利用爬虫代码美女写真套图下载转PDF保存

爬的不是全站链接，该爬虫爬的是每套图的链接，相当于是详情页的链接

需要单独下载的python库：

requests

fake_useragent

xpath

PIL

下面有图片 打码是为了过审，这网站真的是正经的写真网站不是什么老司机网站

import requests  
from fake_useragent import UserAgent
from lxml import etree
import os
import aiohttp
import asyncio
from PIL import Image
import shutil
#获取详情页全部图片函数
async def get_xq(url):
    #计数
    p=0
    tasks = []
    res = requests.get(url=url,headers=header)
    res.encoding="utf-8"
    res.close()
    tree = etree.HTML(res.text)
    #图片标题
    imgtitle = tree.xpath('//title/text()')[0]
    global title
    title = imgtitle
    #第一页的图片链接
    img = tree.xpath('//article//img/@src')
    imgurl = ["https://www.xgyw01.co" + i for i in img]
    print("当前下载的套图标题:\n"+imgtitle)
    for i in imgurl:
        p += 1
        tasks.append(down(i,imgtitle,p))
    #获取下一页的链接
    next = "https://www.xgyw01.co" + tree.xpath('//div[@class="pagination"][1]//a[last()]/@href')[0]
        #判断的条件
    bool = tree.xpath('//div[@class="pagination"][1]//a[last()]/text()')[0]
    #循环获取所有页
    while True:
        print("正在获取"+next)
        if bool == "下一页" or bool == "下页":
            res = requests.get(url=next, headers=header)
            res.encoding = "utf-8"
            res.close()
            tree = etree.HTML(res.text)
            img = tree.xpath('//article//img/@src')
            imgurl = ["https://www.xgyw01.co" + i for i in img]
            for i in imgurl:
                p += 1
                tasks.append(down(i,imgtitle,p))
        #判断的条件
            bool = tree.xpath('//div[@class="pagination"][1]//a[last()]/text()')[0]  
            if bool == "下一页" or bool == "下页":
                next = "https://www.xgyw01.co" + tree.xpath('//div[@class="pagination"][1]//a[last()]/@href')[0]
                continue
            else:
                break
        else:
            break
    print("开始异步下载图片.....")
    await asyncio.wait(tasks)
#下载函数
async def down(url,filename,fn):
    filepath = os.path.join(dirdz,filename)
    if not os.path.exists(filepath):
        os.mkdir(filepath)
    async with aiohttp.ClientSession() as session:
        async with session.get(url) as res:
            with open(filepath+"/"+str(fn)+".jpg",mode="wb") as f:
                f.write(await res.content.read())
                print(f"第{fn}张下载完成")
#写真图片转PDF函数       
def jpg_pdf(filename):
    # 定义文件夹路径和PDF文件名
    folder_path = os.path.join(dirdz,filename)
    pdf_filename = os.path.join(dirdz,filename + ".pdf")
    # # 将JPEG文件转换为Pillow Image对象并添加到列表中
    image_files = [os.path.join(folder_path, f) for f in os.listdir(folder_path) if f.endswith('.jpeg') or f.endswith('.jpg')]
    image_list = []
    for file_path in image_files:
        img = Image.open(os.path.abspath(file_path))
        image_list.append(img)
    # 找到所有JPEG文件
    image_list[0].save(pdf_filename, "PDF" ,resolution=100.0, save_all=True, append_images=image_list[1:])
    print("pdf合并完成,删除缓存的的图片")
    shutil.rmtree(folder_path)
    print("清理完成")
#主函数   
if __name__ == '__main__':
    #定义的公共请求头
    header = {"user-agent": UserAgent().random}
    #定义的保存路径（文件夹路径）
    dirdz = "这里输入保存的文件夹路径"
    #定义一个全局的标题保存文件名字
    title = ""
    #爬取的网站是:https://www.xgyw01.co/，找到想下的套图直接点进去复制详情页的链接就行了
    url = input("请输入套图详情页链接:")
    #使用异常捕获排除异常
    try:
        #因为是异步函数所以需要用asyncio.run启动
        asyncio.run(get_xq(url))
        print(title)
    except:
        print("链接详情页解析错误.........")
    print("全部下载完成,开始生成pdf.......")
    #调用图片转PDF函数
    jpg_pdf(title)