import scrapy

import papernews_spider
from papernews_spider.myfirstPj.spiders import Tools


# 正文爬虫（测试用）
# import PapernewsSpider


class NewscontentSpider(scrapy.Spider):
    name = 'NewsContent'
    allowed_domains = ['www.paper.com.cn']
    urllist = open('url.txt', 'a', encoding='utf-8')
    start_urls = ['http://www.paper.com.cn/']

    def parse(self, response):
        # 资讯详情页
        lists = response.xpath('//b/text() | //p/text()').extract()
        # lists = response.xpath("//a[contains(@target, '_blank')]/text()").extract()
        # 打开保存的url链接
        urllist = open("url.txt", 'a', encoding='utf-8')

        # 编辑输出编码格式，输出文件名，信息为追加写入
        Tools.write_txt(Tools.__init__(self), "News.txt", urllist)