2021-10-10

python xpath爬取美女图片

import requests
from lxml import etree
#https://www.tupianzj.com/meinv/20210830/231951.html
q = input('请输入网址:')
global jpg_list ##申明获取的图片地址列表为全局变量
jpg_list = []
class tupianzj(object):
    def __init__(self):
        self.url = q
        self.headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 5.1; rv:5.0) Gecko/20100101 Firefox/5.0'
        }

    def get_data(self,url):
        res = requests.get(url,headers=self.headers)
        html = res.content
        return html

    def parse_data(self,html):
        parse_html = etree.HTML(html) ##解析为html格式
        image_list = parse_html.xpath('//*[@id="bigpicimg"]/@src') ##获取图片地址
        #print(image_list)
        jpg_list.extend(image_list) ##地址加到这
        #print(jpg_list)
        #print(image_list)
        p_list = parse_html.xpath('//*[@id="container"]/div/div/div[2]/div[2]/div[3]/ul/li[11]/a/@href') ##获取下一个url
        #print(p_list)
        next_url_list =['https://www.tupianzj.com/meinv/20210830/' + herf for herf in p_list] ##拼接url注意url不一样
        #print(next_url_list)
        for next_url in next_url_list:
            #print(next_url)
            return next_url

    def run(self):

        next_url = q
        while True:
            html = self.get_data(next_url)
            next_url = self.parse_data(html)
            #print(jpg_list)
            #print(next_url)
            #return jpg_list
            if next_url is None: ##判断url是否为空，是则停止
                print(jpg_list)
                break

        for i in jpg_list:
            dirname = i[54:64] + ".jpg" ##图片名称列表切片
            html2 = requests.get(url=i, headers=self.headers).content
            file = open(dirname, 'wb')
            file.write(html2)
            print("%s下载成功" % dirname)

if __name__ == '__main__':
    imageSpider = tupianzj()
    imageSpider.run()