33.scrapy采集网站表单数据

这几天一直都再用scrapy写网站数据采集的爬虫，这里我就选一个写过的爬虫来记录一下。

杭州造价网：http://183.129.219.195:8081/bs/hzzjb/web/list

这里出现的主要问题就是：

1.

这里我的代码会出现一些问题，内存溢出，由于程序一直在运行，内存一直在增加（未释放内存，有待改进），就会导致爬虫程序假死等待。

2.

yield scrapy.FormRequest(url='http://183.129.219.195:8081/bs/hzzjb/web/list', callback=self.parse, formdata=data, method="POST", dont_filter=True)

dont_filter 默认设置False 导致 去重过滤，未能获取下一页链接。

3.
还有一个问题就是最后一页的数据我没解决，我拿了5032页，这个翻页还是没完善好。

网站主要信息：

hzzjb.py

# -*- coding: utf-8 -*-
import scrapy
import json
import re
from hzzjb_web.items import HzzjbWebItem
class HzzjbSpider(scrapy.Spider):
    name = 'hzzjb'
    allowed_domains = ['183.129.219.195:8081/bs']
    start_urls = ['http://183.129.219.195:8081/bs/hzzjb/web/list']
    custom_settings = {
        "DOWNLOAD_DELAY": 1,
        "ITEM_PIPELINES": {
            'hzzjb_web.pipelines.MysqlPipeline': 320,
        },
        "DOWNLOADER_MIDDLEWARES": {
            'hzzjb_web.middlewares.HzzjbWebDownloaderMiddleware': 500
        },
    }
    def parse(self, response):
        _response=response.text
        # print(_response)
        try :

            #获取信息表
            tag_list=response.xpath("//table[@class='table1']//tr/td").extract()

            # print(tag_list)
            # for i in tag_list:
            #     print(i)
            tag1=tag_list[:9]
            tag2=tag_list[9:18]
            tag3=tag_list[18:27]
            tag4=tag_list[27:36]
            tag5=tag_list[36:45]
            tag6=tag_list[45:54]
            tag7=tag_list[54:63]
            tag8=tag_list[63:72]
            tag9=tag_list[72:81]
            tag10=tag_list[81:90]
            tag11=tag_list[90:99]
            tag12=tag_list[99:108]
            tag13=tag_list[108:117]
            tag14=tag_list[117:126]
            tag15=tag_list[126:135]
            tag16=tag_list[135:144]
            tag17=tag_list[144:153]
            tag18=tag_list[153:162]
            tag19=tag_list[162:171]
            tag20=tag_list[171:180]

            list=[]
            list.append(tag1)
            list.append(tag2)
            list.append(tag3)
            list.append(tag4)
            list.append(tag5)
            list.append(tag6)
            list.append(tag7)
            list.append(tag8)
            list.append(tag9)
            list.append(tag10)
            list.append(tag11)
            list.append(tag12)
            list.append(tag13)
            list.append(tag14)
            list.append(tag15)
            list.append(tag16)
            list.append(tag17)
            list.append(tag18)
            list.append(tag19)
            list.append(tag20)

            # print(list)
        except:
            print('————————————————网站编码有异常！————————————————————')

        for index,tag in enumerate(list):
            # print('*'*100)
            # print(index+1,TAG(i))

            item = HzzjbWebItem()
            # 地区
            district = tag[0].replace('<td>','').replace('</td>','')
            # print(district)
            item['district'] = district
            # 类别
            category = tag[1].replace('<td>','').replace('</td>','')
            # print(category)
            item['category'] = category
            # 材料名称
            material_name = tag[2].replace('<td>','').replace('</td>','')
            # print(material_name)
            item['material_name'] = material_name
            # 规格及型号
            version = tag[3].replace('<td>','').replace('</td>','')
            # print(version)
            item['version'] = version
            # 单位
            unit = tag[4].replace('<td>','').replace('</td>','')
            # print(unit)
            item['unit'] = unit
            # 含税信息价
            tax_information_price = tag[5].replace('<td>','').replace('</td>','')
            # print(tax_information_price)
            item['tax_information_price'] = tax_information_price
            # 除税信息价
            except_tax_information_price = tag[6].replace('<td>','').replace('</td>','')
            # print(except_tax_information_price)
            item['except_tax_information_price'] = except_tax_information_price
            # 年/月
            year_month = tag[7].replace('<td>','').replace('</td>','')
            # print(year_month)
            item['y_m'] = year_month
            # print('*'*100)

            yield item
        for i in range(2, 5032):
            # 翻页
            data={
                'mtype': '',
                '_query.nfStart':'',
                '_query.yfStart':'',
                '_query.nfEnd':'',
                '_query.yfEnd':'',
                '_query.dqstr':'',
                '_query.dq':'',
                '_query.lbtype':'',
                '_query.clmc':'',
                '_query.ggjxh':'',
                'pageNumber': '{}'.format(i),
                'pageSize':'',
                'orderColunm':'',
                'orderMode':'',
            }

            yield scrapy.FormRequest(url='http://183.129.219.195:8081/bs/hzzjb/web/list', callback=self.parse, formdata=data, method="POST", dont_filter=True)

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 HzzjbWebItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()

    district=scrapy.Field()
    category=scrapy.Field()
    material_name=scrapy.Field()
    version=scrapy.Field()
    unit=scrapy.Field()
    tax_information_price=scrapy.Field()
    except_tax_information_price=scrapy.Field()
    y_m=scrapy.Field()

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 HzzjbWebSpiderMiddleware(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 HzzjbWebDownloaderMiddleware(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
from scrapy.conf import settings
import pymysql

class HzzjbWebPipeline(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()

setting.py

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

# Scrapy settings for hzzjb_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 = 'hzzjb_web'

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

# mysql配置参数
MYSQL_HOST = "172.16.10.197"
MYSQL_PORT = 3306
MYSQL_USER = "root"
MYSQL_PASSWORD = ""
MYSQL_DB = 'web_datas'
TABLE = "web_hzzjb"

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

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# 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 = {
#    'hzzjb_web.middlewares.HzzjbWebSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
   'hzzjb_web.middlewares.HzzjbWebDownloaderMiddleware': 500,
}

# 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 = {
   'hzzjb_web.pipelines.HzzjbWebPipeline': 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'

执行文件  ：scrapy crawl hzzjb -s JOBDIR=myspider 设置持久化

就会生成如下文件：

数据入库如图：