scrapy中文存储

修改setteings文件

ITEM_PIPELINES = {
      'mypjt.pipelines.MypjtPipeline': 300,
 6 }

编写pipelines文件

# -*- coding: utf-8 -*-
import codecs

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html


class MypjtPipeline(object):
    def __init__(self):
        self.file = codecs.open("mydata1.txt","wb",encoding = "utf-8")

    def process_item(self, item, spider):
        #i=json.dumps(dict(item),ensure_ascii=False)当存储json格式时

        l = str(item)+'\n'
        print(l)
        self.file.write(l)
        return item
    def close_spider(self,spider):
        self.file.close()

spider代码

# -*- coding: utf-8 -*-
import scrapy
from mypjt.items import MypjtItem

class MyspdSpider(scrapy.Spider):
    name = 'myspd'
    allowed_domains = ['sina.com.cn']
    start_urls = ['http://tech.sina.com.cn/d/s/2016-09-17/doc-ifxvyqwa3324638.shtml']

    def parse(self, response):
        item = MypjtItem()  
        item["title"] = response.xpath("/html/head/title/text()") #当存储json格式时后面加extract()即可
        print (item["title"])
        yield item                #对item进行迭代,否则文件中将为空