scrapy框架爬取开源中国项目大厅所有的发布项目。

本文爬取的字段，项目名称，发布时间，项目周期，应用领域，最低报价，最高报价，技术类型

1，items中定义爬取字段。

import scrapy


class KaiyuanzhongguoItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    name = scrapy.Field()
    publishTime = scrapy.Field()
    cycle = scrapy.Field()
    application = scrapy.Field()
    budgetMinByYuan = scrapy.Field()
    budgetMaxByYuan = scrapy.Field()
    ski = scrapy.Field()

2，　爬虫主程序

# -*- coding: utf-8 -*-
import scrapy
import json
from kaiyuanzhongguo.items import KaiyuanzhongguoItem
class KyzgSpider(scrapy.Spider):
    name = 'kyzg'
    # allowed_domains = ['www.xxx.com']
    base_url = 'https://zb.oschina.net/project/contractor-browse-project-and-reward?pageSize=10&currentPage='
    start_urls = ['https://zb.oschina.net/project/contractor-browse-project-and-reward?pageSize=10&currentPage=1']
    def parse(self, response):
        result = json.loads(response.text)
        totalpage = result['data']['totalPage']
        for res in result['data']['data']:
            item = KaiyuanzhongguoItem()
            item['name'] = res['name']
            item['publishTime'] = res['publishTime']
            item['cycle'] = res['cycle']
            item['application'] = res['application']
            item['budgetMinByYuan'] = res['budgetMinByYuan']
            item['budgetMaxByYuan'] = res['budgetMaxByYuan']
            skillList = res['skillList']
            skill = []
            item['ski'] = ''
            if skillList:
                for sk in skillList:
                    skill.append(sk['value'])
                    item['ski'] = ','.join(skill)
            yield item
        for i in range(2,totalpage+1):
            url_info = self.base_url+str(i)
            yield scrapy.Request(url=url_info,callback=self.parse)

 3，数据库设计

4，pipelines.py文件中写入mysql数据库

# 写入mysql数据库
import pymysql
class KaiyuanzhongguoPipeline(object):
    conn = None
    mycursor = None

    def open_spider(self, spider):
        self.conn = pymysql.connect(host='172.16.25.4', user='root', password='root', db='scrapy')
        self.mycursor = self.conn.cursor()

    def process_item(self, item, spider):
        print('：正在写数据库...')
        sql = 'insert into kyzg VALUES (null,"%s","%s","%s","%s","%s","%s","%s")' % (
            item['name'], item['publishTime'], item['cycle'], item['application'], item['budgetMinByYuan'], item['budgetMaxByYuan'], item['ski'])
        bool = self.mycursor.execute(sql)
        self.conn.commit()
        return item

    def close_spider(self, spider):
        print('写入数据库完成...')
        self.mycursor.close()
        self.conn.close()

5，settings.py文件中设置请求头和打开下载管道

USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.71 Safari/537.36'

ITEM_PIPELINES = {
   'kaiyuanzhongguo.pipelines.KaiyuanzhongguoPipeline': 300,
}

6，运行爬虫

scrapy crawl kyzg --nolog

7，查看数据库是否写入成功

done。

转载于:https://www.cnblogs.com/nmsghgnv/p/11353395.html