【爬虫软件】孔夫子二手书采集-编程知识

【爬虫软件】孔夫子二手书采集

项目演示

孔网爬取图书信息

目录结构

['    |-- api-ms-win-core-synch-l1-2-0.dll','    |-- api-ms-win-core-sysinfo-l1-1-0.dll','    |-- api-ms-win-core-timezone-l1-1-0.dll','    |-- api-ms-win-core-util-l1-1-0.dll','    |-- api-ms-win-crt-conio-l1-1-0.dll','    |-- api-ms-win-crt-convert-l1-1-0.dll','    |-- api-ms-win-crt-environment-l1-1-0.dll','    |-- api-ms-win-crt-filesystem-l1-1-0.dll','    |-- api-ms-win-crt-heap-l1-1-0.dll','    |-- api-ms-win-crt-locale-l1-1-0.dll','    |-- api-ms-win-crt-math-l1-1-0.dll','    |-- api-ms-win-crt-multibyte-l1-1-0.dll','    |-- api-ms-win-crt-process-l1-1-0.dll','    |-- api-ms-win-crt-runtime-l1-1-0.dll','    |-- api-ms-win-crt-stdio-l1-1-0.dll','    |-- api-ms-win-crt-string-l1-1-0.dll','    |-- api-ms-win-crt-time-l1-1-0.dll','    |-- api-ms-win-crt-utility-l1-1-0.dll','    |-- base_library.zip','    |-- libcrypto-1_1.dll','    |-- libopenblas.XWYDX2IKJW2NMTWSFYNGFUWKQU3LYTCZ.gfortran-win_amd64.dll','    |-- libssl-1_1.dll','    |-- pyexpat.pyd','    |-- python3.dll','    |-- python37.dll','    |-- select.pyd','    |-- tcl86t.dll','    |-- tk86t.dll','    |-- ucrtbase.dll','    |-- unicodedata.pyd','    |-- VCRUNTIME140.dll','    |-- VCRUNTIME140_1.dll','    |-- _bz2.pyd','    |-- _cffi_backend.cp37-win_amd64.pyd','    |-- _ctypes.pyd','    |-- _decimal.pyd','    |-- _elementtree.pyd','    |-- _hashlib.pyd','    |-- _lzma.pyd','    |-- _multiprocessing.pyd','    |-- _queue.pyd','    |-- _socket.pyd','    |-- _ssl.pyd','    |-- _tkinter.pyd','    |-- 孔夫子二手书采集.exe','    |-- certifi','    |   |-- cacert.pem','    |   |-- py.typed','    |-- charset_normalizer','    |   |-- md.cp37-win_amd64.pyd','    |   |-- md__mypyc.cp37-win_amd64.pyd','    |-- cryptography','    |   |-- hazmat','    |       |-- bindings','    |           |-- _rust.pyd','    |-- cryptography-41.0.7.dist-info','    |   |-- INSTALLER','    |   |-- LICENSE','    |   |-- LICENSE.APACHE','    |   |-- LICENSE.BSD','    |   |-- METADATA','    |   |-- RECORD','    |   |-- REQUESTED','    |   |-- top_level.txt','    |   |-- WHEEL','    |-- file','    |   |-- output.xlsx','    |-- lxml','    |   |-- builder.cp37-win_amd64.pyd','    |   |-- etree.cp37-win_amd64.pyd','    |   |-- objectify.cp37-win_amd64.pyd','    |   |-- sax.cp37-win_amd64.pyd','    |   |-- _elementpath.cp37-win_amd64.pyd','    |   |-- html','    |   |   |-- clean.cp37-win_amd64.pyd','    |   |   |-- diff.cp37-win_amd64.pyd','    |   |-- isoschematron','    |       |-- resources',
]

概述

毕业前做的小玩意，今天发现居然还能继续使用，孔夫子二手书采集软件可以将您本地的ISBN全部批量查询书籍信息，并切割保存到本地文件。可查询出版社、出版时间、在售/已售数量、可查询前五本的书籍信息

支持多线程采集
在这里插入图片描述

支持质量筛选、价格排序
在这里插入图片描述
原数据预览图

处理后的数据预览图
在这里插入图片描述

部分核心逻辑

Vb工程图

新建绘制一个VB视图
在这里插入图片描述
导出UI代码

数据导入与读取

def Command4_Cmd(self):global daoru_state# 打开文件选择对话框file_path = filedialog.askopenfilename(filetypes=[('Excel Files', '*.xlsx')])if file_path:# 加载Excel文件wb = load_workbook(filename=file_path)# 处理Excel文件# ...# 保存Excel文件到本地路径wb.save('file/output.xlsx')daoru_state=1# 提示用户导入成功#获取行数# 加载Excel文件wb = load_workbook(filename='file/output.xlsx')# 获取Sheet1工作表ws = wb.active# 获取行数row_count = ws.max_rowself.Text3Var.set(row_count)

下拉框选择参数

self.style.configure('TLabel5.TLabel', anchor='w', font=('宋体', 9))
self.Label5 = Label(self.Frame4, text='价格：', style='TLabel5.TLabel')
self.Label5.place(relx=0.077, rely=0.234, relwidth=0.234, relheight=0.182)self.style.configure('TLabel6.TLabel', anchor='w', font=('宋体', 9))
self.Label6 = Label(self.Frame4, text='品相：', style='TLabel6.TLabel')
self.Label6.place(relx=0.077, rely=0.584, relwidth=0.196, relheight=0.182)self.Combo2List = ['默认', '价格从低到高', '价格从高到低']
self.Combo2Var = StringVar(value='默认')
self.Combo2 = Combobox(self.Frame4, text='默认', textvariable=self.Combo2Var,
values=self.Combo2List, font=('宋体', 9))
self.Combo2.place(relx=0.383, rely=0.234, relwidth=0.541, relheight=0.146)

设置线程

stop_threads = False  # 全局变量，控制线程的停止
# 总行数
total_rows = ws.max_row
# 线程数
num_threads = int(self.Text4Var.get())
# 每个线程处理的行数
rows_per_thread = math.ceil(total_rows / num_threads)
# 创建线程
threads = []
for i in range(num_threads):
# random_number = random.randint(1, )
start_row = i * rows_per_thread + 1
end_row = min((i + 1) * rows_per_thread, total_rows)
t = threading.Thread(target=process_rows,args=(start_row, end_row, table, self, order, quality, int(requests_spped)))
threads.append(t)# 启动线程
for t in threads:
t.start()# 将全局变量设置为False，表示线程不再执行
global stop_threads
stop_threads = False
# # 等待所有线程结束