python爬虫----（5. scrapy框架，综合应用及其他）

# -*- coding: utf-8 -*-

from scrapy import Item, Field


class MovieItem(Item):
    name = Field()
    year = Field()
    score = Field()
    director = Field()
    classification = Field()
    actor = Field()

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


class MovieSpider(CrawlSpider):
    name = "movie"
    allowed_domains = ["douban.com"]
    start_urls = (
        'http://movie.douban.com/top250',
    )
    # rules可以自定义urls的抓取
    rules = (
        # 这个Rule只是在start_urls的基础上查找urls，并不是数据抓取的具体页面
        Rule(SgmlLinkExtractor(allow=(r'http://movie.douban.com/top250\?start=\d+.*'))),
        # 这个Rule是具体数据抓取的页面地址，callback是回调函数，负责处理返回的response数据
        Rule(SgmlLinkExtractor(allow=(r'http://movie.douban.com/subject/\d+')), callback='parse_item'),
    )

    def parse_item(self, response):
        sel = Selector(response)
        item = MovieItem()
        # 此处选择还可使用 css(), re() 等。还可利用FireBug协助选取
        item['name'] = sel.xpath('//span[@property="v:itemreviewed"]/text()').extract()
        item['year'] = sel.xpath('//span[@class="year"]/text()').extract()
        item['score'] = sel.xpath('//strong[@class="ll rating_num"]/text()').extract()
        item['director'] = sel.xpath('//a[@rel="v:directedBy"]/text()').extract()
        item['classification'] = sel.xpath('//span[@property="v:genre"]/text()').extract()
        item['actor'] = sel.xpath('//a[@rel="v:starring"]/text()').extract()
        return item

# 将抓取的数据保存到数据库中，这里有两个版本
#一个是保存到MySQL数据库中
#另一个是保存到非关系型数据库MongoDB中