import re

import scrapy
from vesseltracker.items import VesseltrackerItem


class GetVessel(scrapy.Spider):
    name = "getvessel"
    allowed_domains = ["marinetraffic.com"]
    start_urls = [
        'http://www.marinetraffic.com/en/ais/index/ports/all/flag:AE',
    ]

def parse(self, response):
    item = VesseltrackerItem()
    for ports in response.xpath('//table/tr[position()>1]'):
        item['port_name'] = ports.xpath('td[2]/a/text()').extract()
        port_homepage_url = ports.xpath('td[7]/a/@href').extract()
        port_homepage_url = response.urljoin(port_homepage_url)
        yield scrapy.Request(port_homepage_url, callback=self.parse, meta={'item': item})