一个scrapy使用的demo,以后抓数据可以参考它
1.Items
# -*- coding: utf-8 -*- # Define here the models for your scraped items # # See documentation in: # http://doc.scrapy.org/en/latest/topics/items.html import scrapy class RssItem(scrapy.Item): # define the fields for your item here like: # name = scrapy.Field() title = scrapy.Field() link = scrapy.Field() description = scrapy.Field() lastBuildDate = scrapy.Field() generator = scrapy.Field() language = scrapy.Field() copyright = scrapy.Field() pubDate = scrapy.Field() items = scrapy.Field() class NodeItem(scrapy.Item): title = scrapy.Field() link = scrapy.Field() description = scrapy.Field() author = scrapy.Field() comments = scrapy.Field() pubDate = scrapy.Field() guid = scrapy.Field() class RowItem(scrapy.Item): name = scrapy.Field() sex = scrapy.Field() addr = scrapy.Field() email = scrapy.Field() class GoodsItem(scrapy.Item): name = scrapy.Field() price = scrapy.Field() link = scrapy.Field() commnum = scrapy.Field() class NewsLinkItem(scrapy.Item): name = scrapy.Field() link = scrapy.Field()
2.settings
# -*- coding: utf-8 -*- # Scrapy settings for demo project # # For simplicity, this file contains only settings considered important or # commonly used. You can find more settings consulting the documentation: # # http://doc.scrapy.org/en/latest/topics/settings.html # http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html # http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html BOT_NAME = 'demo' SPIDER_MODULES = ['demo.spiders'] NEWSPIDER_MODULE = 'demo.spiders' # Crawl responsibly by identifying yourself (and your website) on the user-agent #USER_AGENT = 'demo (+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 http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay # See also autothrottle settings and docs DOWNLOAD_DELAY = 0.5 # 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 http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html #SPIDER_MIDDLEWARES = { # 'demo.middlewares.DemoSpiderMiddleware': 543, #} # Enable or disable downloader middlewares # See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html #DOWNLOADER_MIDDLEWARES = { # 'demo.middlewares.MyCustomDownloaderMiddleware': 543, #} # Enable or disable extensions # See http://scrapy.readthedocs.org/en/latest/topics/extensions.html #EXTENSIONS = { # 'scrapy.extensions.telnet.TelnetConsole': None, #} # Configure item pipelines # See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html ITEM_PIPELINES = { 'demo.pipelines.DemoPipeline': 300, } # Enable and configure the AutoThrottle extension (disabled by default) # See http://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 http://scrapy.readthedocs.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'
3.pipline
# -*- coding: utf-8 -*- import json import codecs from demo.dbconnect import DbUtil # Define your item pipelines here # # Don't forget to add your pipeline to the ITEM_PIPELINES setting # See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html class DemoPipeline(object): def __init__(self): self.file = codecs.open("mydata.json", 'wb', encoding='utf-8') self.dbutil = DbUtil('127.0.0.1','longlh','solong1980','orders') def process_item(self, item, spider): #print(item) #print(spider.name) if spider.name is 'DangDangSpider': for i in range(0,len(item['name'])): name = item['name'][i] link = item['link'][i] price = item['price'][i] commnum = item['commnum'][i] goods ={'name':name,'link':link,'price':price,'commnum':commnum} line = json.dumps(dict(goods), ensure_ascii=False) line = str(line) + '\n' self.file.write(line) if spider.name is 'webcrawl': for i in range(0,len(item['name'])): name = item['name'][i] link = item['link'][i] print(name) print(link) print("insert into tbtable(name,link) values('" + name + "','" + link + "')") self.dbutil.add("insert into tbtable(name,link) values('" + name + "','" + link + "')") return item def close_spider(self, spider): self.file.close() self.dbutil.close()
4.db util
# -*- coding: utf-8 -*- import pymysql import logging from pymysql import charset class DbUtil(): def __init__(self, host, user, passwd, db, port=3306): self.host = host self.port = port self.user = user self.passwd = passwd self.db = db try: self.conn = pymysql.connect(host, user, passwd, db,charset='utf8') except Exception as e: logging.error(str(e)) raise Exception("connect fail") def cursor(self): return self.conn.cursor() def select(self, sql): return self.cursor().execute(sql) def add(self, sql): self.conn.query(sql) def close(self): try: self.conn.commit() except Exception as e: print(str(e)) finally: self.conn.close()
5.Spider
# -*- coding: utf-8 -*- from scrapy.linkextractors import LinkExtractor from scrapy.spiders import CrawlSpider, Rule from demo.items import NewsLinkItem class WebcrawlSpider(CrawlSpider): name = 'webcrawl' allowed_domains = ['sohu.com'] start_urls = ['http://sports.sohu.com/nba.shtml'] rules = ( Rule(LinkExtractor(allow=('.*?/n.*?shtml'),allow_domains=('sohu.com')), callback='parse_item', follow=True), ) def parse_item(self, response): i = NewsLinkItem() i['name'] = response.xpath('/html/head/title/text()').extract() i['link'] = response.xpath('//link[@rel="canonical"]/@href').extract() return i