# -*- coding: utf-8 -*-
import scrapy       #导入爬虫模块
from scrapy.selector import HtmlXPathSelector  #导入HtmlXPathSelector模块
from urllib import request                     #导入request模块
import osclass AdcSpider(scrapy.Spider):name = 'adc'                                        #设置爬虫名称allowed_domains = ['www.shaimn.com']start_urls = ['http://www.shaimn.com/xinggan/']def parse(self, response):hxs = HtmlXPathSelector(response)               #创建HtmlXPathSelector对象，将页面返回对象传进去
items = hxs.select('//div[@class="showlist"]/li')  #标签选择器，表示获取所有class等于showlist的div，下面的li标签print(items)                                       #返回标签对象

# -*- coding: utf-8 -*-
import scrapy       #导入爬虫模块
from scrapy.selector import HtmlXPathSelector  #导入HtmlXPathSelector模块
from urllib import request                     #导入request模块
import osclass AdcSpider(scrapy.Spider):name = 'adc'                                        #设置爬虫名称allowed_domains = ['www.shaimn.com']start_urls = ['http://www.shaimn.com/xinggan/']def parse(self, response):hxs = HtmlXPathSelector(response)               #创建HtmlXPathSelector对象，将页面返回对象传进去
items = hxs.select('//div[@class="showlist"]/li')  #标签选择器，表示获取所有class等于showlist的div，下面的li标签# print(items)                                     #返回标签对象for i in range(len(items)):                        #根据li标签的长度循环次数title = hxs.select('//div[@class="showlist"]/li[%d]//img/@alt' % i).extract()   #根据循环的次数作为下标获取到当前li标签，下的img标签的alt属性内容src = hxs.select('//div[@class="showlist"]/li[%d]//img/@src' % i).extract()     #根据循环的次数作为下标获取到当前li标签，下的img标签的src属性内容if title and src:print(title,src)  #返回类容列表

# -*- coding: utf-8 -*-
import scrapy       #导入爬虫模块
from scrapy.selector import HtmlXPathSelector  #导入HtmlXPathSelector模块
from urllib import request                     #导入request模块
import osclass AdcSpider(scrapy.Spider):name = 'adc'                                        #设置爬虫名称allowed_domains = ['www.shaimn.com']start_urls = ['http://www.shaimn.com/xinggan/']def parse(self, response):hxs = HtmlXPathSelector(response)               #创建HtmlXPathSelector对象，将页面返回对象传进去
items = hxs.select('//div[@class="showlist"]/li')  #标签选择器，表示获取所有class等于showlist的div，下面的li标签# print(items)                                     #返回标签对象for i in range(len(items)):                        #根据li标签的长度循环次数title = hxs.select('//div[@class="showlist"]/li[%d]//img/@alt' % i).extract()   #根据循环的次数作为下标获取到当前li标签，下的img标签的alt属性内容src = hxs.select('//div[@class="showlist"]/li[%d]//img/@src' % i).extract()     #根据循环的次数作为下标获取到当前li标签，下的img标签的src属性内容if title and src:# print(title[0],src[0])                                                    #通过下标获取到字符串内容file_path = os.path.join(os.getcwd() + '/img/', title[0] + '.jpg')          #拼接图片保存路径request.urlretrieve(src[0], file_path)                          #将图片保存到本地，参数1获取到的src，参数2保存路径

# -*- coding: utf-8 -*-
import scrapy       #导入爬虫模块
from scrapy.selector import HtmlXPathSelector  #导入HtmlXPathSelector模块
from scrapy.selector import Selectorclass AdcSpider(scrapy.Spider):name = 'adc'                                        #设置爬虫名称allowed_domains = ['www.shaimn.com']start_urls = ['http://www.shaimn.com/xinggan/']def parse(self, response):items = Selector(response=response).xpath('//div[@class="showlist"]/li').extract()# print(items)                                     #返回标签对象for i in range(len(items)):title = Selector(response=response).xpath('//div[@class="showlist"]/li[%d]//img/@alt' % i).extract()src = Selector(response=response).xpath('//div[@class="showlist"]/li[%d]//img/@src' % i).extract()print(title,src)

# -*- coding: utf-8 -*-
import scrapy       #导入爬虫模块
from scrapy.selector import HtmlXPathSelector  #导入HtmlXPathSelector模块
from scrapy.selector import Selectorclass AdcSpider(scrapy.Spider):name = 'adc'                                        #设置爬虫名称allowed_domains = ['www.shaimn.com']start_urls = ['http://www.shaimn.com/xinggan/']def parse(self, response):items = Selector(response=response).xpath('//div[@class="showlist"]/li//img')[0].extract()print(items)                                     #返回标签对象items2 = Selector(response=response).xpath('//div[@class="showlist"]/li//img')[0].re('alt="(\w+)')print(items2)# <img src="http://www.shaimn.com/uploads/170724/1-1FH4221056141.jpg" alt="人体艺术mmSunny前凸后翘性感诱惑写真">
# ['人体艺术mmSunny前凸后翘性感诱惑写真']

# -*- coding: utf-8 -*-
import scrapy       #导入爬虫模块
from scrapy.selector import HtmlXPathSelector  #导入HtmlXPathSelector模块
from scrapy.selector import Selectorclass AdcSpider(scrapy.Spider):name = 'adc'                                        #设置爬虫名称allowed_domains = ['www.shaimn.com']start_urls = ['http://www.shaimn.com/xinggan/']def parse(self, response):items = Selector(response=response).xpath('//div').extract()# print(items)                                     #返回标签对象items2 = Selector(response=response).xpath('//div[re:test(@class, "showlist")]').extract()  #正则找到div的class等于showlist的元素print(items2)