爬的运用玉人不是全站链接 ，找到想下的爬虫mc我的世界正版下载套图直接点进去复制概况页的链接就好了 url = input("请输中计图概况页链接:") #运用颇为捉拿清扫颇为 try: #由于是异步函数以是需要用asyncio.run启动 asyncio.run(get_xq(url)) print(title) except: print("链接概况页剖析过错.........") print("局手下载实现,开始天生pdf.......") #调用图片转PDF函数 jpg_pdf(title)

至关于是代码我的世界模组下载盒子概况页的链接

需要径自下载的python库

requests

fake_useragent

xpath

PIL

下面有图片 打码是为了过审 ，这网站真的写真下载mc我的世界直装是正直的写真网站不是甚么老司机网站

import requests from fake_useragent import UserAgent from lxml import etree import os import aiohttp import asyncio from PIL import Image import shutil #取患上概况页全副图片函数 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) #图片问题 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("之后下载的套图问题:\n"+imgtitle) for i in imgurl: p += 1 tasks.append(down(i,imgtitle,p)) #取患上下一页的链接 next = "https://www.xgyw01.co" + tree.xpath(//div[@class="pagination"][1]//a[last()]/@href)[0] #辨此外条件 bool = tree.xpath(//div[@class="pagination"][1]//a[last()]/text())[0] #循环取患上所有页 while True: print("正在取患上"+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)) #辨此外条件 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}张下载实现") #写真图片转PDF函数 def jpg_pdf(filename): # 界说文件夹道路以及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工具并削减到列表中 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并吞实现,删除了缓存的的图片") shutil.rmtree(folder_path) print("整理实现") #主函数 if __name__ == __main__: #界说的公共恳求头 header = {"user-agent": UserAgent().random} #界说的保存道路（文件夹道路） dirdz = "这里输入保存的文件夹道路" #界说一个全局的问题保存文件名字 title = "" #爬取的网站是:https://www.xgyw01.co/，该爬虫爬的套图游戏辅助器(免费)是每一套图的链接，