elpais_spider.py 文件源码

def get_article_info(url):
    """
    Returns a dictionary with the article info.
    The dictionary contains the following fields:
    - date
    - title
    - tags (list of tags at the end of the article)
    - url
    """
    content = urllib2.urlopen(url)
    tree = html.parse(content)
    content.close()
    title = tree.xpath('//h1[@id="articulo-titulo"]/text()')[0]
    date = tree.xpath('//time//a/text()')[0].strip()
    tags = tree.xpath('//li[@itemprop="keywords"]/a/text()')
    url = url

    result = {'date': date, 'title': title, 'tags': tags, 'url': url}
    return(result)