def __init__(self):
"""
将item中的值初始化为空
"""
Item.__init__(self)
self['coal'] = ''
self['non_coal'] = ''
def __init__(self):
Item.__init__(self)
#爬取下来的一个全局唯一ID
self['crawlerid'] = ''
#页面链接
self['url'] = ''
#html源码
self['html_code'] = ''
#页面编码
self['encoding'] = ''
#标题
self['title'] = ''
#作者
self['authors'] = []
#正文
self['content'] = ''
#新闻时间
self['time'] = ''
#来源
self['source'] = ''
#编辑
self['editor'] = ''
#频道类别
self['ctype'] = ''
#频道类别
self['subtype'] = ''
#关键词
self['keywords'] = []
#摘要
self['abstract'] = ''
self['copyright'] = ''
self['originality'] = ''
self['type'] = 'text'
def __init__(self):
"""
将item中的值初始化为空
"""
Item.__init__(self)
self['coal'] = ''
self['non_coal'] = ''
def __init__(self, *args, **kwargs):
Item.__init__(self, *args, **kwargs)
self['platform'] = kwargs.get("keyword")
self['keyword'] = kwargs.get("keyword")
self['crawl_time'] = int(time.time())
self['url'] = kwargs.get("url")
self['real_url'] = kwargs.get("real_url")
self['title'] = kwargs.get("title")
self['source_url'] = kwargs.get("title")
self['spider'] = kwargs.get("spider")
self['skip_url'] = kwargs.get("skip_url")
self['snapshot_url'] = kwargs.get("snapshot_url")
self['show_url'] = kwargs.get("show_url")
self['is_ad'] = kwargs.get("is_ad")
self['content'] = kwargs.get("content")
def __init__(self, year):
global this_year
this_year = year
Item.__init__(self)
