初始化

import scrapy

class DmozSpider(scrapy.Spider):
    name = "dmoz"
    allowed_domains = ["dmoz.org"]
    start_urls = [
        "http://www.dmoz.org/Computers/Programming/Languages/Python/Books/",
        "http://www.dmoz.org/Computers/Programming/Languages/Python/Resources/"
    ]

    # 解析返回的数据(response data)，提取数据(生成item)以及生成需要进一步处理的URL的Request对象。
    def parse(self, response):
        filename = response.url.split("/")[-2]
        with open(filename, 'wb') as f:
            f.write(response.body)

运行

scrapy crawl spider

selector

# 获取标签中的文字
>>> body = '<html><body><span>good</span></body></html>'
>>> Selector(text=body).xpath('//span/text()').extract()
[u'good']

# 根据class名获取li标签内容，并存储为一个list
results = response.xpath("//li[contains(@class, 'actors__container')]/").extract()

# 获取href标签
>>> response.xpath('//base/@href').extract()
[u'http://example.com/']

# 根据属性获取链接
urls = response.xpath("//a[@rel = 'bookmark']/@href").extract()

# 获取多个标签内容
content_text = response.xpath("//div[@class = 'single__content']/p|//div[@class = 'single__content']/h2/text()").getall()