简单的网络scrapy爬虫示例代码

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


# scrapy genspider itcast "itcast.cn"
# scrapy startproject mySpider


class ITcastItem(scrapy.Item):
    name = scrapy.Field()
    title = scrapy.Field()
    info = scrapy.Field()


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

    # scrapy crawl itcast
    # scrapy crawl itcast -o teachers.csv
    # scrapy crawl itcast -o teachers.json
    # scrapy crawl itcast -o teachers.jsonl
    # scrapy crawl itcast -o teachers.xml
    def parse(self, response):
        filename = "teacher.html"
        open(filename, 'wb').write(response.body)
        context = response.xpath('/html/head/title/text()')
        title = context.extract_first()
        print(title)
        # 存放老师信息的集合
        items = []