scrapy pipline

pipline

 

scrapy pipline
 1 import json
 2 import os
 3 import requests
 4 
 5 
 6 class JsonPipeline(object):
 7     def __init__(self):
 8         self.file = open('xiaohua.txt', 'w')
 9 
10     def process_item(self, item, spider):
11         v = json.dumps(dict(item), ensure_ascii=False)
12         self.file.write(v)
13         self.file.write('\n')
14         self.file.flush()
15         return item
16 
17 
18 class FilePipeline(object):
19     def __init__(self):
20         if not os.path.exists('imgs'):
21             os.makedirs('imgs')
22 
23     def process_item(self, item, spider):
24         response = requests.get(item['url'], stream=True)
25         file_name = '%s_%s.jpg' % (item['name'], item['school'])
26         with open(os.path.join('imgs', file_name), mode='wb') as f:
27             f.write(response.content)
28         return item
pipline scrapy pipline
1 ITEM_PIPELINES = {
2    'spider1.pipelines.JsonPipeline': 100,
3    'spider1.pipelines.FilePipeline': 300,
4 }
5 # 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。
setting scrapy pipline
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')
自定义pipline

 

上一篇:Linux(1/20)


下一篇:pipline中替换tag变量