Scrapy框架学习 - 爬取Boss直聘网Python职位信息

分析

使用CrawlSpider结合LinkExtractor和Rule爬取网页信息

LinkExtractor用于定义链接提取规则，一般使用allow参数即可

LinkExtractor(allow=(), # 使用正则定义提取规则
              deny=(), 	# 排除规则
              allow_domains=(), # 限定域名范围
              deny_domains=(),  # 排除域名范围
              restrict_xpaths=(), # 使用xpath定义提取队则
              tags=('a', 'area'), 
              attrs=('href',), 
              canonicalize=False,
              unique=True, 
              process_value=None,
              deny_extensions=None, 
              restrict_css=(),		# 使用css选择器定义提取规则
              strip=True):

Rule用于定义CrawlSpider的爬取规则，由Spider内部自动识别，提交请求、获取响应，交给callback指定的回调方法处理response

如果指定了callback，参数follow默认为False；如果callback为None，follow默认为True

Rule(link_extractor, 	# LinkExtractor对象,必选参数
     callback=None, 	# 回调方法,可选
     cb_kwargs=None, 	
     follow=None, 	# 是否进行深度爬取,True、False
     process_links=None,	# 用于处理链接(有些反爬策略是返回假的url)
     process_request=identity)

源码

items.py

class BosszhipinItem(scrapy.Item):
    """Boss直聘Pytho职位爬虫Item"""

    # 职位名称
    position=scrapy.Field()
    # 公司名称
    company=scrapy.Field()
    # 薪资
    salary=scrapy.Field()
    # 工作地点
    location=scrapy.Field()
    # 学历要求
    education=scrapy.Field()
    # 工作时间
    year=scrapy.Field()

spiders/bosszhipin_spider.py

# !/usr/bin/env python
# -*- coding:utf-8 -*-

import scrapy
from scrapy.spider import CrawlSpider,Rule
from scrapy.linkextractors import LinkExtractor

from myscrapy.items import BosszhipinItem


class BosszhipinSpider(CrawlSpider):
    """
    Boss直聘Python职位爬虫Spider
        使用CrawlSpider基类实现
    """

    name = 'bosszhipin'
    allowed_domains=['zhipin.com',]
    start_urls=['http://www.zhipin.com/c100010000/h_100010000/?query=Python&page=1',]

    # 链接提取器对象(规定链接提取规则)
    link_extractor=LinkExtractor(allow=(r'page=\d+'))

    # 链接提取规则对象列表
    # 自动调用callback指定的方法,去取爬取由link_extractor指定的链接提取规则匹配到的url
    # 原理:link_extractor.extract_links(response)返回匹配到的链接
    rules = [
        Rule(link_extractor=link_extractor,callback='parse_page',follow=True),
    ]

    def parse_page(self,response):
        """定义回调方法,用于解析每个response对象"""

        job_list=response.xpath('//div[@class="job-list"]//li')
        for job in job_list:
            position = job.xpath('.//div[@class="info-primary"]//h3[@class="name"]/a/text()')[0].extract()
            salary =job.xpath('.//div[@class="info-primary"]//h3[@class="name"]//span/text()')[0].extract()
            company =job.xpath('.//div[@class="company-text"]//a/text()')[0].extract()
            location =job.xpath('.//div[@class="info-primary"]/p/text()[1]')[0].extract()
            year =job.xpath('.//div[@class="info-primary"]/p/text()[2]')[0].extract()
            education =job.xpath('.//div[@class="info-primary"]/p/text()[3]')[0].extract()

            item=BosszhipinItem()
            item['position']=position
            item['salary']=salary
            item['company']=company
            item['location']=location
            item['year']=year
            item['education']=education

            yield item

pipelines.py

class BosszhipinPipeline(object):
    """Boss直聘Python职位爬虫Item Pipeline"""

    def __init__(self):
        self.f=open('data/bosszhipin.json',mode='wb')
        self.f.write(b'[')

    def process_item(self,item,spider):
        data=json.dumps(dict(item),ensure_ascii=False,indent=4)
        self.f.write(data.encode('utf-8'))
        self.f.write(b',')

        return item

    def close_spider(self,spider):
        self.f.write(b']')
        self.f.close()

settings.py

ITEM_PIPELINES = {
   'myscrapy.pipelines.BosszhipinPipeline': 1,
}

运行结果