scrapy框架--？乱码unicode

pip install scrapy

scrapy startproject itcast

scrapy genspider itcast "itcast.cn"

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


class ItcastSpider(scrapy.Spider):
    name = "itcast"
    allowed_domains = ["itcast.cn"]
    start_urls = (
        ‘http://www.itcast.cn/channel/teacher.shtml‘,
    )

    def parse(self, response):
        # print(response)
        data_list = response.xpath("//div[@class=‘tea_con‘]//h3/text()").extract()  # extract() 返回一个含有字符串数据的列表 如果没用这个方法 返回一个包含选择器的列表
        print(data_list)  # 乱码 u\u5218.... setting.py中添加了 FEED_EXPORT_ENCODING = ‘utf-8‘ 还是不行 不知道原因  ？？？
        for i in data_list:
            print(i)  # 此处打印的是中文 

apt-get install language-pack-zh

sudo gedit /etc/environment

PATH="/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games"
LANG="zh_CN.UTF-8"
LANGUAGE="zh_CN:zh:en_US:en"

sudo gedit /var/lib/locales/supported.d/local

zh_CN.UTF-8 UTF-8
en_US.UTF-8 UTF-8

sudo locale-gen

sudo reboot

LOG_LEVEL = "WARNING"

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


class ItcastSpider(scrapy.Spider):
    name = "itcast"
    allowed_domains = ["itcast.cn"]
    start_urls = (
        ‘http://www.itcast.cn/channel/teacher.shtml‘,
    )

    def parse(self, response):
        # # print(response)
        # data_list = response.xpath("//div[@class=‘tea_con‘]//h3/text()").extract()  # extract() 返回一个含有字符串数据的列表 如果没用这个方法 返回一个包含选择器的列表
        # print(data_list)  # 乱码 u\u5218.... setting.py中添加了 FEED_EXPORT_ENCODING = ‘utf-8‘ 还是不行 不知道原因  ？？？
        # for i in data_list:
        #     print(i)  # 此处打印的是中文
        ret = response.xpath("//div[@class=‘tea_con‘]//li")  # xpath分组提取
        # print(ret)
        for i in ret:
            item = {}
            item[‘name‘] = i.xpath(".//h3/text()").extract_first()  # extract_first()相当于 extract()[0] 取列表的第一条数据 
            # extrack_first() 如果没有数据则返回空列表
            # extrack()[0] 如果没有数据会报错
            item[‘position‘] = i.xpath(".//h4/text()").extract_first()
            item[‘commondcommond‘] = i.xpath(".//p/text()").extract_first()
            yield item  # 把数据传给pipline

# -*- coding:utf-8 -*-

# 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
import json
import codecs

class MyspiderPipeline(object):
    # def __init__(self):
    #     # 定义文件编码及名称
    #     self.file = codecs.open(‘中文乱码.json‘, ‘wb‘, encoding=‘utf-8‘)

    def process_item(self, item, spider):  # 实现存储方法
        # line = json.dumps(dict(item)) + ‘\n‘
        # print(line.decode("unicode_escape"))
        # 写入一行，每行为一个抓取项
        # self.file.write(line.decode("unicode_escape"))
        # return item
        print(item)