一些我用得到的 Python 脚本

原创

猫猫摸大鱼

修改于 2022-07-21 12:48:15

68100

代码可运行

文章被收录于专栏：摸鱼摸鱼

运行总次数：0

代码可运行

下面的python脚本有一部分是我百度然后修改的，一部分是我自己写的，如果以后有什么新的我用的到的脚本或者这些脚本有修改我也会在这里更新，这些源码放在这里仅以备份为目的

把图片上传到 sm.ms 图床

sm.ms.py

# coding=utf-8

from time import sleep
import requests, os

url = "https://sm.ms/api/v2/upload"
headers = {
    'Connection': 'close',
    'Authorization': 'key' #此处填写sm.ms图床的token
    }


files_path = r'C:\Users\Administrator\Desktop\pic'
ufile = r'C:\Users\Administrator\Desktop\url.txt'
hfile = r'C:\Users\Administrator\Desktop\hash.txt'
dfile = r'C:\Users\Administrator\Desktop\done.txt'

while True:
    try:
        pfiles = os.listdir(files_path) #遍历文件
        for file in pfiles:
            fpath = os.path.join(files_path, file)
            print('开始上传' + fpath)
            pic = open(fpath, 'rb')
            files = {
                'smfile': pic #读取文件
                }
            r = requests.post(url, headers=headers, files=files, timeout=60)  #上传
            print(r.status_code)
            pic.close()
            r.encoding = 'utf-8'
            print(r.json())
            t = fpath + "_inurl_" + r.json()['data']['url'] + "\n" #文件名+url
            pichash = r.json()['data']['hash']
            with open(ufile,"a") as f: #写入文档
                f.write(t)
                f.close()
            print(t)
            with open(hfile,"a") as f:
                f.write(pichash + "\n")
                f.close()
            print("图片哈希为" + pichash)
            with open(dfile,"a") as f:
                f.write(file + "\n")
                f.close()
            print("图片信息保存完成" + "\n")
            sleep(5)
    except:
        print("程序出错了,开始删除本地已上传的文件" + "\n")
        with open(dfile, "r+") as f:
            for fname in f:
                fpath = os.path.join(files_path, fname)
                fpath = fpath[:-1]
                os.remove(fpath)
                print("已删除" + fpath)
            f.truncate(0)
            f.close()
        print("文件删除完成,900秒后重试上传" + "\n")
        sleep(900)

已知图片API的URL的情况下批量下载图片

picdl.py

# coding=utf-8
 
import requests
 
filepath = 'E:/acg/acg/' #图片存放的地址
i = 1
 
#将图片URL存放在 E:\acg\acgurl.txt 中
with open(r'E:\acg\acgurl.txt','r',encoding= 'UTF-8')as f:
    for url in f:
 
        r = requests.request('get',url)  #get请求
        print(r.status_code)
    
        with open(filepath+str('acgpic')+str(i)+'.jpg','wb') as p: #打开写入到path路径里的二进制文件
            p.write(r.content)  #写入r对象的二进制文件
        p.close()   
        i += 1

图片 MD5 去重

quchong.py

# coding=utf-8
 
import os
import hashlib
 
filedir = 'E:\\acg\\acg'
 
def filecount(DIR):
    filecount = len([name for name in os.listdir(DIR) if os.path.isfile(os.path.join(DIR, name))])
    return (filecount)
 
 
def md5sum(filename):
    f = open(filedir+'/'+filename, 'rb')
    md5 = hashlib.md5()
    while True:
        fb = f.read(8096)
        if not fb:
            break
        md5.update(fb)
    f.close()
    return (md5.hexdigest())
 
 
def delfile():
    all_md5 = {}
    dir =os.walk(filedir)
    for i in dir:
        for tlie in i[2]:
 
            if md5sum(tlie) in all_md5.values():
                os.remove(filedir+'/'+tlie)
                print(tlie)
            else:
                all_md5[tlie] = md5sum(tlie)
 
 
if __name__ == '__main__':
    oldf = filecount(filedir)
    print('去重前有', oldf, '个文件\n请稍等正在删除重复文件...')
    delfile()
    print('\n\n去重后剩', filecount(filedir), '个文件')
    print('\n\n一共删除了', oldf - filecount(filedir), '个文件\n\n')

将图片按分辨率归类，将尺寸大小相同的图片放在一个新文件夹当中

size.py

# coding=utf-8
 
import os
import shutil
from PIL import Image
 
 
files_path = r'E:\acg\acg'


#定义一个分类函数，函数括号中为需要分类的图片文件夹路径
def photo_classify(files_path):
    # 读取文件夹中所有文件的名称
    files_list = os.listdir(files_path)
 
    # 循环文件夹中的所有文件
    for photo in files_list:
 
        # 获取图片的绝对路径
        photo_abspath = os.path.join(files_path, photo)
        print(photo_abspath)
 
        # 判断photo是不是文件夹，若是文件夹则跳过，若不是文件夹则继续执行
        if os.path.isdir(photo_abspath):
            continue
        else:
            print(photo_abspath)
            # 读图片的尺寸
            img = Image.open(photo_abspath)
 
            weight = img.size[0]
            high = img.size[1]
 
            print(weight)
            print(high)
 
            # 判断新文件夹是否存在，若不存在，则新建文件夹，若存在，则将图片复制到文件夹中
            # 先定义新文件的路径,名字是new_path
            name_path = str(weight) + '-' + str(high)
            print(name_path)
            new_path = os.path.join(files_path, name_path)
            print(new_path)
            # 查询新文件路径下面是否是文件夹
            if os.path.isdir(new_path):
                # 将图片复制到新闻家当中
                shutil.copyfile(photo_abspath, os.path.join(new_path, photo))
                # shutil.copyfile(photo_abspath, new_path)
            else:
                os.mkdir(new_path)
                shutil.copyfile(photo_abspath, os.path.join(new_path, photo))
                # shutil.copyfile(photo_abspath, new_path)
        print('分类成功！')
 

 
if __name__ == '__main__':
    photo_classify(files_path)

将图片按分辨率归为四类

size4.py

# coding=utf-8
 
import os
import shutil
from PIL import Image
 
files_path = r'E:\pic\1'
suffixlist = ['.Webp', '.BMP', '.JPEG', '.RAW', '.JPG', '.PNG', '.webp', '.bmp', '.jpeg', '.raw', '.jpg', '.png',]
 
#定义一个分类函数，函数括号中为需要分类的图片文件夹路径
def photo_classify(files_path):
    # 读取文件夹中所有文件的名称
    files_list = os.listdir(files_path)
 
    # 循环文件夹中的所有文件
    for photo in files_list:
 
        # 获取图片的绝对路径
        photo_abspath = os.path.join(files_path, photo)
 
        # 判断photo是不是文件夹，若是文件夹则跳过，若不是文件夹则继续执行
        if os.path.isdir(photo_abspath):
            print(photo_abspath + '是文件夹')
            continue
        elif os.path.splitext(photo_abspath)[-1] not in suffixlist:
            print(photo_abspath + "的文件后缀不是'.Webp', '.BMP', '.JPEG', '.RAW', '.JPG', '.PNG', '.bmp', '.jpeg', '.raw', '.jpg', '.png',中的一个")
        else:
            print('处理' + photo_abspath)
            # 读图片的尺寸
            img = Image.open(photo_abspath)
 
            weight = img.size[0]
            high = img.size[1]
            ratio = float(weight) / float(high)
            print('宽' + str(weight) + '高' + str(high) + '比例' + str(ratio))
 
            if 0.45 <= ratio <= 0.72:
            #if weight < high:
                picKind = 'pe'
            elif 1.50 <= ratio <= 2.30:
                picKind = 'pc'
            elif weight == high:
                picKind = 'pp'
            else:
                picKind = 'other'
 
            new_path = os.path.join(files_path, picKind)
            print(new_path)
            # 查询新文件路径下面是否是文件夹
            if os.path.isdir(new_path):
                # 将图片复制到新文件夹当中
                shutil.copyfile(photo_abspath, os.path.join(new_path, photo))
                # shutil.copyfile(photo_abspath, new_path)
            else:
                os.mkdir(new_path)
                shutil.copyfile(photo_abspath, os.path.join(new_path, photo))
                # shutil.copyfile(photo_abspath, new_path)
        print('分类成功！')
 
 
if __name__ == '__main__':
    photo_classify(files_path)

将通过 API 获取的 json 信息写入 txt 文件

json_into_txt.py

# coding=utf-8
 
import requests, json
 
tfile = "E:/acg/acgurl.txt" 
i = 1
url = 'https://www.loliapi.com/acg?type=json'
 
while i < 100:
    r = requests.request('get',url)  #获取网页
    imgjson = r.text
    text = json.loads(imgjson)
    t = text['imgurl'] + "\n"
 
    with open(tfile,"a") as f:
        f.write(t)
        f.close()
    print(t)
    i += 1

将网页里带 img标签的图片的地址写入 txt 文件（不知道能不能用）

# coding=utf-8
 
import requests, json
from bs4 import BeautifulSoup
 
tfile = "E:/acg/picurl.txt" 
 
url = ' '
 
#while True:

    r = requests.request('get',url)  #获取网页
    soup = BeautifulSoup(r.text, "lxml")
    for a in soup.find_all('a'):
        if a.img:
            src = a.img['src']
 
            with open(tfile,"a") as f:
                f.write(src)
                f.close()
            print(src)

文件批量重命名

rename.py

# coding=utf-8

import os

files_path = r'E:\acg\acg'   #文件位置


num = 1
newname = "img"

files = os.listdir(files_path) 
for filename in files:
    portion = os.path.splitext(filename)
    nname = newname + str(num) + portion[1]
    os.chdir(files_path)
    os.rename(filename,nname)
    print("文件" + filename + "已修改为" + nname)
    num = num + 1

文件批量改后缀

resuffix.py

# coding=utf-8

import os

files_path = r'E:\acg\acg'   #文件位置

originalsuffix = "all" #要修改的后缀名,如果要修改所有文件则填'all'
suffix = "png"  #目标后缀名

files = os.listdir(files_path) 
#files.sort(key=lambda x:int(x[:-4]))
for filename in files:
    portion = os.path.splitext(filename)

    if originalsuffix == "all" or portion[1] == originalsuffix:
        # 重新组合文件名和后缀名  
        newname = portion[0] + "." + suffix  
        os.chdir(files_path)
        os.rename(filename,newname)
        print("文件" + filename + "已修改为" + newname)

图片格式转换

pic2webp.py

# coding=utf-8

import os
from PIL import Image


files_path = r'E:\acg\acg'   #文件位置

suffix = "webp"  #目标格式（后缀名）
del_original_img = "true" #是否删除原图片
for dpath, dname, dfiles in os.walk(files_path, topdown=False):
    for fname in dfiles:
        imgpath = os.path.join(dpath, fname)
        portion = os.path.splitext(fname)
        suffixfname = os.path.join(dpath, portion[0] + "." + suffix)
        im = Image.open(imgpath)
        if suffix == "jpg" or suffix == "jpeg":
            im = im.convert("RGB") 
        im.save(suffixfname)
        print(imgpath + "成功转换为" + suffixfname)
        if del_original_img == "true":
            if imgpath == suffixfname:
                print("目标文件" + imgpath + "已是" + suffix + "格式,为防止误删，跳过此文件")
            else:
                os.remove(imgpath)
                print("已删除源文件" + imgpath)