python初学爬虫校花图片（内存有点不足啊，直接看源码)

本文来源吾爱破解论坛

import string
import urllib

import requests
from lxml import etree

url = "http://www.xiaohuar.com/hua/"
proxies = {
    # 'http':'http://183.196.170.247:9000/',
    # "http": "111.29.3.190:80"
}
headers = {

    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.90 Safari/537.36"
}

rep = requests.get(url, headers=headers, proxies=proxies)
html_content = rep.content.decode(encoding='gb2312')
# print(html_content)
dom = etree.HTML(html_content)
# xh_photos_href = dom.xpath('//div[@id="list_img"]//div[@class="img"]/a/@href')
# http://www.xiaohuar.com/
xh_photos_src = dom.xpath('//div[@id="list_img"]//div[@class="img"]/a/img/@src')
xh_photos_info = dom.xpath('//div[@id="list_img"]//a/img/@alt')
# 下一页
xh_photos_href = dom.xpath('//body//div[@id="list_img"]//div[@id="page"]/div/a/@href')
# 判断尾页
xh_photos_a_text = dom.xpath('//body//div[@id="list_img"]//div[@id="page"]/div/a/text()')
print(xh_photos_a_text[-2])
i = 1
while xh_photos_a_text[-2] == '下一页':
    for url, alt_info in zip(xh_photos_src, xh_photos_info):
        # img_url=c.strip('//')
        src_name = url.split('.')
        print(src_name)
        img_name = alt_info + '.' + src_name[-1]
        print(img_name)
        url = 'http://www.xiaohuar.com/' + url
        url = urllib.parse.quote(url, safe=string.printable)
        rep = requests.get(url, headers=headers)
        with open(r'I:\Pchong\pc_image\flowers\\' + img_name.replace("/", "_"), 'wb')as f:
            f.write(rep.content)
            print('图片保存完毕！！')
    print('-------第' + str(i) + '图片爬取完毕---------')
    i += 1

    print("下一页地址：",xh_photos_href[-2])
    print("下一页地址：",xh_photos_href)
    rep = requests.get(xh_photos_href[-2], headers=headers, proxies=proxies)
    html_content = rep.content.decode(encoding='gbk')
    # print(html_content)
    dom = etree.HTML(html_content)
    # xh_photos_href = dom.xpath('//div[@id="list_img"]//div[@class="img"]/a/@href')
    # http://www.xiaohuar.com/
    xh_photos_src = dom.xpath('//div[@id="list_img"]//div[@class="img"]/a/img/@src')
    xh_photos_info = dom.xpath('//div[@id="list_img"]//a/img/@alt')
    # 下一页
    xh_photos_href = dom.xpath('//body//div[@id="list_img"]//div[@id="page"]/div/a/@href')
    # 判断尾页
    xh_photos_a_text = dom.xpath('//body//div[@id="list_img"]//div[@id="page"]/div/a/text()')

1582338980(1).jpg (145.18 KB, 下载次数: 1)

下载附件  保存到相册

2020-2-22 10:37 上传

image.png (1010 Bytes, 下载次数: 0)

下载附件  保存到相册

2020-2-22 10:38 上传