Question

我正在使用Scrapy从http://www.vesselfinder.com/vessels

下载图片

但是，我只能获得像http://www.vesselfinder.com/vessels/ship-photo/0-227349190-7c01e2b3a7a5078ea94fff9a0f862f8a/0

这样的图像的相对网址

所有图片都名为0.jpg，但如果我尝试使用该绝对网址，则无法访问该图片。

我的代码：的 items.py

import scrapy

class VesselItem(scrapy.Item):
    name = scrapy.Field()
    nationality = scrapy.Field()
    image_urls = scrapy.Field()
    images = scrapy.Field()

pipelines.py

import scrapy
from scrapy.contrib.pipeline.images import ImagesPipeline
from scrapy.exceptions import DropItem

class VesselPipeline(object):
    def get_media_requests(self, item, info):
        for image_url in item['image_urls']:
            yield scrapy.Request(image_url)

    def item_completed(self, results, item, info):
        image_paths = [x['path'] for ok, x in results if ok]
        if not image_paths:
            raise DropItem("Item contains no images")
        item['image_paths'] = image_paths
        return item

vessel_spider.py

import scrapy
import string

from vessel.items import VesselItem

class VesselSpider(scrapy.Spider):
    """docstring for VesselSpider"""
    name = "vessel"
    allowed_domains = ["vesselfinder.com"]
    page_name = "http://vesselfinder.com"
    start_urls = [
        # "http://vesselfinder.com/vessels?page=%d" %i for i in range(0,1000)
        "http://vesselfinder.com/vessels"
    ]

    def parse(self, response):
        f = open('vessels.txt', 'a')
        count = 0;

        for sel in response.xpath('//div[@class="items"]/article'):
            item = VesselItem()

            imageStr = str(sel.xpath('div[1]/a/picture/img/@src').extract())
            item['image_urls'] = self.page_name + imageStr[3:-2]
            nameStr = str(sel.xpath('div[2]/header/h1/a/text()').extract())
            item['name'] = nameStr[19:-8]
            typeStr = str(sel.xpath('div[2]/div[2]/div[2]/text()').extract())
            item['type'] = typeStr[3:-2]

            return item

当我运行这个蜘蛛时，我收到了exceptions.ValueError: Missing scheme in request url: h错误，因为我没有提供绝对网址。

[vessel] ERROR: Error processing {'image_urls': 'http://vesselfinder.com/vessels/ship-photo/0-224138470-a2fdc783d05a019d00ad9db0cef322f7/0.jpg',
     'name': 'XILGARO ALEANTE',
     'type': 'Sailing vessel'}
    Traceback (most recent call last):
      File "/usr/local/lib/python2.7/dist-packages/scrapy/middleware.py", line 62, in _process_chain
        return process_chain(self.methods[methodname], obj, *args)
      File "/usr/local/lib/python2.7/dist-packages/scrapy/utils/defer.py", line 65, in process_chain
        d.callback(input)
      File "/usr/local/lib/python2.7/dist-packages/twisted/internet/defer.py", line 383, in callback
        self._startRunCallbacks(result)
      File "/usr/local/lib/python2.7/dist-packages/twisted/internet/defer.py", line 491, in _startRunCallbacks
        self._runCallbacks()
    --- <exception caught here> ---
      File "/usr/local/lib/python2.7/dist-packages/twisted/internet/defer.py", line 578, in _runCallbacks
        current.result = callback(current.result, *args, **kw)
      File "/usr/local/lib/python2.7/dist-packages/scrapy/contrib/pipeline/media.py", line 40, in process_item
        requests = arg_to_iter(self.get_media_requests(item, info))
      File "/usr/local/lib/python2.7/dist-packages/scrapy/contrib/pipeline/images.py", line 104, in get_media_requests
        return [Request(x) for x in item.get(self.IMAGES_URLS_FIELD, [])]
      File "/usr/local/lib/python2.7/dist-packages/scrapy/http/request/__init__.py", line 26, in __init__
        self._set_url(url)
      File "/usr/local/lib/python2.7/dist-packages/scrapy/http/request/__init__.py", line 61, in _set_url
        raise ValueError('Missing scheme in request url: %s' % self._url)
    exceptions.ValueError: Missing scheme in request url: h

我该如何解决这个问题。是否有任何特殊的方式来获取像这样的网站的图像（或其绝对网址）。

Answer 1

将图片网址包装在如下列表中：

item['image_urls'] = [self.page_name + imageStr[3:-2]]

Answer 2

我认为以下代码可以解决问题（对代码的更改很少），

<强> vessel_spider.py

class VesselSpider(scrapy.Spider):
    """docstring for VesselSpider"""
    name = "vessel"
    allowed_domains = ["vesselfinder.com"]
    page_name = "http://vesselfinder.com"
    start_urls = [
        # "http://vesselfinder.com/vessels?page=%d" %i for i in range(0,1000)
        "http://vesselfinder.com/vessels"
    ]

    def parse(self, response):
        f = open('vessels.txt', 'a')
        count = 0;
        for sel in response.xpath('//div[@class="items"]/article'):
            item = VesselItem()
            imageStr = sel.xpath('./div[@class="small-12 medium-5 large-5 columns"]/a/picture/img/@src').extract()
            imageStr = imageStr[0] if imageStr else 'N/A'
            item['image_urls'] = [self.page_name + imageStr]
            nameStr = sel.xpath('./div/header/h1[@class="subheader"]/a/text()').extract()
            nameStr = ' '.join(' '.join(nameStr).split()) if nameStr else 'N/A'
            item['name'] = nameStr
            typeStr = sel.xpath('.//div[@class="small-4 columns" and contains(text(), "Ship type")]/following-sibling::div/text()').extract()
            typeStr = typeStr[0].strip() if typeStr else 'N/A'
            item['ship_type'] = typeStr
            yield item

<强> items.py

class VesselItem(scrapy.Item):
    name = scrapy.Field()
    nationality = scrapy.Field()
    image_urls = scrapy.Field()
    images = scrapy.Field()
    ship_type = scrapy.Field()

附加示例输出

{'image_urls': u'http://vesselfinder.com/vessels/ship-photo/0-227349190-7c01e2b3a7a5078ea94fff9a0f862f8a/0',
 'name': u'IBTISAM ATAO',
 'ship_type': u'Sailing vessel'}

无法使用相对URL Python Scrapy下载图像

2 个答案: