Scrapy框架抓取豆瓣电影TOP250 实践Python的爬虫框架Scrapy来抓取豆瓣电影TOP250

easy_install -U Scrapy

pip install Scrapy

D:\WEB\Python>scrapy startproject doubanmoive

D:\WEB\Python\doubanmoive>tree /f
Folder PATH listing for volume Data
Volume serial number is 00000200 34EC:9CB9
D:.
│ scrapy.cfg
│
└─doubanmoive
 │ items.py
 │ pipelines.py
 │ settings.py
 │ __init__.py
 │
 └─spiders
   __init__.py

from scrapy.item import Item, Field

class DoubanmoiveItem(Item):
  pass

from scrapy.item import Item, Field

class DoubanmoiveItem(Item):
 name=Field()#电影名
 year=Field()#上映年份
 score=Field()#豆瓣分数
 director=Field()#导演
 classification=Field()#分类
 actor=Field()#演员

# -*- coding: utf-8 -*-
from scrapy.selector import Selector
from scrapy.contrib.spiders import CrawlSpider,Rule
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from doubanmoive.items import DoubanmoiveItem

class MoiveSpider(CrawlSpider):
 name="doubanmoive"
 allowed_domains=["movie.douban.com"]
 start_urls=["http://movie.douban.com/top250"]
 rules=[
  Rule(SgmlLinkExtractor(allow=(r'http://movie.douban.com/top250\?start=\d+.*'))),
  Rule(SgmlLinkExtractor(allow=(r'http://movie.douban.com/subject/\d+')),callback="parse_item"),  
 ]

 def parse_item(self,response):
  sel=Selector(response)
  item=DoubanmoiveItem()
  item['name']=sel.xpath('//*[@id="content"]/h1/span[1]/text()').extract()
  item['year']=sel.xpath('//*[@id="content"]/h1/span[2]/text()').re(r'\((\d+)\)')
  item['score']=sel.xpath('//*[@id="interest_sectl"]/div/p[1]/strong/text()').extract()
  item['director']=sel.xpath('//*[@id="info"]/span[1]/a/text()').extract()
  item['classification']= sel.xpath('//span[@property="v:genre"]/text()').extract()
  item['actor']= sel.xpath('//*[@id="info"]/span[3]/a[1]/text()').extract()
  return item

# -*- coding: utf-8 -*-
from scrapy import log
from twisted.enterprise import adbapi
from scrapy.http import Request

import MySQLdb
import MySQLdb.cursors


class DoubanmoivePipeline(object):
 def __init__(self):
  self.dbpool = adbapi.ConnectionPool('MySQLdb',
    db = 'python',
    user = 'root',
    passwd = 'root',
    cursorclass = MySQLdb.cursors.DictCursor,
    charset = 'utf8',
    use_unicode = False
  )
 def process_item(self, item, spider):
  query = self.dbpool.runInteraction(self._conditional_insert, item)
  query.addErrback(self.handle_error)
  return item

 def _conditional_insert(self,tx,item):
  tx.execute("select * from doubanmoive where m_name= %s",(item['name'][0],))
  result=tx.fetchone()
  log.msg(result,level=log.DEBUG)
  print result
  if result:
   log.msg("Item already stored in db:%s" % item,level=log.DEBUG)
  else:
   classification=actor=''
   lenClassification=len(item['classification'])
   lenActor=len(item['actor'])
   for n in xrange(lenClassification):
    classification+=item['classification'][n]
    if n<lenClassification-1:
     classification+='/'
   for n in xrange(lenActor):
    actor+=item['actor'][n]
    if n<lenActor-1:
     actor+='/'

   tx.execute(\
    "insert into doubanmoive (m_name,m_year,m_score,m_director,m_classification,m_actor) values (%s,%s,%s,%s,%s,%s)",\
    (item['name'][0],item['year'][0],item['score'][0],item['director'][0],classification,actor))
   log.msg("Item stored in db: %s" % item, level=log.DEBUG)

 def handle_error(self, e):
  log.err(e)

# -*- coding: utf-8 -*-
import pymongo

from scrapy.exceptions import DropItem
from scrapy.conf import settings
from scrapy import log

class MongoDBPipeline(object):
 #Connect to the MongoDB database
 def __init__(self):
  connection = pymongo.Connection(settings['MONGODB_SERVER'], settings['MONGODB_PORT'])
  db = connection[settings['MONGODB_DB']]
  self.collection = db[settings['MONGODB_COLLECTION']]

 def process_item(self, item, spider):
  #Remove invalid data
  valid = True
  for data in item:
   if not data:
   valid = False
   raise DropItem("Missing %s of blogpost from %s" %(data, item['url']))
  if valid:
  #Insert data into database
   new_moive=[{
    "name":item['name'][0],
    "year":item['year'][0],
    "score":item['score'][0],
    "director":item['director'],
    "classification":item['classification'],
    "actor":item['actor']
   }]
   self.collection.insert(new_moive)
   log.msg("Item wrote to MongoDB database %s/%s" %
   (settings['MONGODB_DB'], settings['MONGODB_COLLECTION']),
   level=log.DEBUG, spider=spider) 
  return item

BOT_NAME = 'doubanmoive'
SPIDER_MODULES = ['doubanmoive.spiders']
NEWSPIDER_MODULE = 'doubanmoive.spiders'
ITEM_PIPELINES={
 'doubanmoive.mongo_pipelines.MongoDBPipeline':300,
 'doubanmoive.pipelines.DoubanmoivePipeline':400,
}
LOG_LEVEL='DEBUG'

DOWNLOAD_DELAY = 2
RANDOMIZE_DOWNLOAD_DELAY = True
USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_3) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.54 Safari/536.5'
COOKIES_ENABLED = True

MONGODB_SERVER = 'localhost'
MONGODB_PORT = 27017
MONGODB_DB = 'python'
MONGODB_COLLECTION = 'test'