使用requests下载彼岸图W高清图片到本地

requests_pic_netbian_com.py

#!/usr/bin/env python3
# coding=utf-8
# Version:python3.6.1
# File:requests_pic_netbian_com.py
# Author:LGSP_Harold
import requests
from lxml import etree

headers = {
    'authority': 'pic.netbian.com',
    'method': 'GET',
    'path': '/4kmeinv/',
    'scheme': 'https',
    'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
    'accept-encoding': 'gzip, deflate, br',
    'accept-language': 'zh-CN,zh;q=0.9',
    'cache-control': 'no-cache',
    'dnt': '1',
    'pragma': 'no-cache',
    'referer': 'https://pic.netbian.com/4kqiche/',
    'upgrade-insecure-requests': '1',
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36',
}


def down_img(page_obj):
    items = page_obj.xpath('//div[@class="slist"]//li/a/@href')
    for item in items:
        detail_url = 'https://pic.netbian.com' + item
        detail_response = requests.get(url=detail_url, headers=headers)
        detail_response.encoding = 'gbk'
        detail_obj = etree.HTML(detail_response.text)

        detail_title = detail_obj.xpath('//div[@class="photo-hd"]/h1/text()')[0]
        file_path = './imgs/netbian_com/' + detail_title + '.jpg'
        img_src = 'https://pic.netbian.com' + \
                  detail_obj.xpath('//div[@class="photo-pic"]/a[@id="img"]/img/@src')[0]
        img_response = requests.get(url=img_src)
        if img_response.status_code == 522:
            print('%s图片不存在' % detail_title)
            continue
        with open(file_path, 'wb') as f:
            f.write(img_response.content)
        print('%s图片成功下载' % detail_title)


for page in range(1, 9):
    if page == 1:
        url = 'https://pic.netbian.com/4kmeinv/'
    else:
        url = 'https://pic.netbian.com/4kmeinv' + '/index_' + str(page) + '.html'
    response = requests.get(url=url, headers=headers)
    page_obj = etree.HTML(response.text)
    down_img(page_obj)