爬取图片

import urllib.request
from lxml import etree
from urllib import parse

class Image():
    def __init__(self,url):
        self.url = url
        self.headers = {"User-Agent" : "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11"}

    def loadPage(self):
        request = urllib.request.Request(self.url,headers=self.headers)
        html = urllib.request.urlopen(request).read().decode()
        content = etree.HTML(html)
        link_list = content.xpath('//div[@class="main wrap"]/div/div/div/div/a/@href')
        for link in link_list:
            if link[-4:] == "html":
                fullurl = self.url + link[-11:]
                self.loadImag(fullurl)

    def loadImag(self,url):
        #print(url)
        headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36"}
        request = urllib.request.Request(url, headers=headers)
        html = urllib.request.urlopen(request).read().decode()
#//div[@class="detail"]/p/a/img/@src
        content = etree.HTML(html)
        link_list = content.xpath('//div[@class="detail"]/p/a/img/@src')
        print(link_list)
        for link in link_list:
            self.writeImage(link)

    def writeImage(self,link):
        request = urllib.request.Request(link, headers=self.headers)
        #由于下载图片所以不用进行转码
        image = urllib.request.urlopen(request).read()
        filename = link[-10:]
        with open(filename,"wb") as f:
            f.write(image)
        print("download...%s"%filename)





if __name__ == "__main__":
     url = "http://www.neihanpa.com/pic/"
     print(url)
     img = Image(url)
     img.loadPage()