scrapy item loader机制

from scrapy.loader import ItemLoader   #继在jobbole中导入模块

item_loader=ItemLoader(item=JobBoleArticleItem(),response=response)  #JobBoleArticleItem需要与items.py中的类名一致

item_loader.add_css("title",".entry-header h1::text")
item_loader.add_css("create_date","p.entry-meta-hide-on-mobile::text")
item_loader.add_value("url","response.url")
item_loader.add_value("front_image_url","front_image_url")
item_loader.add_value("front_image_path","get_md5(response.url)")
item_loader.add_xpath("praise_nums","//span[contains(@class,‘vote-post-up‘)]/h10/text()")
item_loader.add_xpath("comment_nums","//a[@href=‘#article-comment‘]/span/text()")
item_loader.add_xpath("fav_nums","//span[contains(@class,‘bookmark-btn‘)]/text()")
item_loader.add_css("tags","p.entry-meta-hide-on-mobile a::text")
item_loader.add_xpath("content","div.entry")
article_item=item_loader.load_item()  #引用

其中由于里面用了css和path两种获取方法，可以任意切换。

from scrapy.loader.processors import MapCompose,TakeFirst,Join#在items.py中导入模块，其中类MapCompos可以传递任意多的函数

def add_jobbole(value):
    return value+"-jobbole"

def date_convert(value):
    try:
        create_date = datetime.datetime.strptime(‘create_date‘, "%Y/%m/%d").date()
    except Exception as e:
        create_date = datetime.datetime.now()
    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 remove_comment_tags(value):
    # 去掉tag中提取的评论
    if "评论" in value:
        return ""
    else:
        return value

def return_value(value):
    return value         #不变

class JobBoleArticleItem(scrapy.Item):

    title=scrapy.Field(
        #input_processor=MapCompose(add_jobbole)#进行预处理
        input_processor= MapCompose(lambda x:x+"-jobbole",add_jobbole)
    )
    create_date=scrapy.Field(
        input_processor= MapCompose(date_convert),
        output_processor=TakeFirst() #取第一个

     )
    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(
        intput_processor=MapCompose(remove_comment_tags),
        output_processor=Join(",")