利用Crawlspider爬取腾讯招聘数据(全站，深度)

需求：

使用crawlSpider（全站）进行数据爬取

- 首页: 岗位名称，岗位类别

- 详情页：岗位职责

- 持久化存储

代码：

爬虫文件：

from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from ..items import CrawlproItem,TenproItem_detail


class CrawSpider(CrawlSpider):
    name = 'craw'
    # allowed_domains = ['www.xxx.com']
    start_urls = ['https://hr.tencent.com/position.php?&start=0#a']
    # 首页所有页码的连接提取器
    link1 = LinkExtractor(allow=r'&start=\d+#a')
    # 详情页连接提取器
    link2 = LinkExtractor(allow=r'position_detail.php\?id=\d+&keywords=&tid=0&lid=0$')  # 问号转义

    rules = (
        Rule(link1, callback='parse_item', follow=True),
        Rule(link2, callback='parse_detail', follow=True),
    )

    def parse_item(self, response):
        # 岗位名称和类别
        print('item',response)
        tr_list = response.xpath('//table[@class="tablelist"]/tr[@class="odd"] | //table[@class="tablelist"]/tr[@class="even"]')
        for tr in tr_list:
            job_name = tr.xpath('./td[1]/a/text()').extract_first()
            job_class = tr.xpath('./td[2]/text()').extract_first()
            # 实例化item类
            item = CrawlproItem()
            item['job_name'] = job_name
            item['job_class'] = job_class

            yield item

    def parse_detail(self, response):
        # 岗位职责
        desc = response.xpath('//ul[@class="squareli"]/li/text()').extract()
        desc = ''.join(desc)
        item = TenproItem_detail()
        item['desc'] = desc
        yield item

items.py文件:

import scrapy


class CrawlproItem(scrapy.Item):
    job_name = scrapy.Field()
    job_class = scrapy.Field()


class TenproItem_detail(scrapy.Item):
    desc = scrapy.Field()

管道文件pipelines.py:

class CrawlproPipeline(object):
    fp = None

    def open_spider(self, spider):
        # 文件只打开一次
        self.fp = open('./tenxun.txt', 'w',encoding='utf-8')

    def process_item(self, item, spider):
        desc = None
        # 取出item中的值

        if item.__class__.__name__ == 'CrawlproItem':
            job_name = item["job_name"]
            job_class = item["job_class"]
            self.fp.write(f'{job_name}\n{job_class}\n\n')
        else:
            desc = item['desc']
            self.fp.write(desc)
        return item  # 返回给下一个即将被执行的管道类

    def close_spider(self, spider):
        self.fp.close()

配置文件中注意开启管道

 

转载于:https://www.cnblogs.com/zwq-/p/10602093.html