CrawlSpiders

1.用 scrapy 新建一个 tencent 项目

2.在 items.py 中确定要爬去的内容

# -*- coding: utf-8 -*-

# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/items.html

import scrapy


class TencentItem(scrapy.Item):
    # define the fields for your item here like:
    # 职位
    position_name = scrapy.Field()
    # 详情链接
    positin_link = scrapy.Field()
    # 职业类别 
    position_type = scrapy.Field()
    # 招聘人数
    people_number = scrapy.Field()
    # 工作地点
    work_location = scrapy.Field()
    # 发布时间
    publish_time = scrapy.Field()

 

3.快速创建 CrawlSpider模板

scrapy genspider -t crawl tencent_spider tencent.com

注意  此时中的名称不能与项目名相同

4.打开tencent_spider.py 编写代码

# -*- coding: utf-8 -*-
import scrapy
# 导入链接规则匹配类，用来提取符合规则的链接
from scrapy.linkextractors import LinkExtractor
# 导入CrawlSpider类和Rule
from scrapy.spiders import CrawlSpider, Rule
# 从tentcent项目下的itmes.py中导入TencentItem类
from tencent.items import TencentItem


class TencentSpiderSpider(CrawlSpider):
    name = 'tencent_spider'
    allowed_domains = ['hr.tencent.com']
    start_urls = ['http://hr.tencent.com/position.php?&start=0#a']
    pagelink = LinkExtractor(allow=("start=\d+")) # 正则匹配

    rules = (
        # 获取这个列表的链接，依次发送请求，并继续跟进，调用指定的回调函数
        Rule(pagelink, callback='parse_item', follow=True),
    )

    def parse_item(self, response):
        for each in response.xpath("//tr[@class='even'] | //tr[@class='odd']"):
            item = TencentItem()
            # 职位名称
            item['position_name'] = each.xpath("./td[1]/a/text()").extract()[0]
            # 详情连接
            item['position_link'] = each.xpath("./td[1]/a/@href").extract()[0]
            # 职位类别
            #item['position_type'] = each.xpath("./td[2]/text()").extract()[0]
            # 招聘人数
            item['people_number'] = each.xpath("./td[3]/text()").extract()[0]
            # 工作地点
            # item['work_location'] = each.xpath("./td[4]/text()").extract()[0]
            # 发布时间
            item['publish_time'] = each.xpath("./td[5]/text()").extract()[0]

            yield item

5.在 piplines.py 中写入文件

 1 # -*- coding: utf-8 -*-
 2 
 3 # Define your item pipelines here
 4 #
 5 # Don't forget to add your pipeline to the ITEM_PIPELINES setting
 6 # See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
 7 
 8 import json
 9 
10 class TencentPipeline(object):
11     def open_spider(self, spider):
12         self.filename = open("tencent.json", "w")
13 
14     def process_item(self, item, spider):
15         text = json.dumps(dict(item), ensure_ascii = False) + "\n"
16         self.filename.write(text.encode("utf-8")
17         return item
18 
19     def close_spider(self, spider):
20         self.filename.close()

7.在命令输入以下命令运行

scrapy crawl tencen_spider.py

 

出现以下问题在tencent_spider.py 文件中只有把position_type 和 work_location 注销掉才能运行...