0 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from lxml.html import parse | |
| from urllib import request | |
| import csv | |
| def get_info_autor(autor): | |
| soup = parse(request.urlopen(autor['url'])).getroot() | |
| p = soup.cssselect("#infoGeral")[0] | |
| autor['partido'] = p.xpath('.//label[text()=" Partido "]')[0].getnext().text.strip() | |
| return autor | |
| def get_detalhes(pl): | |
| soup = parse(request.urlopen(pl['url'])).getroot() | |
| d = soup.cssselect(".tabelaDados")[0] | |
| pl['documento'] = d.cssselect(".campo_conteudo a")[0].get('href') | |
| pl['numero'] = d.xpath('.//td[text()="Número Legislativo"]')[0].getnext().text.split('/')[0].strip() | |
| pl['ano'] = d.xpath('.//td[text()="Número Legislativo"]')[0].getnext().text.split('/')[1].strip() | |
| pl['regime'] = d.xpath('.//td[text()="Regime"]')[0].getnext().text.strip() | |
| pl['apoiadores'] = d.xpath('.//td[text()="Apoiador(es)"]')[0].getnext().text_content().strip() | |
| if d.xpath('.//td[text()="Transformado em Norma"]'): | |
| pl['norma'] = 1 | |
| else: | |
| pl['norma'] = 0 | |
| return pl | |
| def getPLs(autores): | |
| base_url = "https://www.al.sp.gov.br/alesp/pesquisa-proposicoes/" | |
| args = "?direction=inicio&lastPage=5&act=detalhe&idDocumento=&rowsPerPage=1000¤tPageDetalhe=1&tpDocumento=&method=search&text=Declara%20de%20UTILIDADE%2520P%25C3%259ABLICA&natureId=1¤tPage=" | |
| soup = parse(request.urlopen(base_url+args+str(0))).getroot() | |
| lista_pl = [] | |
| count = 0 | |
| for x in soup.cssselect("#lista_resultado .tabela tr a")[1:]: | |
| pl = {} | |
| pl['url'] = 'https://www.al.sp.gov.br' + x.get('href') | |
| pl['titulo'] = x.cssselect("strong")[0].text | |
| pl['ementa'] = x.cssselect("br")[0].tail.strip() | |
| pl['autor'] = x.getparent().getnext().text.split('\n')[0] | |
| if pl['autor'] in autores: | |
| pl['partido'] = autores[pl['autor']]['partido'] | |
| pl['area'] = autores[pl['autor']]['area'] | |
| pl['base'] = autores[pl['autor']]['base'] | |
| else: | |
| pass | |
| pl = get_detalhes(pl) | |
| count += 1 | |
| if count > 100: | |
| print ("Got 10!") | |
| count = 0 | |
| lista_pl.append(pl) | |
| return lista_pl | |
| def getAutores(): | |
| url = "https://www.al.sp.gov.br/alesp/deputados-estaduais/?filtroNome=&filtroAreaAtuacao=&filtroBaseEleitoral=&filtroPartido=&filtroLegislatura=18&filtroEmExercicioPesquisa=N&filtroLegislaturaAtual=S" | |
| soup = parse(request.urlopen(url)).getroot() | |
| linhas = soup.cssselect(".tabela tbody tr") | |
| autores = {} | |
| for p in linhas: | |
| nome = p.xpath('.//td/a')[0].text.strip() | |
| autores[nome] = {} | |
| autores[nome]['nome'] = p.xpath('.//td/a')[0].text.strip() | |
| autores[nome]['area'] = p.xpath('.//td')[1].text.strip() | |
| autores[nome]['base'] = p.xpath('.//td')[2].text.strip() | |
| autores[nome]['partido'] = p.xpath('.//td')[3].text.strip() | |
| print("Getting "+nome) | |
| return autores | |
| def escrevecsv(lista_pl): | |
| with open('projetos.csv', 'w') as f: # Just use 'w' mode in 3.x | |
| w = csv.DictWriter(f, lista_pl[0].keys()) | |
| w.writeheader() | |
| for row in lista_pl: | |
| w.writerow(row) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment