Scrapy和MongoDB的应用---爬取

　　settings.py

BOT_NAME = ‘novelspider‘

SPIDER_MODULES = [‘novelspider.spiders‘]
NEWSPIDER_MODULE = ‘novelspider.spiders‘

ITEM_PIPELINES = [‘novelspider.pipelines.NovelspiderPipeline‘]　　#导入pipelines.py中的方法

USER_AGENT = ‘Mozilla/5.0 (Windows NT 6.1; WOW64; rv:39.0) Gecko/20100101 Firefox/39.0‘
COOKIES_ENABLED = True

MONGODB_HOST = ‘127.0.0.1‘   
MONGODB_PORT = 27017
MONGODB_DBNAME = ‘zzl‘　　　　#数据库名
MONGODB_DOCNAME = ‘Book‘　　　#表名

　　pipelines.py

from scrapy.conf import settings
import pymongo

class NovelspiderPipeline(object):
    def __init__(self):
        host = settings[‘MONGODB_HOST‘]
        port = settings[‘MONGODB_PORT‘]
        dbName = settings[‘MONGODB_DBNAME‘]
        client = pymongo.MongoClient(host=host, port=port)
        tdb = client[dbName]
        self.post = tdb[settings[‘MONGODB_DOCNAME‘]]

    def process_item(self, item, spider):
        bookInfo = dict(item)
        self.post.insert(bookInfo)
        return item

　　items.py

from scrapy import Item,Field


class NovelspiderItem(Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    bookName = Field()
    bookTitle = Field()
    chapterNum = Field()
    chapterName = Field()
    chapterURL = Field()

　　在spiders目录下创建novspider.py

from scrapy.spiders import CrawlSpider
from scrapy.selector import Selector
from novelspider.items import NovelspiderItem

class novSpider(CrawlSpider):
    name = "novspider"
    redis_key = ‘novspider:start_urls‘
    start_urls = [‘http://www.daomubiji.com/‘]

    def parse(self,response):
        selector = Selector(response)
        table = selector.xpath(‘//table‘)
        for each in table:
            bookName = each.xpath(‘tr/td[@colspan="3"]/center/h2/text()‘).extract()[0]
            content = each.xpath(‘tr/td/a/text()‘).extract()
            url = each.xpath(‘tr/td/a/@href‘).extract()
            for i in range(len(url)):
                item = NovelspiderItem()
                item[‘bookName‘] = bookName
                item[‘chapterURL‘] = url[i]
                try:
                    item[‘bookTitle‘] = content[i].split(‘ ‘)[0]
                    item[‘chapterNum‘] = content[i].split(‘ ‘)[1]
                except Exception,e:
                    continue

                try:
                    item[‘chapterName‘] = content[i].split(‘ ‘)[2]
                except Exception,e:
                    item[‘chapterName‘] = content[i].split(‘ ‘)[1][-3:]
                yield item

　　5.启动项目命令: scrapy crawl novspider.  

　　   抓取结果

Scrapy和MongoDB的应用---爬取

标签：