Xpath-彼岸图网高清图片获取_彼岸图网原图真实链接

Xpath-彼岸图网高清图片获取

目标网站：彼岸图网

首先导入所需包

import os
import time

import requests
from lxml import etree
1
2
3
4
5

做好伪装(F12获取信息)

headers = {
    'User-Agent': '',
    'Referer': '',
    'Cookie': ''
}
1
2
3
4
5

获取总页数(非固定)

# 获取总页数
def get_last_page():
    response = requests.get('http://pic.netbian.com/', headers=headers)
    response.encoding = "GBK"
    html = etree.HTML(response.text)
    last_page = html.xpath('//div[@class="page"]/a[10]/text()')
    last = ''.join(last_page)
    print("本站一共有{0}页\n".format(last))
    return last
1
2
3
4
5
6
7
8
9

由于彼岸图网的高清图片需要在进入一个网页才能拿到，所以先获取小图链接

首页的链接并不规则，须单独设置

def get_main_page():

    last = get_last_page()
    for page in range(1, int(last) + 1):
        print('\n第{0}页'.format(page))
        if page == 1:
            url = 'http://pic.netbian.com/'
        else:
            url = 'http://pic.netbian.com//index_{0}.html'.format(page)
        response = requests.get(url, headers=headers)
        response.encoding = "GBK"

        if response.status_code == 200:
            html = etree.HTML(response.text)
            biglink_list = html.xpath('//div[@class="slist"]//li/a/@href')
            for link in biglink_list:
                get_img_link('http://pic.netbian.com/'+link)
    return biglink_list
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18

进一步访问小图链接，解析高清图链并输出图片名称和链接

# 获取高清图链接
def get_img_link(link):
    global pic_sum
    try:
        response = requests.get(link, headers=headers)
        response.encoding = "GBK"

        if response.status_code == 200:
            html = etree.HTML(response.text)
            img_list = html.xpath('//div[@class="photo-pic"]/a/img/@src')
            title_list = html.xpath('//div[@class="photo-pic"]/a/img/@title')

            for title, img in zip(title_list, img_list):
                pic_sum = pic_sum+1
                print('{0}:{1}
声明：本文内容由网友自发贡献，不代表【wpsshop博客】立场，版权归原作者所有，本站不承担相应法律责任。如您发现有侵权的内容，请联系我们。转载请注明出处：https://www.wpsshop.cn/w/weixin_40725706/article/detail/460848