scrapy 的使用 ItemLoader

我们下载item 文件写

导入这个文件
from scrapy.loader import ItemLoader

自定义的Loader
class ArticleItemLoader(ItemLoader):
    #自定义itemloader
    default_output_processor = TakeFirst()

自定义item类

class JobBoleArticleItem(scrapy.Item):
    title = scrapy.Field()
    create_date = scrapy.Field(
        #  自定义日期转换
        input_processor=MapCompose(date_convert),
    )
    url = scrapy.Field()
    url_object_id = scrapy.Field()
    front_image_url = scrapy.Field(
        output_processor=MapCompose(return_value)
    )
    front_image_path = scrapy.Field()
    praise_nums = scrapy.Field(
        input_processor=MapCompose(get_nums)
    )
    comment_nums = scrapy.Field(
        input_processor=MapCompose(get_nums)
    )
    fav_nums = scrapy.Field(
        input_processor=MapCompose(get_nums)
    )
    tags = scrapy.Field(
        input_processor=MapCompose(remove_comment_tags),
        output_processor=Join(",")
    )
    content = scrapy.Field()

    def get_insert_sql(self):
        insert_sql = """
            insert into jobbole_article(title, url, create_date, fav_nums, front_image_url, front_image_path,
            praise_nums, comment_nums, tags, content)
            VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s) ON DUPLICATE KEY UPDATE content=VALUES(fav_nums)
        """

        fron_image_url = ""
        # content = remove_tags(self["content"])

        if self["front_image_url"]:
            fron_image_url = self["front_image_url"][0]
        params = (self["title"], self["url"], self["create_date"], self["fav_nums"],
                  fron_image_url, self["front_image_path"], self["praise_nums"], self["comment_nums"],
                  self["tags"], self["content"])
        return insert_sql, params

input_processor 和 output_processor 转换方法要是处理方法

def date_convert(value):
    try:
        create_date = datetime.datetime.strptime(value, "%Y/%m/%d").date()
    except Exception as e:
        create_date = datetime.datetime.now().date()

    return create_date


def get_nums(value):
    match_re = re.match(".*?(\d+).*", value)
    if match_re:
        nums = int(match_re.group(1))
    else:
        nums = 0

    return nums

def return_value(value):
    return value


def remove_comment_tags(value):
    #去掉tag中提取的评论
    if "评论" in value:
        return ""
    else:
        return value

我们在解析文件使用自定义ArticleItemLoader

  def parse_detail(self, response):
        article_item = JobBoleArticleItem()
        #通过item loader加载item
        front_image_url = response.meta.get("front_image_url", "")  # 文章封面图
        item_loader = ArticleItemLoader(item=JobBoleArticleItem(), response=response)
        item_loader.add_css("title", ".entry-header h1::text")
        item_loader.add_value("url", response.url)
        item_loader.add_value("url_object_id", get_md5(response.url))
        item_loader.add_css("create_date", "p.entry-meta-hide-on-mobile::text")
        item_loader.add_value("front_image_url", [front_image_url])
        item_loader.add_css("praise_nums", ".vote-post-up h10::text")
        item_loader.add_css("comment_nums", "a[href='#article-comment'] span::text")
        item_loader.add_css("fav_nums", ".bookmark-btn::text")
        item_loader.add_css("tags", "p.entry-meta-hide-on-mobile a::text")
        item_loader.add_css("content", "div.entry")

        article_item = item_loader.load_item()
        yield article_item