42.scrapy爬取数据入库mongodb

scrapy爬虫采集数据存入mongodb
采集效果如图：


1.首先开启服务
切换到mongodb的bin目录下   命令：mongod --dbpath e:\data\db

另开黑窗口  命令：mongo.exe

2.连接可视化工具 studio—3t  建立本地连接

如图：

3.代码如下  采集的是玻璃网站产品数据   http://www.boliwang.com.cn/

boliwang.py

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

import scrapy

import re

from boliwang_web.items import BoliwangWebItem

class BoliwangSpider(scrapy.Spider):

    name = 'boliwang'

    allowed_domains = ['www.boliwang.com.cn']

    start_urls = ['http://www.boliwang.com.cn/gy/index-htm-page-1.html']

    custom_settings = {

        'DOWNLOAD_DELAY': 0.5,

        "DOWNLOADER_MIDDLEWARES": {

            'boliwang_web.middlewares.BoliwangWebDownloaderMiddleware': 500,

        },

    }

    def parse(self, response):

        # print(response.text)

        # 获取当前页面url

        link_urls = response.xpath("//table//tr/td[4]/ul/li[1]/a/@href").extract()

        for link_url in link_urls:

            # print(link_url)

            yield scrapy.Request(url=link_url, callback=self.parse_detail)

        # print('*'*100)

        #翻页

        tag = response.xpath("//div[@class='pages']/cite/text()").extract_first()

        # print(tag)

        p_num = tag.split('/')[1].replace('页','')

        # print(p_num)

        for i in range(1, int(p_num)+1):

            url = 'http://www.boliwang.com.cn/gy/index-htm-page-{}.html'.format(i)

            # print(url)

            yield scrapy.Request(url=url, callback=self.parse)

    def parse_detail(self, response):

        # 获取当前页面信息

        item = BoliwangWebItem()

        # 产品名称

        p_name = response.xpath("//table//tr[1]/td/h1[@id='title']/text()").extract_first()

        item['p_name'] = p_name

        # 品牌

        brand = response.xpath("//table//tr[2]/td[3]/table//tr[1]/td[2]/text()").extract_first()

        item['brand'] = brand

        # 单价

        price = response.xpath("//table//tr[2]/td[@class='f_b f_orange']/text()").extract_first()

        item['price'] = price

        # 起订

        set_up = response.xpath("//table//tr[3]/td[@class='f_b f_orange']/text()").extract_first()

        item['set_up'] = set_up

        # 供货总量

        summation = response.xpath("//table//tr[4]/td[@class='f_b f_orange']/text()").extract_first()

        item['summation'] = summation

        # 发货期限

        dispatch = response.xpath("//table//tr[5]/td[2]/span[@class='f_b f_orange']/text()").extract_first()

        dispatch = '{}'.format(dispatch)

        item['dispatch'] = dispatch

        # 所在地区

        dist = response.xpath("//table//tr[6]/td[2]/text()").extract_first()

        item['dist'] = dist

        # 有效期

        term_of_valid = response.xpath("//table//tr[7]/td[2]/text()").extract_first()

        item['term_of_valid'] = term_of_valid

        # 最后更新

        last_update = response.xpath("//table//tr[8]/td[2]/text()").extract_first()

        item['last_update'] = last_update

        # 详情信息

        content = response.xpath("//div[@class='box_body']/div[@id='content']").extract_first()

        item['content'] = content

        # 公司名称

        company = response.xpath("//li[@class='f_b t_c']/a/text()").extract_first()

        item['company'] = company

        # 联系人

        try:

            link_man = re.findall("<span>联系人</span>(.*?)&nbsp;&nbsp", response.text)

            link_man = link_man[0]

        except:

            link_man = ''

        item['link_man'] = link_man

        # 邮件

        try:

            email = re.findall('<li><span>邮件</span>(.*?)</li>', response.text)

            email = email[0]

        except:

            email = ''

        item['email'] = email

        # 电话

        try:

            tel = re.findall('<li><span>电话</span>(.*?)</li>', response.text)

            tel = tel[0]

        except:

            tel = ''

        item['tel'] = tel

        # 手机

        try :

            phone = re.findall('<li><span>手机</span>(.*?)</li>', response.text)

            phone = phone[0]

        except:

            phone = ''

        item['phone'] = phone

        # 公司地址

        try:

            c_dist = re.findall('<span>地址</span>(.*?)</li></ul>',response.text)

            c_dist = c_dist[0]

        except:

            c_dist = ''

        item['c_dist'] = c_dist

        yield item

        print('*'*100)

items.py

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

# Define here the models for your scraped items

#

# See documentation in:

# https://doc.scrapy.org/en/latest/topics/items.html

import scrapy

class BoliwangWebItem(scrapy.Item):

    # define the fields for your item here like:

    # name = scrapy.Field()

    collection = table = 'products'

    # 产品名称

    p_name = scrapy.Field()

    # 品牌

    brand = scrapy.Field()

    # 单价

    price = scrapy.Field()

    # 起订

    set_up = scrapy.Field()

    # 供货总量

    summation = scrapy.Field()

    # 发货期限

    dispatch = scrapy.Field()

    # 所在地区

    dist = scrapy.Field()

    # 有效期

    term_of_valid = scrapy.Field()

    # 最后更新

    last_update = scrapy.Field()

    # 详情信息

    content = scrapy.Field()

    # 公司名称

    company = scrapy.Field()

    # 联系人

    link_man = scrapy.Field()

    # 邮件

    email = scrapy.Field()

    # 电话

    tel = scrapy.Field()

    # 手机

    phone = scrapy.Field()

    # 公司地址

    c_dist = scrapy.Field()

items.py

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

# Define here the models for your spider middleware

#

# See documentation in:

# https://doc.scrapy.org/en/latest/topics/spider-middleware.html

from scrapy import signals

class BoliwangWebSpiderMiddleware(object):

    # Not all methods need to be defined. If a method is not defined,

    # scrapy acts as if the spider middleware does not modify the

    # passed objects.

    @classmethod

    def from_crawler(cls, crawler):

        # This method is used by Scrapy to create your spiders.

        s = cls()

        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)

        return s

    def process_spider_input(self, response, spider):

        # Called for each response that goes through the spider

        # middleware and into the spider.

        # Should return None or raise an exception.

        return None

    def process_spider_output(self, response, result, spider):

        # Called with the results returned from the Spider, after

        # it has processed the response.

        # Must return an iterable of Request, dict or Item objects.

        for i in result:

            yield i

    def process_spider_exception(self, response, exception, spider):

        # Called when a spider or process_spider_input() method

        # (from other spider middleware) raises an exception.

        # Should return either None or an iterable of Response, dict

        # or Item objects.

        pass

    def process_start_requests(self, start_requests, spider):

        # Called with the start requests of the spider, and works

        # similarly to the process_spider_output() method, except

        # that it doesn’t have a response associated.

        # Must return only requests (not items).

        for r in start_requests:

            yield r

    def spider_opened(self, spider):

        spider.logger.info('Spider opened: %s' % spider.name)

class BoliwangWebDownloaderMiddleware(object):

    # Not all methods need to be defined. If a method is not defined,

    # scrapy acts as if the downloader middleware does not modify the

    # passed objects.

    @classmethod

    def from_crawler(cls, crawler):

        # This method is used by Scrapy to create your spiders.

        s = cls()

        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)

        return s

    def process_request(self, request, spider):

        # Called for each request that goes through the downloader

        # middleware.

        # Must either:

        # - return None: continue processing this request

        # - or return a Response object

        # - or return a Request object

        # - or raise IgnoreRequest: process_exception() methods of

        #   installed downloader middleware will be called

        return None

    def process_response(self, request, response, spider):

        # Called with the response returned from the downloader.

        # Must either;

        # - return a Response object

        # - return a Request object

        # - or raise IgnoreRequest

        return response

    def process_exception(self, request, exception, spider):

        # Called when a download handler or a process_request()

        # (from other downloader middleware) raises an exception.

        # Must either:

        # - return None: continue processing this exception

        # - return a Response object: stops process_exception() chain

        # - return a Request object: stops process_exception() chain

        pass

    def spider_opened(self, spider):

        spider.logger.info('Spider opened: %s' % spider.name)

piplines.py

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

# Define your item pipelines here

#

# Don't forget to add your pipeline to the ITEM_PIPELINES setting

# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html

import pymongo

class BoliwangWebPipeline(object):

    def process_item(self, item, spider):

        return item

class MongoPipeline(object):

    def __init__(self, mongo_uri, mongo_db):

        self.mongo_uri = mongo_uri

        self.mongo_db = mongo_db

    @classmethod

    def from_crawler(cls, crawler):

        return cls(mongo_uri=crawler.settings.get('MONGO_URI'), mongo_db=crawler.settings.get('MONGO_DB'))

    def open_spider(self, spider):

        self.client = pymongo.MongoClient(self.mongo_uri)

        self.db = self.client[self.mongo_db]

    def process_item(self, item, spider):

        self.db[item.collection].insert(dict(item))

        return item

    def close_spider(self, spider):

        self.client.close()

settinngs.py

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

# Scrapy settings for boliwang_web project

#

# For simplicity, this file contains only settings considered important or

# commonly used. You can find more settings consulting the documentation:

#

#     https://doc.scrapy.org/en/latest/topics/settings.html

#     https://doc.scrapy.org/en/latest/topics/downloader-middleware.html

#     https://doc.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'boliwang_web'

SPIDER_MODULES = ['boliwang_web.spiders']

NEWSPIDER_MODULE = 'boliwang_web.spiders'

# Crawl responsibly by identifying yourself (and your website) on the user-agent

#USER_AGENT = 'boliwang_web (+http://www.yourdomain.com)'

# Obey robots.txt rules

ROBOTSTXT_OBEY = False

MONGO_HOST = "localhost"

MONGO_PORT = 27017

MONGO_DB = 'boliwang'

# Configure maximum concurrent requests performed by Scrapy (default: 16)

#CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)

# See https://doc.scrapy.org/en/latest/topics/settings.html#download-delay

# See also autothrottle settings and docs

#DOWNLOAD_DELAY = 3

# The download delay setting will honor only one of:

#CONCURRENT_REQUESTS_PER_DOMAIN = 16

#CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)

#COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)

#TELNETCONSOLE_ENABLED = False

# Override the default request headers:

#DEFAULT_REQUEST_HEADERS = {

#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',

#   'Accept-Language': 'en',

#}

# Enable or disable spider middlewares

# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html

#SPIDER_MIDDLEWARES = {

#    'boliwang_web.middlewares.BoliwangWebSpiderMiddleware': 543,

#}

# Enable or disable downloader middlewares

# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html

DOWNLOADER_MIDDLEWARES = {

   'boliwang_web.middlewares.BoliwangWebDownloaderMiddleware': 543,

}

# Enable or disable extensions

# See https://doc.scrapy.org/en/latest/topics/extensions.html

#EXTENSIONS = {

#    'scrapy.extensions.telnet.TelnetConsole': None,

#}

# Configure item pipelines

# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html

ITEM_PIPELINES = {

   'boliwang_web.pipelines.MongoPipeline': 300,

}

# Enable and configure the AutoThrottle extension (disabled by default)

# See https://doc.scrapy.org/en/latest/topics/autothrottle.html

#AUTOTHROTTLE_ENABLED = True

# The initial download delay

#AUTOTHROTTLE_START_DELAY = 5

# The maximum download delay to be set in case of high latencies

#AUTOTHROTTLE_MAX_DELAY = 60

# The average number of requests Scrapy should be sending in parallel to

# each remote server

#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0

# Enable showing throttling stats for every response received:

#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)

# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings

#HTTPCACHE_ENABLED = True

#HTTPCACHE_EXPIRATION_SECS = 0

#HTTPCACHE_DIR = 'httpcache'

#HTTPCACHE_IGNORE_HTTP_CODES = []

#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

42.scrapy爬取数据入库mongodb的更多相关文章

如何提升scrapy爬取数据的效率
在配置文件中修改相关参数: 增加并发默认的scrapy开启的并发线程为32个,可以适当的进行增加,再配置文件中修改CONCURRENT_REQUESTS = 100值为100,并发设置成了为100. ...
scrapy爬取数据的基本流程及url地址拼接
说明:初学者,整理后方便能及时完善,冗余之处请多提建议,感谢! 了解内容: Scrapy :抓取数据的爬虫框架异步与非阻塞的区别异步:指的是整个过程,中间如果是非阻塞的,那就是异步 ...
将scrapy爬取数据通过django入到SQLite数据库
1. 在django项目根目录位置创建scrapy项目,django_12是django项目,ABCkg是scrapy爬虫项目,app1是django的子应用 2.在Scrapy的settings.p ...
python之scrapy爬取数据保存到mysql数据库
1.创建工程 scrapy startproject tencent 2.创建项目 scrapy genspider mahuateng 3.既然保存到数据库,自然要安装pymsql pip inst ...
scrapy爬取数据保存csv、mysql、mongodb、json
目录前言 Items Pipelines 前言用Scrapy进行数据的保存进行一个常用的方法进行解析 Items item 是我们保存数据的容器,其类似于 python 中的字典.使用 item ...
scrapy爬取数据进行数据库存储和本地存储
今天记录下scrapy将数据存储到本地和数据库中,不是不会写,因为小编每次都写觉得都一样,所以记录下,以后直接用就可以了-^o^- 1．本地存储设置pipel ines.py class Ak17P ...
Python 爬取数据入库mysql
# -*- enconding:etf-8 -*- import pymysql import os import time import re serveraddr="localhost& ...
Python使用Scrapy框架爬取数据存入CSV文件(Python爬虫实战4)
1. Scrapy框架 Scrapy是python下实现爬虫功能的框架,能够将数据解析.数据处理.数据存储合为一体功能的爬虫框架. 2. Scrapy安装 1. 安装依赖包 yum install g ...
爬虫必知必会（6）_提升scrapy框架爬取数据的效率之配置篇
如何提升scrapy爬取数据的效率:只需要将如下五个步骤配置在配置文件中即可增加并发:默认scrapy开启的并发线程为32个,可以适当进行增加.在settings配置文件中修改CONCURRENT_ ...

随机推荐

PHP代码实现2 [从变量和数据的角度] 1
PHP代码实现2 [从变量和数据的角度] 1 数据类型 1.静态类型语言,比如:C/Java等,在静态语言类型中,类型的检查是在<编译>(compile-time)确定的, 也就是说在运行 ...
innobackupex
time innobackupex --defaults-file=/data/mysql/3306/my.cnf --user=root --password=123456 \--rsync --p ...
Excel技巧--漏斗图让转化率直观明了
当要实现如上图那样表现转化率等漏斗形图表时,可以这么做: 1.选择表格,点击“插入”-->“二维条形图”-->堆积条形图类型: 2.点击选中图表,点击”设计“-->“选择数据”: 将 ...
在windows server上配置java jdk后，可能要些时间生效。
特别是程序调用java写的bat脚本时.
java.lang.NoClassDefFoundError: com/sun/image/codec/jpeg/JPEGCodec 解决方案
使用java生成图片的时候,报了java.lang.NoClassDefFoundError: com/sun/image/codec/jpeg/JPEGCodec 错误. 根据这个类的api说明,在 ...
Excel导出文件流下载
Controller.cs @CrossOrigin(allowCredentials="true", allowedHeaders="*", methods= ...
学习笔记之PostgreSQL / pgAdmin / Psycopg / PostGIS
PostgreSQL: The world's most advanced open source database https://www.postgresql.org/ POSTGRESQL: T ...
[转][C#]WebAPI 必需 Dll
IRQL Ring0实现
一,IRQL的定义Interrupt ReQuest Level DDK对IRQL的定义是:中断请求级(IRQL)标示中断的优先级.处理器在一个IRQL上执行线程代码,IRQL是帮助决定线程如 ...
vmware导出为ovf
鼠标单击要导出的虚拟机à文件-à导出为OVFà开始导出(耗时有点长) 导出过程导出的文件格式为: 出现此报错请点击重试虚拟就就导入了导入后就可以使用了 vmware1 ...

42.scrapy爬取数据入库mongodb

42.scrapy爬取数据入库mongodb的更多相关文章

随机推荐

热门专题