Scrapy爬取豆瓣电影top250的电影数据、海报，MySQL存储

从GitHub得到完整项目（https://github.com/daleyzou/douban.git）

1、成果展示

数据库

本地海报图片

2、环境

（1）已安装Scrapy的Pycharm

(2)mysql

（3）连上网络的电脑

3、实体类设计

4、代码

items.py

 class DoubanItem(scrapy.Item):
     title = scrapy.Field()
     bd = scrapy.Field()
     star = scrapy.Field()
     quote = scrapy.Field()
     img_url = scrapy.Field()
     pic_path = scrapy.Field()

doubanmovie.py(爬虫类)

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

 # noinspection PyUnresolvedReferences
 from douban.items import DoubanItem
 import sys
 reload(sys)
 sys.setdefaultencoding('utf-8')

 class DoubanmovieSpider(scrapy.Spider):
     name = 'doubanmovie'
     allowed_domains = ['douban.com']
     offset = 0
     url = "https://movie.douban.com/top250?start="
     start_urls = [url + str(offset),]

     def parse(self, response):
         item = DoubanItem()
         movies = response.xpath("//div[ @class ='info']")
         links = response.xpath("//div[ @class ='pic']//img/@src").extract()
         for (each, link) in zip(movies,links):
             # 标题
             item['title'] = each.xpath('.//span[@class ="title"][1]/text()').extract()[0]
             # 信息
             item['bd'] = each.xpath('.//div[@ class ="bd"][1]/p/text()').extract()[0]
             # 评分
             item['star'] = each.xpath('.//div[@class ="star"]/span[@ class ="rating_num"]/text()').extract()[0]
             # 简介
             quote = each.xpath('.//p[@ class ="quote"] / span / text()').extract()
             # quote可能为空，因此需要先进行判断
             if quote:
                 quote = quote[0]
             else:
                 quote = ''
             item['quote'] = quote
             item['img_url'] = link

             yield item
         if self.offset < 225:
             self.offset += 25
             yield scrapy.Request(self.url+str(self.offset), callback=self.parse)
 

pipelines.py

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

 import MySQLdb

 from scrapy import Request
 from scrapy.pipelines.images import ImagesPipeline

 class DoubanPipeline(object):

     def __init__(self):
         self.conn = MySQLdb.connect(host='localhost', port=3306, db='douban', user='root', passwd='root', charset='utf8')
         self.cur = self.conn.cursor()

     def process_item(self, item, spider):
         print '--------------------------------------------'
         print item['title']
         print '--------------------------------------------'
         try:
             sql = "INSERT IGNORE INTO doubanmovies(title,bd,star,quote_mv,img_url) VALUES(\'%s\',\'%s\',%f,\'%s\',\'%s\')" %(item['title'], item['bd'], float(item['star']), item['quote'], item['title']+".jpg")
             self.cur.execute(sql)
             self.conn.commit()
         except Exception, e:
             print "----------------------inserted faild!!!!!!!!-------------------------------"
             print e.message
         return item

     def close_spider(self, spider):
         print '-----------------------quit-------------------------------------------'
         # 关闭数据库连接
         self.cur.close()
         self.conn.close()

 # 下载图片
 class DownloadImagesPipeline(ImagesPipeline):
     def get_media_requests(self, item, info):
         image_url = item['img_url']
         # 添加meta是为了下面重命名文件名使用
         yield Request(image_url,meta={'title': item['title']})

     def file_path(self, request, response=None, info=None):
         title = request.meta['title']  # 通过上面的meta传递过来item
         image_guid = request.url.split('.')[-1]
         filename = u'{0}.{1}'.format(title, image_guid)
         print '++++++++++++++++++++++++++++++++++++++++++++++++'
         print filename
         print '++++++++++++++++++++++++++++++++++++++++++++++++'
         return filename

middlewares.py

 import random
 import base64
 from settings import USER_AGENTS
 from settings import PROXIES

 class RandomUserAgent(object):
     def process_request(self, request, spider):
         useragent = random.choice(USER_AGENTS)
         request.headers.setdefault("User-Agent",useragent)

 class RandomProxy(object):
     def process_request(self, request, spider):
         proxy = random.choice(PROXIES)
         print '---------------------'
         print proxy
         if proxy['user_passwd'] is None:
             # 如果没有代理账户验证
             request.meta['proxy'] = "http://" + proxy['ip_port']
         else:
             base64_userpasswd = base64.b64encode(proxy['user_passwd'])
             # 对账户密码进行base64编码转换
             request.meta['proxy'] = "http://" + proxy['ip_port']
             # 对应到代理服务器的信令格式里
             request.headers['Proxy-Authorization'] = 'Basic '+ base64_userpasswd
 

解释HTTP代理使用base64编码

为什么HTTP代理要使用base64编码：

HTTP代理的原理很简单，就是通过HTTP协议与代理服务器建立连接，
协议信令中包含要连接到的远程主机的IP和端口号，如果有需要身份验证的话还需要加上授权信息，
服务器收到信令后首先进行身份验证，通过后便与远程主机建立连接，连接成功之后会返回给客户端200，
表示验证通过，就这么简单，下面是具体的信令格式：

CONNECT 59.64.128.198:21 HTTP/1.1
Host: 59.64.128.198:21
Proxy-Authorization: Basic bGV2I1TU5OTIz
User-Agent: OpenFetion

其中Proxy-Authorization是身份验证信息，
Basic后面的字符串是用户名和密码组合后进行base64编码的结果，
也就是对username:password进行base64编码。

HTTP/1.0 200 Connection established

OK，客户端收到收面的信令后表示成功建立连接，
接下来要发送给远程主机的数据就可以发送给代理服务器了，
代理服务器建立连接后会在根据IP地址和端口号对应的连接放入缓存，
收到信令后再根据IP地址和端口号从缓存中找到对应的连接，将数据通过该连接转发出去。

settings.py

 USER_AGENTS = [
 'Mozilla/5.0 (Windows; U; Windows NT 5.2) Gecko/2008070208 Firefox/3.0.1',
 'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070309 Firefox/2.0.0.3',
 'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070803 Firefox/1.5.0.12',
 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0)',
 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.2)',
 'Opera/9.27 (Windows NT 5.2; U; zh-cn)',
 'Opera/8.0 (Macintosh; PPC Mac OS X; U; en)',
 'Mozilla/5.0 (Macintosh; PPC Mac OS X; U; en) Opera 8.0 ',
 'Mozilla/5.0 (Windows; U; Windows NT 5.2) AppleWebKit/525.13 (KHTML, like Gecko) Version/3.1 Safari/525.13',
 'Mozilla/5.0 (iPhone; U; CPU like Mac OS X) AppleWebKit/420.1 (KHTML, like Gecko) Version/3.0 Mobile/4A93 Safari/419.3',
 'Mozilla/5.0 (Linux; U; Android 4.0.3; zh-cn; M032 Build/IML74K) AppleWebKit/534.30 (KHTML, like Gecko) Version/4.0 Mobile Safari/534.30'
 ]

 PROXIES = [
    {"ip_port":"202.103.14.155:8118","user_passwd":""},
    {"ip_port":"110.73.11.21:8123","user_passwd":""}
 ]
 # 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.html
 ITEM_PIPELINES = {
    'douban.pipelines.DoubanPipeline': 1,
    'douban.pipelines.DownloadImagesPipeline': 100
 }

IMAGES_STORE = 'D:\Python\Scrapy\douban\Images'

5、运行

(1)打开本地MySQL数据库

（2）创建一个douban的数据库，并新建一个doubanmovie的表

（3）更改代码中连接到数据库代码中的端口、用户名、密码

（4）切换到项目目录下的/douban/douban/spiders中

（5）运行scrapy crawl doubanmovie

作者：Daley Zou

出处：http://www.cnblogs.com/daleyzou/p/8325857.html