36.scrapy框架采集全球玻璃网数据

1.
采集目标地址 https://www.glass.cn/gongying/sellindex.aspx  网站比较简单，没什么大的需要注意的问题。
2.
通过分析测试 https://www.glass.cn/gongying/a_l_p1_ky/ 等价于目标采集网站首页，只需设置{}.format 翻页
这个完整比较简单，就是获取一下页码，再做一下翻页，循环采集页面跳转url，再进入url采集页面内容信息。
3.
采集数据过程及结果

#glass_gy.py

# -*- coding: utf-8 -*-
import scrapy
import re
from glass_gy_web.items import GlassGyWebItem
class GlassGySpider(scrapy.Spider):
    name = 'glass_gy'
    allowed_domains = ['www.glass.cn']
    start_urls = ['https://www.glass.cn/gongying/a_l_p1_ky/']
    custom_settings = {
        'DOWNLOAD_DELAY': 0.5,
        "ITEM_PIPELINES": {
            'glass_gy_web.pipelines.MysqlPipeline': 300,
        },
        "DOWNLOADER_MIDDLEWARES": {
            'glass_gy_web.middlewares.GlassGyWebDownloaderMiddleware': 500,
        },
    }
    def parse(self, response):

        link_urls = response.xpath("//div[@class='brandinfotxt z']/h4[@class='brandHTit clearfix']/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
        pg_num = re.findall('共(.*?)页',response.text)
        # print(pg_num[0])
        for i in range(2, int(pg_num[0])+1):
            url = 'https://www.glass.cn/gongying/a_l_p{}_ky/'.format(i)
            yield scrapy.Request(url=url, callback=self.parse)

    def parse_detail(self, response):

        item=GlassGyWebItem()
        # 产品名称
        p_name = response.xpath("//div[@class='ProductDel']/h1/text()").extract_first()
        item['p_name'] = p_name
        # 数量
        num = response.xpath("//table//tr/td[@class='bot'][1]/text()").extract_first()
        item['num'] = num
        # 价格
        price = response.xpath("//table//tr/td[@class='bot'][2]/text()").extract_first()
        item['price'] = price
        # 供货总量
        total_supply = re.findall('<li><span>供货总量：</span>(.*?)</li>',response.text)
        item['total_supply'] = total_supply[0]
        # 最小起订
        _order = re.findall('<li><span>最小起订： </span>(.*?)</li>',response.text)
        item['_order'] = _order[0]
        # 发货地址
        ship_add = re.findall('<li><span>发货地址： </span>(.*?)</li>',response.text)
        item['ship_add'] = ship_add[0]
        # 发货期限
        dispatch = re.findall('<li><span>发货期限： </span>(.*?)</li>',response.text)
        item['dispatch'] = dispatch[0]
        # 物流运费
        fare = re.findall('<li><span>物流运费： </span>(.*?)</li>',response.text)
        item['fare'] = fare[0]
        # 发布日期
        release_date = re.findall('<li><span>发布日期：</span>(.*?)</li>',response.text)
        item['release_date'] = release_date[0]
        # 采购电话
        purchase = re.findall('<div class="sell_tel clearfix"><span>采购电话：</span>(.*?)</div>',response.text)
        item['purchase'] = purchase[0]
        # 产品详情
        content = response.xpath("//div[@id='pdetail']/text()").extract()
        item['content'] = content[-1].strip()
        # 公司名称
        company = response.xpath("//div[@class='zcbw']/h2/a/text()").extract_first()
        item['company'] = company
        # 联系人
        linkman = re.findall('<span>联系人：(.*?)</span>',response.text)
        item['linkman'] = linkman[0]
        # 手机
        phone = re.findall('<li>手机：(.*?)</li>',response.text)
        item['phone'] = phone[0]
        # 电话
        mobile = re.findall('<li>电话：(.*?)</li>',response.text)
        item['mobile'] = mobile[0]
        # 营业执照
        try:
             licence = re.findall('<li>营业执照：(.*?) <img',response.text)
             licence = licence[0]
        except:
             licence = ""
        item['licence'] = licence
        # 经营模式
        try:
            model = re.findall('<li>经营模式： (.*?)</li',response.text)
            model = model[0]
        except:
            model = ""
        item['model'] = model
        # 所在地区
        dist = re.findall('<li>所在地区：(.*?)</li>',response.text)
        item['dist'] = dist[0]
        # 产品数量
        quantity = re.findall('<li>产品数量：(.*?)</li>',response.text)
        item['quantity'] = quantity[0]
        # 玻璃金币
        gold = re.findall('<li>玻璃金币：(.*?)</li>',response.text)
        item['gold'] = gold[0]

        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 GlassGyWebItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    # 产品名称
    p_name = scrapy.Field()
    # 数量
    num = scrapy.Field()
    # 价格
    price = scrapy.Field()
    # 供货总量
    total_supply = scrapy.Field()
    # 最小起订
    _order = scrapy.Field()
    # 发货地址
    ship_add = scrapy.Field()
    # 发货期限
    dispatch = scrapy.Field()
    # 物流运费
    fare = scrapy.Field()
    # 发布日期
    release_date = scrapy.Field()
    # 采购电话
    purchase = scrapy.Field()
    # 产品详情
    content = scrapy.Field()
    # 公司名称
    company = scrapy.Field()
    # 联系人
    linkman = scrapy.Field()
    # 手机
    phone = scrapy.Field()
    # 电话
    mobile = scrapy.Field()
    # 营业执照
    licence = scrapy.Field()
    # 经营模式
    model = scrapy.Field()
    # 所在地区
    dist = scrapy.Field()
    # 产品数量
    quantity = scrapy.Field()
    # 玻璃金币
    gold = scrapy.Field()

# 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
from scrapy.conf import settings
import pymysql

class GlassGyWebPipeline(object):
    def process_item(self, item, spider):
        return item


# 数据保存mysql
class MysqlPipeline(object):

    def open_spider(self, spider):
        self.host = settings.get('MYSQL_HOST')
        self.port = settings.get('MYSQL_PORT')
        self.user = settings.get('MYSQL_USER')
        self.password = settings.get('MYSQL_PASSWORD')
        self.db = settings.get(('MYSQL_DB'))
        self.table = settings.get('TABLE')
        self.client = pymysql.connect(host=self.host, user=self.user, password=self.password, port=self.port, db=self.db, charset='utf8')

    def process_item(self, item, spider):
        item_dict = dict(item)
        cursor = self.client.cursor()
        values = ','.join(['%s'] * len(item_dict))
        keys = ','.join(item_dict.keys())
        sql = 'INSERT INTO {table}({keys}) VALUES ({values})'.format(table=self.table, keys=keys, values=values)
        try:
            if cursor.execute(sql, tuple(item_dict.values())):  # 第一个值为sql语句第二个为 值 为一个元组
                print('数据入库成功!')
                self.client.commit()
        except Exception as e:
            print(e)

            print('数据已存在!')
            self.client.rollback()
        return item

    def close_spider(self, spider):

        self.client.close()

#settings.py

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

# Scrapy settings for glass_gy_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 = 'glass_gy_web'

SPIDER_MODULES = ['glass_gy_web.spiders']
NEWSPIDER_MODULE = 'glass_gy_web.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'glass_gy_web (+http://www.yourdomain.com)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# mysql配置参数
MYSQL_HOST = "172.16.10.157"
MYSQL_PORT = 3306
MYSQL_USER = "root"
MYSQL_PASSWORD = "123456"
MYSQL_DB = 'web_datas'
TABLE = "glass_gy"

# 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 = {
#    'glass_gy_web.middlewares.GlassGyWebSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
   'glass_gy_web.middlewares.GlassGyWebDownloaderMiddleware': 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 = {
   'glass_gy_web.pipelines.GlassGyWebPipeline': 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'

#middlewares.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 GlassGyWebSpiderMiddleware(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 GlassGyWebDownloaderMiddleware(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)