scrapy爬虫实践（部分源代码）

items.py

# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html

import scrapy


class SyItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    name=scrapy.Field()

spider_title.py

import scrapy
from sy.items import SyItem

class SpiderTitleSpider(scrapy.Spider):
    name = "spider_title"
    allowed_domains = ["www.zongheng.com"]
    start_urls = ["https://read.zongheng.com/chapter/1215341/68208370.html"]

    def parse(self, response):
        item = SyItem()
        titles = [each.extract() for each in response.xpath('//*[@id="Jcontent"]/div/div[4]/p/text()')]
        print(titles)
        item['name']=titles
        print(type(titles))
        f=open('aa.txt','w')
        for asd in titles:
            f.write(asd+'\n')
        return item