Created
November 15, 2012 04:55
-
-
Save mekler/4076744 to your computer and use it in GitHub Desktop.
scraper de diputados en méxico (noviembre-2012) con scrapy
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 scrapy.contrib.spiders import CrawlSpider, Rule | |
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor | |
from scrapy.selector import HtmlXPathSelector | |
from diputados.items import DiputadosItem | |
from time import time | |
import re | |
class DiputadosSpider(CrawlSpider): | |
name = 'diputados' | |
allowed_domains = ["sitl.diputados.gob.mx"] | |
start_urls = [ | |
'http://sitl.diputados.gob.mx/LXII_leg/listado_diputados_gpnp.php?tipot=TOTAL' | |
] | |
rules = [Rule(SgmlLinkExtractor(allow=[r'LXII_leg/curricula([\w\W])+$']), callback='parse_diputados', follow=True)] | |
def parse_diputados(self, response): | |
hxs = HtmlXPathSelector(response) | |
items = [] | |
item = DiputadosItem() | |
print response.url | |
item['tipo_eleccion'] = hxs.select('//html/body/table/tr[3]/td/table[2]/tr[2]/td[2]/text()').extract()[0].strip().encode('utf-8') | |
item['nombre'] = hxs.select('/html/body/table/tr[3]/td/table[2]/tr/td[3]/span/text()').extract()[0].strip().encode('utf-8') | |
aux = hxs.select('/html/body/table/tr[3]/td/table[2]/tr/td/img/@src').extract() | |
item['imagenes'] = aux | |
item['entidad'] = hxs.select('/html/body/table/tr[3]/td/table[2]/tr[3]/td/text()').extract()[0].strip().encode('utf-8') | |
item['distrito'] = hxs.select('/html/body/table/tr[3]/td/table[2]/tr[4]/td[2]/text()').extract()[0].strip().encode('utf-8') | |
item['suplente'] = hxs.select('/html/body/table/tr[3]/td/table[2]/tr[7]/td/span/text()').extract()[0].strip().encode('utf-8') | |
item['cumpleanios'] = hxs.select('/html/body/table/tr[3]/td/table[2]/tr[8]/td/text()').extract()[0].strip().encode('utf-8') | |
item['foto'] = 'http://sitl.diputados.gob.mx/LXII_leg/'+aux[0][2:] | |
item['correo'] = hxs.select('/html/body/table/tr[3]/td/table[2]/tr[9]/td/a/text()').extract()[0].strip() | |
if aux[1] == 'images/pri01.png': | |
item['partido'] = 'pri' | |
elif aux[1] == 'images/pan.png': | |
item['partido'] = 'pan' | |
elif aux[1] == 'images/prd01.png': | |
item['partido'] = 'prd' | |
elif aux[1] == 'images/logvrd.jpg': | |
item['partido'] = 'partido verde' | |
elif aux[1] == 'images/logo_movimiento_ciudadano.png': | |
item['partido'] = 'movimiento ciudadano' | |
elif aux[1] == 'images/logpt.jpg': | |
item['partido'] = 'pt' | |
elif aux[1] == 'images/panal.gif': | |
item['partido'] = 'panal' | |
items.append(item) | |
return items |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment