scrapy项目3

# -*- coding: utf-8 -*-
import scrapy

#导入items
from tencent.items import TencentItem

class HrSpider(scrapy.Spider):
    name = 'hr'
    allowed_domains = ['tencent.com']
    start_urls = ['https://hr.tencent.com/position.php']

    def parse(self, response):
        print("=========")
        tr_list = response.xpath("//table[@class='tablelist']/tr")[1:-1] #去掉第一个和最后一个

        for tr in tr_list:
            # 使用item，items里面的字段要和这下面的字段一样
            item = TencentItem()
            # item = {}  #不使用items

            item["title"] = tr.xpath("./td[1]/a/text()").extract_first()
            item["position"] = tr.xpath("./td[4]/text()").extract_first()
            item["publish_date"] = tr.xpath("./td[5]/text()").extract_first()
            yield item

            # <a href="javascript:;"class="noactive" id="next">下一页</a>
            #判断下一页，最后一页的href="javascript
        next_url = response.xpath("//a[@id='next']/@href").extract_first()
        if next_url != "javascript": #如果href的属性不为javascript，代表有下一页
            next_url = 'https://hr.tencent.com/'+next_url
            yield scrapy.Request(
                next_url,
                callback=self.parse
            )

pipelines.py

# mogodb数据库
# from pymongo import MogoClient
# client = MogoClient()
# collection = client["tencent"]["hr"]
#导入items
from tencent.items import TencentItem
class TencentPipeline(object):
    def process_item(self, item, spider):
        # print(spider.name)
        if isinstance(item,TencentItem):


            print(item)
        # collection.insert(dict(item))
        return item

items,py

import scrapy

# 可以定义多个item对应不同的爬虫项目字段，比如怕京东，抽屉，汽车之家
#然后再pipelines中做判断
class TencentItem(scrapy.Item): #scrapy.Item也是一个字典
    # define the fields for your item here like:
    # name = scrapy.Field()
    num = scrapy.Field()
    title = scrapy.Field()   #scrapy.Field()是一个字典
    position = scrapy.Field()
    publish_date = scrapy.Field()


class ChoutiItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    title = scrapy.Field()
    position = scrapy.Field()
    publish_date = scrapy.Field()


class JdItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    title = scrapy.Field()
    position = scrapy.Field()
    publish_date = scrapy.Field()

settings.py

LOG_LEVEL = "WARNING"


# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.87 Safari/537.36'

项目地址：https://github.com/CH-chen/tencent

猜你喜欢