国家统计局爬虫样例

 

items.py 

import scrapy

class NewsItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    title = scrapy.Field() # 标题
    summary = scrapy.Field() # 主旨
    origin = scrapy.Field()  # 文章原文链接
    cover = scrapy.Field()  # 文章封面图片
    author = scrapy.Field()  # 文章作者
    publish_date = scrapy.Field() # 发布日期
    publish_time = scrapy.Field()  # 发布日期含时间
    publish_from = scrapy.Field() # 文章来源
    category = scrapy.Field() # 文章所属分类 report,
    type = scrapy.Field() # 类型，图片（img）或者文字（txt）
    html = scrapy.Field() # html内容
    text = scrapy.Field() # 文本内容
    image_urls = scrapy.Field() # 正文图片Url地址
    images = scrapy.Field() # 正文图片本地地址