爬蟲框架Scrapy實戰之批量抓取招募訊息

from scrapy.item import Item, Field
class TencentItem(Item):
    name = Field()                # 职位名称
    catalog = Field()             # 职位类别
    workLocation = Field()        # 工作地点
    recruitNumber = Field()       # 招聘人数
    detailLink = Field()          # 职位详情页链接
    publishTime = Field()         # 发布时间

import re
import json
from scrapy.selector import Selector
try:
    from scrapy.spider import Spider
except:
    from scrapy.spider import BaseSpider as Spider
from scrapy.utils.response import get_base_url
from scrapy.utils.url import urljoin_rfc
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor as sle
from itzhaopin.items import *
from itzhaopin.misc.log import *
class TencentSpider(CrawlSpider):
    name = "tencent"
    allowed_domains = ["tencent.com"]
    start_urls = [
        "http://hr.tencent.com/position.php"
    ]
    rules = [ # 定义爬取URL的规则
        Rule(sle(allow=("/position.php\?&start=\d{,4}#a")), follow=True, callback='parse_item')
    ]
    def parse_item(self, response): # 提取数据到Items里面，主要用到XPath和CSS选择器提取网页数据
        items = []
        sel = Selector(response)
        base_url = get_base_url(response)
        sites_even = sel.css('table.tablelist tr.even')
        for site in sites_even:
            item = TencentItem()
            item['name'] = site.css('.l.square a').xpath('text()').extract()
            relative_url = site.css('.l.square a').xpath('@href').extract()[0]
            item['detailLink'] = urljoin_rfc(base_url, relative_url)
            item['catalog'] = site.css('tr > td:nth-child(2)::text').extract()
            item['workLocation'] = site.css('tr > td:nth-child(4)::text').extract()
            item['recruitNumber'] = site.css('tr > td:nth-child(3)::text').extract()
            item['publishTime'] = site.css('tr > td:nth-child(5)::text').extract()
            items.append(item)
            #print repr(item).decode("unicode-escape") + '\n'
        sites_odd = sel.css('table.tablelist tr.odd')
        for site in sites_odd:
            item = TencentItem()
            item['name'] = site.css('.l.square a').xpath('text()').extract()
            relative_url = site.css('.l.square a').xpath('@href').extract()[0]
            item['detailLink'] = urljoin_rfc(base_url, relative_url)
            item['catalog'] = site.css('tr > td:nth-child(2)::text').extract()
            item['workLocation'] = site.css('tr > td:nth-child(4)::text').extract()
            item['recruitNumber'] = site.css('tr > td:nth-child(3)::text').extract()
            item['publishTime'] = site.css('tr > td:nth-child(5)::text').extract()
            items.append(item)
            #print repr(item).decode("unicode-escape") + '\n'
        info('parsed ' + str(response))
        return items
    def _process_request(self, request):
        info('process ' + str(request))
        return request

from scrapy import signals
import json
import codecs
class JsonWithEncodingTencentPipeline(object):
    def __init__(self):
        self.file = codecs.open('tencent.json', 'w', encoding='utf-8')
    def process_item(self, item, spider):
        line = json.dumps(dict(item), ensure_ascii=False) + "\n"
        self.file.write(line)
        return item
    def spider_closed(self, spider):
        self.file.close(
)

scrapy crawl tencent