Python爬虫：Scrapy链接解析器LinkExtractor返回Link对象

from scrapy.linkextractors import LinkExtractor

from scrapy.link import Link

url text fragment nofollow

link_extractor = LinkExtractor(attrs=('href','text'))
links = link_extractor.extract_links(response)

import scrapy
from scrapy.linkextractors import LinkExtractor
class DemoSpider(scrapy.Spider):
    name = 'spider'
    start_urls = [
        "https://book.douban.com/"
    ]
    def parse(self, response):
        # 参数是正则表达式
        link_extractor = LinkExtractor(allow="https://www.tianyancha.com/brand/b.*")
        links = link_extractor.extract_links(response)
        for link in links:
            print(link.text, link.url)
if __name__ == '__main__':
    cmdline.execute("scrapy crawl spider".split())