当前位置: 移动技术网 > IT编程>脚本编程>Python > Scrapy框架-Spider和CrawlSpider的区别

Scrapy框架-Spider和CrawlSpider的区别

2019年02月16日  | 移动技术网IT编程  | 我要评论

北京教父在线阅读,临汾一中校园网,溧阳论坛

1.目标

爬取每个页面链接的内部内容和投诉信息

2.方法1:通过spider爬取

# -*- coding: utf-8 -*-
import scrapy
from dongguanspider.items import dongguanitem

class sunspider(scrapy.spider):
    name = 'sun'
    allowed_domains = ['wz.sun0769.com']
    url = 'http://wz.sun0769.com/index.php/question/questiontype?type=4&page='
    offset = 0

    start_urls = [url + str(offset)]


    def parse(self, response):
        # 每一页的所有帖子的链接集合
        links = response.xpath('//div[@class="greyframe"]/table//td/a[@class="news14"]/@href').extract()
        # 迭代取出集合里的链接
        for link in links:
            # 提取列表里每个帖子的链接,发送请求并调用parse——item来处理
            yield scrapy.request(link, callback=self.parse_item)

        # 页面终止条件成立前,会一直自增offset的值,并发送新的页面请求,调用parse方法处理
        if self.offset<=71160:
            self.offset +=30

            yield scrapy.request(self.url + str(self.offset), callback=self.parse)


    def parse_item(self, response):

        item = dongguanitem()

        item['title'] = response.xpath('//div[@class="wzy1"]/table[1]//tr/td[2]/span[1]/text()').extract()[0].split(':')[-1]
        item['url'] = response.url
        item['number'] = response.xpath('//div[@class="wzy1"]/table[1]//tr/td[2]/span[2]/text()').extract()[0].split(':')[-1]

        # 是否是图片
        content_pic = response.xpath('//div[@class="textpic"]/img/@src').extract()

        if len(content_pic)==0:
            content_no_pic = response.xpath('//div[@class="wzy1"]/table[2]//tr/td/text()').extract()[0]
            item['content'] = "".join(content_no_pic).replace("\xa0", "")
        else:
            item['content'] = "".join(content_pic[0]).replace("\xa0", "")

        yield item

3. 通过crawlspider爬取

# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import linkextractor
from scrapy.spiders import crawlspider, rule
from dongguan.items import dongguanitem


class sunspider(crawlspider):
    name = 'sun'
    allowed_domains = ['wz.sun0769.com']
    start_urls = ['http://wz.sun0769.com/index.php/question/questiontype?type=4&page=30']

    rules = [
        rule(linkextractor(allow=('type=4&page=\d+'))),
        rule(linkextractor(allow = ('/html/question/\d+/\d+.shtml')), callback = 'parsedongguan')
    ]

    def parsedongguan(self, response):

        item = dongguanitem()


        item['title'] = response.xpath('//div[@class="wzy1"]/table[1]//tr/td[2]/span[1]/text()').extract()[0].split(':')[-1]
        item['url'] = response.url
        item['number'] = response.xpath('//div[@class="wzy1"]/table[1]//tr/td[2]/span[2]/text()').extract()[0].split(':')[-1]

        # 是否是图片
        content_pic = response.xpath('//div[@class="textpic"]/img/@src').extract()

        if len(content_pic)==0:
            content_no_pic = response.xpath('//div[@class="wzy1"]/table[2]//tr/td/text()').extract()[0]
            item['content'] = "".join(content_no_pic).replace("\xa0", "")
        else:
            item['content'] = "".join(content_pic[0]).replace("\xa0", "")

        yield item

如对本文有疑问,请在下面进行留言讨论,广大热心网友会与你互动!! 点击进行留言回复

相关文章:

验证码:
移动技术网