小圖片下載

#coding=utf-8
import requests
from lxml import etree
import sys
reload(sys)
sys.setdefaultencoding('utf-8')

url_start = 'http://www.xxxxxx.com/yyy/'
url_base = 'http://www.xxxxx.com'
for page in range(1,208):
    if page==1:
        url  = url_start+'7.html'
    else:
        url = url_start+'7-'+str(page)+'.html'
    print url
    url_lists = requests.get(url).text
    print url_lists
    selector = etree.HTML(url_lists)
    content_lists = selector.xpath('//div[@class="art"]/ul/li')
    print content_lists
    for each_url in content_lists:
        imgs_url = url_base + each_url.xpath('a/@href')[0]
        html = requests.get(imgs_url).text
        selector = etree.HTML(html)
        content = selector.xpath('//div[@class="artbody imgbody"]/p')
        for each in content:
            imgs = each.xpath('img/@src')[0]
            headers = { "Accept":"text/html,application/xhtml+xml,application/xml;",
                    "Accept-Encoding":"gzip",
                    "Accept-Language":"zh-CN,zh;q=0.8",
                    "Referer":"http://www.example.com/",
                    "User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36"
                    }
            r = requests.get(imgs,headers=headers)
            img_name = imgs.split('/')[-1]
            with open("./imgs/"+img_name, "wb") as code:
                code.write(r.content)