[scrapy] scrapy 使用goose作为正文提取

import scrapy
from goose import Goose

class Article(scrapy.Item):
    title = scrapy.Field()
    text = scrapy.Field()

class MyGooseSpider(scrapy.Spider):
    name = ‘goose‘
    start_urls = [
        ‘http://blog.scrapinghub.com/2014/06/18/extracting-schema-org-microdata-using-scrapy-selectors-and-xpath/‘,
        ‘http://blog.scrapinghub.com/2014/07/17/xpath-tips-from-the-web-scraping-trenches/‘,
    ]

    def parse(self, response):
        article = Goose().extract(raw_html=response.body)
        yield Article(title=article.title, text=article.cleaned_text)