Scrapy框架的使用 -- 自动跳转链接并请求

Scrapy框架的使用 -- 自动跳转链接并请求

# -*- coding: utf-8 -*-
import scrapy
from movie.items import MovieItem


class MoviespiderSpider(scrapy.Spider):
    name = 'moviespider'
    # allowed_domains = ['www.movie.com']
    start_urls = ['https://www.4567tv.tv/index.php/vod/show/id/1.html']

    def detail_parse(self, response):
        item = response.meta['item']
        director = response.xpath('/html/body/div[1]/div/div/div/div[2]/p[3]/a/text()').extract()

        item['director'] = director

        yield item

    def parse(self, response):
        li_list = response.xpath('//li[@class="col-md-6 col-sm-4 col-xs-3"]')
        for li in li_list:
            title = li.xpath('./div/a/@title').extract_first()
            actor = li.xpath('./div/div/p/text()').extract_first()
            detail_url = 'https://www.4567tv.tv' + li.xpath('./div/a/@href').extract_first()

            item = MovieItem()

            item['name'] = title
            item['actor'] = actor

            # 第一个解析的函数中不直接yield item, yield scrapy.Request()对象 传入下一个连接的url 

            yield scrapy.Request(url=detail_url, callback=self.detail_parse, meta={'item': item})

View Code

 

posted on 2019-03-04 17:06 徐建0304 阅读( ...) 评论( ...) 编辑 收藏

转载于:https://www.cnblogs.com/Treasuremy/p/10471792.html