Last active
October 8, 2018 15:47
-
-
Save zuhrig/7f05bf6d342438da9ee9cbea0ef74da7 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
import urllib2 | |
from bs4 import BeautifulSoup | |
numero_expediente = 61333 | |
url = "http://www.concejodeliberante.laplata.gov.ar/MesaEntradas/expediente.asp?Numero={}&Buscar=Enviar".format(numero_expediente) | |
page = urllib2.urlopen(url) | |
soup = BeautifulSoup(page, 'html.parser') | |
expediente = { | |
"id": [text for text in soup.table.find_all('tr')[0].find_all('li')[0].stripped_strings][1], | |
"started": [text for text in soup.table.find_all('tr')[0].find_all('li')[1].stripped_strings][1], | |
"started_date": [text for text in soup.table.find_all('tr')[0].find_all('li')[2].stripped_strings][1], | |
"presentation_type": [text for text in soup.table.find_all('tr')[0].find_all('li')[3].stripped_strings][1], | |
"detail": [text for text in soup.table.find_all('tr')[0].find_all('li')[4].stripped_strings][1], | |
"status": [text for text in soup.table.find_all('tr')[1].find_all('li')[0].stripped_strings][1], | |
"last_update": soup.table.find_all('tr')[1].find_all('li')[1].get_text().split(':')[1].replace(u'\xa0',''), | |
"resolution_id": soup.table.find_all('tr')[1].find_all('li')[2].get_text().split(':')[1].replace(u'\xa0','').replace(u'\xb0','') | |
} | |
print(expediente) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment