scrapy pipline

pipline

import json
import os
import requests


class JsonPipeline(object):
    def __init__(self):
        self.file = open('xiaohua.txt', 'w')

    def process_item(self, item, spider):
        v = json.dumps(dict(item), ensure_ascii=False)
        self.file.write(v)
        self.file.write('\n')
        self.file.flush()
        return item


class FilePipeline(object):
    def __init__(self):
        if not os.path.exists('imgs'):
            os.makedirs('imgs')

    def process_item(self, item, spider):
        response = requests.get(item['url'], stream=True)
        file_name = '%s_%s.jpg' % (item['name'], item['school'])
        with open(os.path.join('imgs', file_name), mode='wb') as f:
            f.write(response.content)
        return item

ITEM_PIPELINES = {
   'spider1.pipelines.JsonPipeline': 100,
   'spider1.pipelines.FilePipeline': 300,
}
# 每行后面的整型值，确定了他们运行的顺序，item按数字从低到高的顺序，通过pipeline，通常将这些数字定义在0-1000范围内。

from scrapy.exceptions import DropItem

class CustomPipeline(object):
    def __init__(self,v):
        self.value = v

    def process_item(self, item, spider):
        # 操作并进行持久化

        # return表示会被后续的pipeline继续处理
        return item

        # 表示将item丢弃，不会被后续pipeline处理
        # raise DropItem()


    @classmethod
    def from_crawler(cls, crawler):
        """
        初始化时候，用于创建pipeline对象
        :param crawler: 
        :return: 
        """
        val = crawler.settings.getint('MMMM')
        return cls(val)

    def open_spider(self,spider):
        """
        爬虫开始执行时，调用
        :param spider: 
        :return: 
        """
        print('000000')

    def close_spider(self,spider):
        """
        爬虫关闭时，被调用
        :param spider: 
        :return: 
        """
        print('111111')