這里爬取的是http://sc.chinaz.com/tag_tupian/OuMeiMeiNv.html網(wǎng)站
獻(xiàn)上歐美美女！！！！

            
              from lxml import etree
import urllib.request,os,time

class OuMeiSpider(object):
    def __init__(self,start_page,end_page):
        self.start_page = start_page
        self.end_page = end_page
        self.first_url = 'http://sc.chinaz.com/tag_tupian/OuMeiMeiNv.html'
        self.url = 'http://sc.chinaz.com/tag_tupian/OuMeiMeiNv_{}.html'
        self.headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36',}
    def get_request(self,page):
        #判斷使得否為第一頁(yè)
        if page == 1:
            url = self.first_url
        else:
            url = self.url.format(page)
        #構(gòu)建請(qǐng)求對(duì)象
        request = urllib.request.Request(url=url,headers=self.headers)
        return request

    def parse_content(self,content):
        #生成tree對(duì)象
        tree = etree.HTML(content)
        #圖片地址
        img_src_list = tree.xpath('//div[@id="container"]/div/div/a/img/@src2')
        # print(len(img_src))
        img_name_list = tree.xpath('//div[@id="container"]/div/div/a/img/@alt')
        #下載圖片
        for img_src in img_src_list:
            filename = img_name_list[img_src_list.index(img_src)] + '.' + img_src.split('.')[-1]
            dirname = 'oumei'
            print("正在下載%s-----"%filename)
            filepath = os.path.join(dirname,filename)
            #寫入圖片
            urllib.request.urlretrieve(img_src,filepath)
            print("結(jié)束下載%s-----" % filename)
            time.sleep(2)



    def run(self):
        for page in range(self.start_page,self.end_page+1):
            #拼接地址
            request = self.get_request(page)
            #發(fā)送請(qǐng)求得到響應(yīng)，并且將響應(yīng)直接轉(zhuǎn)化為內(nèi)容
            content = urllib.request.urlopen(request).read().decode('utf8')
            #解析內(nèi)容
            self.parse_content(content)



def main():
    start_page = int(input("請(qǐng)輸入起始頁(yè)"))
    end_page = int(input("請(qǐng)輸入終止頁(yè)"))
    obj = OuMeiSpider(start_page,end_page)
    obj.run()

if __name__ == '__main__':
    main()