Created
March 23, 2016 10:40
-
-
Save clizarralde/a3dcf653d375d476a9c2 to your computer and use it in GitHub Desktop.
This is a spider to get Argentinian soccer stats from promiedos.com.ar
This file contains 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
#!/usr/bin/python | |
# -*- coding: utf-8 -*- | |
import scrapy | |
from scrapy.spiders import CrawlSpider, Rule | |
from scrapy.linkextractors import LinkExtractor | |
from sqlalchemy import create_engine | |
from sqlalchemy.orm import sessionmaker | |
from sqlalchemy.ext.declarative import declarative_base | |
from sqlalchemy import Column, Integer, String, DateTime, Float, Text, Boolean | |
from sqlalchemy.engine.url import URL | |
import settings | |
# cosas de base de datos | |
Base = declarative_base() | |
engine = create_engine(URL(**settings.DATABASE)) | |
Session = sessionmaker(bind=engine) | |
class PartidoModel(Base): | |
__tablename__ = 'vetvot_partido' | |
id = Column(Integer, primary_key=True) | |
descripcion = Column(String(200)) | |
equipo1 = Column(String(100)) | |
gol1 = Column(Integer) | |
equipo2 = Column(String(100)) | |
gol2 = Column(Integer) | |
fecha = Column(DateTime) | |
anio = Column(Integer) | |
nfecha = Column(Integer) | |
class PosicionModel(Base): | |
__tablename__ = 'vetvot_posicion' | |
id = Column(Integer, primary_key=True) | |
anio = Column(Integer) | |
nfecha = Column(Integer) | |
equipo = Column(String(100)) | |
puntos = Column(Integer) | |
posicion = Column(Integer) | |
class PartidoItem(scrapy.Item): | |
partido = scrapy.Field() | |
equipo1 = scrapy.Field() | |
equipo2 = scrapy.Field() | |
gol1 = scrapy.Field() | |
gol2 = scrapy.Field() | |
class PartidoPipeline(object): | |
def __init__(self): | |
""" | |
Initializes database connection and sessionmaker. | |
Creates deals table. | |
""" | |
Base.metadata.create_all(engine) | |
def process_item(self, item, spider): | |
"""Save deals in the database. | |
This method is called for every item pipeline component. | |
""" | |
session = Session() | |
try: | |
if not session.query(PartidoModel).filter_by(equipo1=item['equipo1'].strip(), equipo2=item['equipo2'].strip(),descripcion = item['partido'].strip()).first(): | |
partido = PartidoModel() | |
partido.equipo1 = item['equipo1'].strip() | |
partido.equipo2 = item['equipo2'].strip() | |
partido.gol1 = int(item['gol1']) | |
partido.gol2 = int(item['gol2']) | |
partido.descripcion = item['partido'].strip() | |
session.add(partido) | |
session.commit() | |
except: | |
session.rollback() | |
raise | |
finally: | |
session.close() | |
return item | |
class PromiedosSpider(CrawlSpider): | |
''' | |
Un spider para bajar los partidos de la pagina promiedos | |
''' | |
name = 'promiedos.com.ar' | |
allowed_domains = ['promiedos.com.ar'] | |
start_urls = ['http://www.promiedos.com.ar/historialpartidos.php' , | |
#'http://www.promiedos.com.ar/historialpartidos.php?equipo1=Atl%20Rafaela&equipo2=Belgrano' | |
] | |
custom_settings = { 'ITEM_PIPELINES' : ['promiedos.PartidoPipeline'] } | |
rules = ( | |
# Extract links matching 'category.php' (but not matching 'subsection.php') | |
# and follow links from them (since no callback means follow=True by default). | |
Rule(LinkExtractor(allow=('historialpartidos\.php\?equipo=.*', ), deny=('subsection\.php', ))), | |
# Extract links matching 'item.php' and parse them with the spider's method parse_item | |
Rule(LinkExtractor(allow=('historialpartidos\.php?.equipo.*equipo.*', )), callback='parse_item', follow=False), | |
) | |
def parse_item(self, response): | |
''' | |
<div style="border: 1px solid #888; width: 360px"> | |
<table align="center"> | |
<tbody> | |
<tr> | |
<td colspan="5"> | |
<span class="diadelpart"> | |
Torneo Clausura 2012 - Promoción</span> | |
</td> | |
</tr> | |
<tr style="background: #e5e5e5"> | |
<td width="140"> | |
<img src="images/cuadrados/sanlorenzo.gif" border="0"> San Lorenzo</td> | |
<td width="20" style="text-align: center"> | |
<span class="datoequipo">1</span> | |
</td> | |
<td width="20" style="text-align: center"> | |
<span class="datoequipo">1</span> | |
</td> | |
<td width="140"> | |
<img src="images/cuadrados/instituto.gif" border="0"> Instituto</td> | |
</tr> | |
</tbody></table> | |
</div> | |
''' | |
self.logger.info('Acá esta el historia de dos equipos!: %s', response.url) | |
matches = response.xpath('//div[@style="border: 1px solid #888; width: 360px"]') | |
self.logger.info('Hay %i partidos entre ellos', len(matches)) | |
partidos = [] | |
for m in matches: | |
if 1==1: | |
item = PartidoItem() | |
item['partido'] = m.xpath('table/tr/td/span/text()').extract()[0] | |
item['equipo1'] = m.xpath('table/tr/td/text()').extract()[3] | |
item['gol1'] = m.xpath('table/tr/td/span/text()').extract()[1] | |
item['equipo2'] = m.xpath('table/tr/td/text()').extract()[9] | |
item['gol2'] = m.xpath('table/tr/td/span/text()').extract()[2] | |
partidos.append(item) | |
return partidos | |
if __name__ == '__main__': | |
Base.metadata.create_all(engine) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment