这里是直接拿之前未配置代码做修改，主要问题就是在piplines中添加修改配置文件(先解决文件下载问题，图片其实也类似)
效果如图：
北京造价信息网站爬虫bjjs.py# -*- coding: utf-8 -*-import scrapyimport refrom bjjs_web.items import BjjsWebItemclass BjjsSpider(scrapy.Spider): name = 'bjjs' allowed_domains = ['www.bjjs.gov.cn'] base_url=['http://www.bjjs.gov.cn'] start_urls = ['http://www.bjjs.gov.cn/bjjs/gcjs/zczjxx/zjxx/48843934-1.shtml'] custom_settings = { "DOWNLOAD_DELAY": 0.5, "ITEM_PIPELINES": { 'bjjs_web.pipelines.MysqlPipeline': 320, 'bjjs_web.pipelines.MyFilePipeline': 321, }, "DOWNLOADER_MIDDLEWARES": { 'bjjs_web.middlewares.BjjsWebDownloaderMiddleware': 500, }, } def parse(self, response): # tag_list=response.xpath("//div[@class='list_box']/ul/li/a/@href").extract() # for tag in tag_list: # url=self.base_url[0]+tag # print(url) # print('*'*100) #正则匹配url，标题，时间 tag_list=re.findall('items.py# -*- coding: utf-8 -*-# Define here the models for your scraped items## See documentation in:# https://doc.scrapy.org/en/latest/topics/items.htmlimport scrapyclass BjjsWebItem(scrapy.Item): # define the fields for your item here like: # name = scrapy.Field() file_urls=scrapy.Field() title=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.htmlfrom scrapy import signalsclass BjjsWebSpiderMiddleware(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 BjjsWebDownloaderMiddleware(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.htmlfrom scrapy.conf import settingsfrom scrapy.exceptions import DropItemfrom scrapy.pipelines.files import FilesPipelineimport pymysqlimport scrapyclass BjjsWebPipeline(object): def process_item(self, item, spider): return item# 数据保存mysqlclass 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()#定义下载class MyFilePipeline(FilesPipeline): def get_media_requests(self, item, info): for file_url in item['file_urls']: yield scrapy.Request(file_url, meta = { 'item': item}) def file_path(self, request, response=None, info=None): item = request.meta['item'] filename = u'full/{}.pdf'.format(item['title']) return filename def item_completed(self, results, item, info): image_paths = [x['path'] for ok, x in results if ok] if not image_paths: raise DropItem("Item contains no file_urls") item['file_urls'] = image_paths return item setting.py# -*- coding: utf-8 -*-# Scrapy settings for bjjs_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.htmlBOT_NAME = 'bjjs_web'SPIDER_MODULES = ['bjjs_web.spiders']NEWSPIDER_MODULE = 'bjjs_web.spiders'FILES_STORE = './download'# Crawl responsibly by identifying yourself (and your website) on the user-agent#USER_AGENT = 'bjjs_web (+http://www.yourdomain.com)'# Obey robots.txt rulesROBOTSTXT_OBEY = True# mysql配置参数MYSQL_HOST = "172.16.10.157"MYSQL_PORT = 3306MYSQL_USER = "root"MYSQL_PASSWORD = "123456"MYSQL_DB = 'web_datas'TABLE = "web_bjjs"# 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 = { # 'bjjs_web.middlewares.BjjsWebSpiderMiddleware': 543,#}# Enable or disable downloader middlewares# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.htmlDOWNLOADER_MIDDLEWARES = { 'bjjs_web.middlewares.BjjsWebDownloaderMiddleware': 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.htmlITEM_PIPELINES = { # 下载文件管道 'scrapy.pipelines.MyFilePipeline': 1, 'bjjs_web.pipelines.BjjsWebPipeline': 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'
posted on 2018-10-24 11:32 阅读( ...) 评论( ...)