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
1 class DoubanItem(scrapy.Item): 2 title = scrapy.Field() 3 bd = scrapy.Field() 4 star = scrapy.Field() 5 quote = scrapy.Field() 6 img_url = scrapy.Field() 7 pic_path = scrapy.Field()
doubanmovie.py(爬虫类)
1 # -*- coding: utf-8 -*- 2 import scrapy 3 4 # noinspection PyUnresolvedReferences 5 from douban.items import DoubanItem 6 import sys 7 reload(sys) 8 sys.setdefaultencoding('utf-8') 9 10 11 class DoubanmovieSpider(scrapy.Spider): 12 name = 'doubanmovie' 13 allowed_domains = ['douban.com'] 14 offset = 0 15 url = "https://movie.douban.com/top250?start=" 16 start_urls = [url + str(offset),] 17 18 def parse(self, response): 19 item = DoubanItem() 20 movies = response.xpath("//div[ @class ='info']") 21 links = response.xpath("//div[ @class ='pic']//img/@src").extract() 22 for (each, link) in zip(movies,links): 23 # 标题 24 item['title'] = each.xpath('.//span[@class ="title"][1]/text()').extract()[0] 25 # 信息 26 item['bd'] = each.xpath('.//div[@ class ="bd"][1]/p/text()').extract()[0] 27 # 评分 28 item['star'] = each.xpath('.//div[@class ="star"]/span[@ class ="rating_num"]/text()').extract()[0] 29 # 简介 30 quote = each.xpath('.//p[@ class ="quote"] / span / text()').extract() 31 # quote可能为空,因此需要先进行判断 32 if quote: 33 quote = quote[0] 34 else: 35 quote = '' 36 item['quote'] = quote 37 item['img_url'] = link 38 39 yield item 40 if self.offset < 225: 41 self.offset += 25 42 yield scrapy.Request(self.url+str(self.offset), callback=self.parse) 43
pipelines.py
1 # -*- coding: utf-8 -*- 2 3 import MySQLdb 4 5 6 from scrapy import Request 7 from scrapy.pipelines.images import ImagesPipeline 8 9 10 class DoubanPipeline(object): 11 12 def __init__(self): 13 self.conn = MySQLdb.connect(host='localhost', port=3306, db='douban', user='root', passwd='root', charset='utf8') 14 self.cur = self.conn.cursor() 15 16 def process_item(self, item, spider): 17 print '--------------------------------------------' 18 print item['title'] 19 print '--------------------------------------------' 20 try: 21 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") 22 self.cur.execute(sql) 23 self.conn.commit() 24 except Exception, e: 25 print "----------------------inserted faild!!!!!!!!-------------------------------" 26 print e.message 27 return item 28 29 def close_spider(self, spider): 30 print '-----------------------quit-------------------------------------------' 31 # 关闭数据库连接 32 self.cur.close() 33 self.conn.close() 34 35 36 # 下载图片 37 class DownloadImagesPipeline(ImagesPipeline): 38 def get_media_requests(self, item, info): 39 image_url = item['img_url'] 40 # 添加meta是为了下面重命名文件名使用 41 yield Request(image_url,meta={'title': item['title']}) 42 43 def file_path(self, request, response=None, info=None): 44 title = request.meta['title'] # 通过上面的meta传递过来item 45 image_guid = request.url.split('.')[-1] 46 filename = u'{0}.{1}'.format(title, image_guid) 47 print '++++++++++++++++++++++++++++++++++++++++++++++++' 48 print filename 49 print '++++++++++++++++++++++++++++++++++++++++++++++++' 50 return filename 51 52 53
middlewares.py
1 import random 2 import base64 3 from settings import USER_AGENTS 4 from settings import PROXIES 5 6 class RandomUserAgent(object): 7 def process_request(self, request, spider): 8 useragent = random.choice(USER_AGENTS) 9 request.headers.setdefault("User-Agent",useragent) 10 11 12 class RandomProxy(object): 13 def process_request(self, request, spider): 14 proxy = random.choice(PROXIES) 15 print '---------------------' 16 print proxy 17 if proxy['user_passwd'] is None: 18 # 如果没有代理账户验证 19 request.meta['proxy'] = "http://" + proxy['ip_port'] 20 else: 21 base64_userpasswd = base64.b64encode(proxy['user_passwd']) 22 # 对账户密码进行base64编码转换 23 request.meta['proxy'] = "http://" + proxy['ip_port'] 24 # 对应到代理服务器的信令格式里 25 request.headers['Proxy-Authorization'] = 'Basic '+ base64_userpasswd 26
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
1 USER_AGENTS = [ 2 'Mozilla/5.0 (Windows; U; Windows NT 5.2) Gecko/2008070208 Firefox/3.0.1', 3 'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070309 Firefox/2.0.0.3', 4 'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070803 Firefox/1.5.0.12', 5 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0)', 6 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.2)', 7 'Opera/9.27 (Windows NT 5.2; U; zh-cn)', 8 'Opera/8.0 (Macintosh; PPC Mac OS X; U; en)', 9 'Mozilla/5.0 (Macintosh; PPC Mac OS X; U; en) Opera 8.0 ', 10 'Mozilla/5.0 (Windows; U; Windows NT 5.2) AppleWebKit/525.13 (KHTML, like Gecko) Version/3.1 Safari/525.13', 11 'Mozilla/5.0 (iPhone; U; CPU like Mac OS X) AppleWebKit/420.1 (KHTML, like Gecko) Version/3.0 Mobile/4A93 Safari/419.3', 12 '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' 13 ] 14 15 PROXIES = [ 16 {"ip_port":"202.103.14.155:8118","user_passwd":""}, 17 {"ip_port":"110.73.11.21:8123","user_passwd":""} 18 ] 19 # Enable or disable extensions 20 # See https://doc.scrapy.org/en/latest/topics/extensions.html 21 #EXTENSIONS = { 22 # 'scrapy.extensions.telnet.TelnetConsole': None, 23 #} 24 25 # Configure item pipelines 26 # See https://doc.scrapy.org/en/latest/topics/item-pipeline.html 27 ITEM_PIPELINES = { 28 'douban.pipelines.DoubanPipeline': 1, 29 'douban.pipelines.DownloadImagesPipeline': 100 30 }
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