这里主要解决的问题：
1.翻页需要找到页面中加载的两个参数。
'__VIEWSTATE': '{}'.format(response.meta['data']['__VIEWSTATE']),
'__EVENTVALIDATION': '{}'.format(response.meta['data']['__EVENTVALIDATION']),
还有一点需要注意的就是 dont_filter=False
yield scrapy.FormRequest(url=response.url, callback=self.parse, formdata=data, method="POST", dont_filter=False)
2.日期 我自己做的时候取的是2008-2018年的数据。
3.还有的就是数据字段入库乱的问题。
4.一些问题比如越界等，我都没做具体的解决只是做了一个抛出异常没做处理。
这个相对较麻烦一点，首先先分析一下网站，地址: http://www.nbzj.net/MaterialPriceList.aspx (宁波造价网) 这里呢我主要是拿这个材料信息价数据。
nbzj.py
# -*- coding: utf-8 -*- import scrapy import re from nbzj_web.items import NbzjWebItem class NbzjSpider(scrapy.Spider): name = 'nbzj' allowed_domains = ['www.nbzj.net'] start_urls = ['http://www.nbzj.net/MaterialPriceList.aspx'] custom_settings = { "DOWNLOAD_DELAY": 1, "ITEM_PIPELINES": { 'nbzj_web.pipelines.MysqlPipeline': 300, }, "DOWNLOADER_MIDDLEWARES": { 'nbzj_web.middlewares.NbzjWebDownloaderMiddleware': 500, }, } def parse(self, response): _response=response.text # print(_response) #获取翻页参数 __VIEWSTATE=re.findall(r'id="__VIEWSTATE" value="(.*?)" />',_response) A=__VIEWSTATE[0] # print(A) __EVENTVALIDATION=re.findall(r'id="__EVENTVALIDATION" value="(.*?)" />',_response) B=__EVENTVALIDATION[0] # print(B) #页码 page_num=re.findall(r'>下页</a><a title="转到第(.*?)页"',_response) # print(page_num[0]) max_page=page_num[0] # print(max_page) content={ '__VIEWSTATE':A, '__EVENTVALIDATION':B, 'page_num':max_page, } # 获取标签列表 tag_list=response.xpath("//div[@class='fcon']/table[@class='mytable']//tr/td").extract() # print(tag_list) #这里我直接取文本出现问题，我就直接拿标签数据等下面在做字符串的修改删除 list=[] try: tag1=tag_list[:9] list.append(tag1) tag2=tag_list[9:18] list.append(tag2) tag3=tag_list[18:27] list.append(tag3) tag4=tag_list[27:36] list.append(tag4) tag5=tag_list[36:45] list.append(tag5) tag6=tag_list[45:54] list.append(tag6) tag7=tag_list[54:63] list.append(tag7) tag8=tag_list[63:72] list.append(tag8) tag9=tag_list[72:81] list.append(tag9) tag10=tag_list[81:90] list.append(tag10) tag11=tag_list[99:108] list.append(tag11) tag12=tag_list[108:117] list.append(tag12) tag13=tag_list[117:126] list.append(tag13) tag14=tag_list[126:135] list.append(tag14) tag15=tag_list[135:144] list.append(tag15) print(list) for tag in list: item=NbzjWebItem() # print(tag) #代码 code=tag[0].replace('<td style="text-align: center">','').replace('</td>','') # print(code) item['code']=code #名称 name=tag[1].replace('<td>','').replace('</td>','') # print(name) item['name']=name #地区 district=tag[2].replace('<td style="text-align: center">','').replace('</td>','') # print(district) item['district']=district #型号规格 _type=tag[3].replace('<td>','').replace('</td>','') # print(_type) item['_type']=_type #单位 unit=tag[4].replace('<td style="text-align: center">','').replace('</td>','') # print(unit) item['unit']=unit #除税价 except_tax_price = tag[5].replace('<td style="text-align: right">','').replace('</td>','') # print(except_tax_price) item['except_tax_price']=except_tax_price #含税价 tax_price = tag[6].replace('<td style="text-align: right">','').replace('</td>','') # print(tax_price) item['tax_price']=tax_price #时间 time=tag[7].replace('<td style="text-align: center">','').replace('</td>','') print(time) item['time']=time # print('-'*100) yield item # print('*'*100) except: pass yield scrapy.Request(url=response.url,callback=self.parse_detail,meta={"data": content}) def parse_detail(self,response): for h in range(2008,2019): list=['01','02','03','04','05','06','07','08','09','10','11','12'] for j in list: try: max_page=response.meta['data']['page_num'] # print(max_page) for i in range(2,int(max_page)): data={ '__VIEWSTATE': '{}'.format(response.meta['data']['__VIEWSTATE']), '__VIEWSTATEGENERATOR': 'E53A32FA', '__EVENTTARGET': 'ctl00$ContentPlaceContent$Pager', '__EVENTARGUMENT':'{}'.format(i), '__EVENTVALIDATION': '{}'.format(response.meta['data']['__EVENTVALIDATION']), 'HeadSearchType': 'localsite', 'ctl00$ContentPlaceContent$txtnewCode':'', 'ctl00$ContentPlaceContent$txtMaterualName':'', 'ctl00$ContentPlaceContent$ddlArea':'', 'ctl00$ContentPlaceContent$txtPublishDate': '{} - 0{}'.format(h,j), 'ctl00$ContentPlaceContent$ddlCategoryOne':'', 'ctl00$ContentPlaceContent$hidCateId':'', 'ctl00$ContentPlaceContent$txtSpecification':'', 'ctl00$ContentPlaceContent$Pager_input': '{}'.format(i-1), 'ctl00$foot$ddlsnzjw': '0', 'ctl00$foot$ddlswzjw': '0', 'ctl00$foot$ddlqtxgw': '0' } yield scrapy.FormRequest(url=response.url, callback=self.parse, formdata=data, method="POST", dont_filter=False) except: pass
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 NbzjWebItem(scrapy.Item): # define the fields for your item here like: # name = scrapy.Field() code=scrapy.Field() name=scrapy.Field() district=scrapy.Field() _type=scrapy.Field() unit=scrapy.Field() except_tax_price=scrapy.Field() tax_price =scrapy.Field() time=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 NbzjWebSpiderMiddleware(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 NbzjWebDownloaderMiddleware(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 # -*- coding: utf-8 -*- from scrapy.conf import settings import pymysql class NbzjWebPipeline(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 nbzj_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 = 'nbzj_web' SPIDER_MODULES = ['nbzj_web.spiders'] NEWSPIDER_MODULE = 'nbzj_web.spiders' # mysql配置参数 MYSQL_HOST = "172.16.10.197" MYSQL_PORT = 3306 MYSQL_USER = "root" MYSQL_PASSWORD = "123456" MYSQL_DB = 'web_datas' TABLE = "web_nbzj" # Crawl responsibly by identifying yourself (and your website) on the user-agent #USER_AGENT = 'nbzj_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 = { # 'nbzj_web.middlewares.NbzjWebSpiderMiddleware': 543, #} # Enable or disable downloader middlewares # See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html DOWNLOADER_MIDDLEWARES = { 'nbzj_web.middlewares.NbzjWebDownloaderMiddleware': 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 = { 'nbzj_web.pipelines.NbzjWebPipeline': 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'
scrapy crawl nbzj 执行结果如下
由于设置deloy为 1s 所以速度会比较慢，采集237142条数据。
