[开发工具]一个爬取美女图片的Python程序（仅供学习交流）

import requests
import re
import os
import easygui
import time


def get_mom_url_list(page, home_url):
    url = home_url + '/home/' + str(page)
    url_text = requests.get(url).text
    url_list = re.findall('a\shref=\"(/mm/.*?\d)\"\starget', url_text)[0:30]
    f_url_list = []
    for index in range(len(url_list)):
        if index % 2 == 0:
            f_url_list.append(home_url + url_list[index])
    return f_url_list


def get_jpg_url(f_url):
    url_text = requests.get(f_url).text
    jpg_download_url = re.findall("img\ssrc=\"(.*?)\"\salt", url_text)[0]
    return jpg_download_url


if __name__ == '__main__':
    # 获取最近一次的下载位置
    txt_file_path = os.getcwd() + '\\latest.txt'
    if not os.path.exists(txt_file_path):
        mom = '1'
        son = '1'
        jpg = '0'
    else:
        date = open(txt_file_path, 'r')
        txt_list = date.readlines()
        mom = txt_list[0].strip()
        son = txt_list[1].strip()
        jpg_path = os.getcwd() + '/' + txt_list[2].strip()
        if os.path.exists(jpg_path):
            jpg = str(len(os.listdir(jpg_path)))
        else:
            jpg = '0'
    # 输入最新的网址及开始下载的位置
    msg = "输入开始下载的页码及主题序号"
    title = "确定开始下载的位置"
    fieldNames = ["最新网址：", "开始下载的页码:(1~306)", "主题序号:(1~15)", "本主题已下载的照片数量："]
    Values = ['https://www.mm5mm5.com', mom, son, jpg]
    fieldValues = easygui.multenterbox(msg, title, fieldNames, Values)
    if fieldValues is None: exit()
    # 获取数据，网址，母页，子页，文件夹中已有照片
    url_home = fieldValues[0]
    start_mom_page = int(fieldValues[1]) - 1
    start_son_page = int(fieldValues[2]) - 1
    start_jpg_page = int(fieldValues[3])
    first_run = True
    jpg_first_run = True
    start_son_p = 0
    for page_num in range(start_mom_page, 306):
        mom_url_list = get_mom_url_list(page_num, url_home)  # 获取当前页面所有图片包的地址
        # 判断母页是否下一页，若下一页子页从0开始
        if first_run is True:
            start_son_p = start_son_page
        # 对母页中主题进行循环
        for son_url in mom_url_list[start_son_p:]:
            theme_num = mom_url_list.index(son_url)
            # 生成文件夹名称
            text = requests.get(son_url).text
            theme = re.findall('<h2>\s*(.*?)\s*</h2>', text)
            folder_name = '【' + theme[0] + '】'
            # 建立文件夹
            path = os.getcwd() + "\\" + str(folder_name)
            if not os.path.isdir(path):
                os.mkdir(path)

            # 判断母页是否下一页，若下一页子页从0开始
            start_jpg_p = 0
            if jpg_first_run is True:
                start_jpg_p = start_jpg_page
            # 开始对子页中所有图片进行下载
            for i in range(start_jpg_p, 100):
                son_jpg_url = son_url + '/' + str(i)
                jpg_url = get_jpg_url(son_jpg_url)
                if len(jpg_url) == 0:
                    break
                else:
                    content = requests.get(jpg_url).content
                    jpg_name = re.findall("\d/(.*?jpg)", jpg_url)[0]
                    if not os.path.exists(path + "\\" + jpg_name):
                        with open(path + "\\" + jpg_name, 'wb') as f:
                            f.write(content)
                            f.close()
                        # 获取现在的时间
                        t = time.localtime(time.time())
                        s = time.strftime('%Y-%m-%d  %H:%M:%S\t', t)
                        out_mess = f'{s}成功下载第{page_num + 1}页的第{theme_num + 1}个主题{folder_name}的{jpg_name}照片'
                        print(out_mess)
                        with open(os.getcwd() + "\\下载记录.txt", 'a', encoding='utf-8') as q:
                            q.writelines(out_mess + '\n')
                            q.close()
                        with open(os.getcwd() + '\\latest.txt', 'w') as b:
                            b.write(f'{page_num + 1}\n{theme_num + 1}\n{folder_name}')
                            b.close()
                    else:
                        print(f'{folder_name}的{jpg_name}照片已存在')
            jpg_first_run = False
        first_run = False