scrapy框架实战之爬取阳光热线案例

1、创建一个scrapy项目

scrapy startproject sunPro
cd sunPro
scrapy genspider  -t crawl sun www.xxxx.com

2、配置文件（settings.py）修改

# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = "'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.71 Safari/537.36 Core/1.94.197.400 QQBrowser/11.6.5265.400'"
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
LOG_LEVEL = 'ERROR'
# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   "essays.pipelines.EssaysPipeline": 300,
}

3、代码部分

3.1 items.py如下，

import scrapy


class SunproItem(scrapy.Item):
    # define the fields for your item here like:
    title = scrapy.Field()
    new_num = scrapy.Field()
    new_state = scrapy.Field()
    new_datetime = scrapy.Field()


class DetailItem(scrapy.Item):
    content = scrapy.Field()

3.2 sun.py如下，

# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from sunPro.items import SunproItem,DetailItem

#需求：爬取sun网站中的编号，新闻标题，新闻内容，标号
class SunSpider(CrawlSpider):
    name = 'sun'
    # allowed_domains = ['www.xxx.com']
    start_urls = ['https://wz.sun0769.com/political/index/politicsNewest?id=1&page=1']

    #链接提取器：根据指定规则（allow="正则"）进行指定链接的提取
    link = LinkExtractor(allow=r'id=1&page=\d+')
    link_detail = LinkExtractor(allow=r'id=\d+')
    rules = (
        #规则解析器：将链接提取器提取到的链接进行指定规则（callback）的解析操作
        Rule(link, callback='parse_item', follow=True),
        #follow=True：可以将链接提取器 继续作用到 连接提取器提取到的链接 所对应的页面中
        Rule(link_detail,callback='parse_detail')
    )
    #http://wz.sun0769.com/html/question/201907/421001.shtml
    #http://wz.sun0769.com/html/question/201907/420987.shtml

    #解析新闻编号和新闻的标题，以及状态和时间
    #如下两个解析方法中是不可以实现请求传参！
    #如法将两个解析方法解析的数据存储到同一个item中，可以以此存储到两个item
    def parse_item(self, response):
        #注意：xpath表达式中不可以出现tbody标签
        tr_list = response.xpath('/html/body/div[2]/div[3]/ul[2]/li')
        for tr in tr_list:
            new_num = tr.xpath('./span[1]/text()').extract_first()
            new_state = tr.xpath('./span[2]/text()').extract_first()
            new_title = tr.xpath('./span[3]/a/text()').extract_first()
            new_datetime = tr.xpath('./span[5]/text()').extract_first()
            item = SunproItem()
            item['title'] = new_title
            item['new_num'] = new_num
            item['new_state'] = new_state
            item['new_datetime'] = new_datetime

            yield item

    #解析新闻内容
    def parse_detail(self,response):
        new_content = response.xpath('/html/body/div[3]/div[2]/div[2]/div[2]/pre/text()').extract()
        new_content = ''.join(new_content)

        # print(new_id,new_content)
        item = DetailItem()
        item['content'] = new_content


        yield item

3.3 pipelines.py如下，

class SunproPipeline(object):
    fp = None

    def open_spider(self, spider):
        self.fp = open('./news.txt', 'w+', encoding='utf-8')
        print('正在爬取文件...')

    def process_item(self, item, spider):
        # 如何判定item的类型
        # 将数据写入数据库时，如何保证数据的一致性
        if item.__class__.__name__ == 'DetailItem':
            self.fp.write('内容:', item['content'])
        else:
            self.fp.write('编号:', item['new_num'], '标题:',item['title'], '状态:',item['new_state'], '受理时间:',item['new_datetime'])
            print(item['new_num'], item['title'], item['new_state'], item['new_datetime'])
        return item

    def close_spider(self, spider):
        self.fp.close()
        print('新闻爬取完毕...')