Python 爬取必應(yīng)壁紙的實(shí)例講解

import re
import os
import requests
from time import sleep

headers = {
  "User-Agent": ("Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:64.0) "
          "Gecko/20100101 Firefox/64.0")
}

def get_index(resolution, index=1):
  url = f"https://bing.ioliu.cn/ranking?p={index}"
  res = requests.get(url, headers=headers)
  urls = re.findall('pic=(.*?)\\.jpg', res.text)
  _old_resolution = urls[1].split("_")[-1]
  return {url.split("/")[-1].replace(_old_resolution, resolution): url.replace(_old_resolution, resolution) + ".jpg"
      for url in urls}

def download_pic(pics):
  if os.path.exists('F:\\必應(yīng)壁紙'):
    pass
  else:
    os.mkdir('F:\\必應(yīng)壁紙')
    print('目錄創(chuàng)建成功')
  try:
    for pic_name, pic_url in pics.items():
      res = requests.get(pic_url, headers=headers)
      with open(f"F:\\必應(yīng)壁紙\\{pic_name}.jpg", mode="wb") as f:
        f.write(res.content)
      print(f"{pic_name} 下載完成")
  except Exception as e:
    print("下載出錯(cuò)", e)

def input_index():
  print("必應(yīng)壁紙下載工具, 本工具未經(jīng)資源站授權(quán).")
  print("僅做學(xué)習(xí)和交流之用, 隨時(shí)有可能停止維護(hù).")
  print("目前資源站收容頁數(shù)為87,當(dāng)前僅提供1920x1080分辨率下載")
  while True:
    sleep(0.1)
    index = input("請(qǐng)輸入要下載的頁數(shù)(Max=87):")
    try:
      if index == "Q":
        exit()
      index = 87 if int(index) > 87 else int(index)
      return index
    except ValueError:
      print("請(qǐng)輸入數(shù)字, 或輸入Q退出!")

def main():
  index = input_index()
  i = 1
  while i <= index:
    print(f"當(dāng)前第{i}頁,共需要下載{index}頁")
    pics = get_index("1920x1080", i)
    download_pic(pics)
    i += 1
  print("下載完成,將在3秒后關(guān)閉...")
  sleep(1)
  print("2")
  sleep(1)
  print("1")
  sleep(1)
  print("0")

if __name__ == '__main__':
  main()