add word2pdf in gui

.gitignore

@@ -14,6 +14,7 @@ pids
 *.pid
 *.seed
 *.pid.lock
+*.spec
 
 # Directory for instrumented libs generated by jscoverage/JSCover
 lib-cov

PDF.py

@@ -1,7 +1,7 @@
 from PyPDF2 import PdfFileReader, PdfFileWriter
 import sys
 import os
-import fitz
+from pdf2image import convert_from_path
 
 class PDF: 
     def __init__(self):
@@ -16,17 +16,17 @@ def pdf_info(self):
     def split_pdf_each(self): 
         for infn in self.infn:
             try:
-                pdf_name = infn.split('\\')[-1];
-                dir_ = infn.replace(pdf_name, pdf_name[:-4] + '\\')
-                if not os.path.exists(dir_):
-                    os.mkdir(dir_)
+                (dir_, pdf_name) = os.path.split(infn)
                 pdf_input = PdfFileReader(open(infn, 'rb')) 
                 pages = pdf_input.getNumPages()  
                 self.message = '正在拆分...'
                 for i in range(pages): 
                     pdf_output = PdfFileWriter()
                     pdf_output.addPage(pdf_input.getPage(i)) 
-                    pdf_output.write(open(dir_ + pdf_name[:-4] + '-' + str(i + 1) + '.pdf', 'wb')) 
+                    path = dir_ + '/' + pdf_name[:-4] + '单页拆分'
+                    if not os.path.exists(path):
+                        os.mkdir(path)
+                    pdf_output.write(open(path + '/' + pdf_name[:-4] + '-' + str(i + 1) + '.pdf', 'wb')) 
                     self.message = pdf_name + ':  ' + str(i) + '/' + str(pages)
                 self.message = '完成'
             except:
@@ -35,13 +35,17 @@ def split_pdf_each(self):
     def split_pdf_parts(self): 
         for infn in self.infn:
             try:
+                (dir_, pdf_name) = os.path.split(infn)
                 pdf_input = PdfFileReader(open(infn, 'rb'))
                 self.message = '正在拆分...'
                 for part in self.params:
                     pdf_output = PdfFileWriter()
                     for i in range(part[0] - 1, part[1]):
                         pdf_output.addPage(pdf_input.getPage(i));
-                    pdf_output.write(open(infn[:-4] + '-' + str(part[0]) + '-' + str(part[1]) + '.pdf', 'wb'))
+                    path = dir_ + '/' + pdf_name[:-4] + '部分拆分'
+                    if not os.path.exists(path):
+                        os.mkdir(path)
+                    pdf_output.write(open(path + '/' + pdf_name[:-4] + '-' + str(part[0]) + '-' + str(part[1]) + '.pdf', 'wb'))
                     self.message = '第%d部分已拆分'%(self.params.index(part) + 1)
                 self.message = '完成'
             except:
@@ -127,23 +131,15 @@ def add_watermark(self):
             except: 
                 self.message = '出错了，请检查输入格式是否正确(page-number.pdf文件要求和程序在同一目录)'
 
-    def convert_pdf2_image(self):
+    def pdf2image(self):
         self.message = '正在转换，所需时间较长，请稍等'
-        zoom, type_ = self.params
         for infn in self.infn:
             try:
-                pdf_name = infn.split('\\')[-1];
-                dir_ = infn.replace(pdf_name, pdf_name[:-4] + '\\')
-                if not os.path.exists(dir_):
-                    os.mkdir(dir_)
-                doc = fitz.open(infn)
-                for pg in range(doc.pageCount):
-                    page = doc[pg]
-                    rotate = int(0)
-                    trans = fitz.Matrix(zoom, zoom).preRotate(rotate)
-                    pm = page.getPixmap(matrix=trans, alpha=False)
-                    pm.writePNG( dir_ + pdf_name + '-' + str(pg) + '.' + type_ ) 
-                    self.message = pdf_name + ':  ' + str(pg + 1) + '/' + str(doc.pageCount) ;
+                (dir_, pdf_name) = os.path.split(infn)
+                outfn = dir_ + pdf_name[:-4] + 'images/'
+                if not os.path.exists(outfn):
+                        os.mkdir(outfn)
+                images = convert_from_path(infn, dpi=self.params, output_folder=outfn, fmt='png', thread_count=5)
                 self.message = '完成';
             except:
                 self.message = '出错: 如输入格式无误, 则不支持此文件'

README.md

@@ -11,11 +11,49 @@
 
 # 相关库
 1. pdf文档处理： PyPDF2.
-2. UI：wx.
-3. exe文件：pyinstaller, pywin32, pywin32-ctypes.
+2. pdf转图片: pdf2image.
+3. word转pdf: pywin32, 调用Office.
+4. UI：wxpython.
+5. exe文件：pyinstaller.
 
 
 # 打包方法
-首先安装上述三个库，其中pyinstaller可以官网下载压缩包，然后把待打包程序放在其解压文件夹下，然后命令行运行
-python pyinstaller.py -F -w client.py
+python需要3.6版本
+首先安装上述库，其中pyinstaller可以官网下载压缩包，然后把待打包程序放在其解压文件夹下，然后命令行运行
+pyinstaller -F -w xx/xx/app.py
 其中-F, -w分别表示打包为单个执行exe程序，不显示命令行窗口。
+
+
+
+@author JMx
+date 2018-04-26
+pdf文件拆分,合并,剪切等功能.
+
+        1   将pdf文件拆分成单页.
+            split_pdf_each(infn):                        
+                    "infn"表示文件名(含路径).
+                    例:split_pdf_each('F:/pdf/test.pdf').
+
+        2   将pdf文件拆分成多个部分.
+            split_pdf_parts(infn, parts): 
+                    "infn"为文件名(含路径).
+                    "parts"为每个部分起始页码列表.
+                    例:split_pdf_parts('F:/p/1.pdf',[(1,3),(40,50)]).
+
+        3   将多个pdf文件合并成一个.
+            merge_pdf(infnList, outfn):                       
+                    "infnList"为要合并的文件名(含路径)列表.
+                    "outfn"为合并后文件名(含路径).
+                    例:merge_pdf(['F:/1.pdf','F:/2.pdf'], 'F:/12.pdf').
+                    
+        4   将pdf文件页面剪切至合适大小.
+            cut_pdf(infn, left, right, lower, upper, option, isTest):        
+                    "infn"表示文件名(含路径).
+                    2~5四个参数分别是四周需要剪去的宽度(一般在10～160).
+                    "option"为剪切方式,all/odd/even 页.
+                    "isTest"表示是否先对第一页进行测试.
+                    例:cut_pdf('F:/1.pdf',20,20,20,20,'even',1).测试.
+                                只剪切前两页,单独生成一个pdf文件.
+                        cut_pdf('F:/1.pdf',20,20,20,20,'odd',0)不测试.
+                                剪切奇数页.
+

app.py

@@ -0,0 +1,133 @@
+import wx, time, re, os
+from PDF import PDF
+from word2pdf import Word2PDF
+from threading import Thread
+
+pdfdo = PDF()
+word2pdf = Word2PDF()
+
+app = wx.App()
+frm = wx.Frame(None, title="pdf处理器", size = (600, 470));
+message = False
+
+def split_fn(fn):
+	word2pdf.infn += list( filter(lambda f: os.path.splitext(f)[1] in ['.doc', '.docx'] , fn) )
+	pdfdo.infn += list( filter(lambda f: os.path.splitext(f)[1] == '.pdf' , fn) )
+	message.SetValue('PDF文档信息: ' + str(pdfdo.pdf_info()) )
+	fn = [f.split("\\")[-1] for f in (word2pdf.infn + pdfdo.infn)]
+	wx.FindWindowById(0).SetValue(str(fn));
+
+def select_files():
+	if fileDialog.ShowModal() == wx.ID_OK:
+		path = fileDialog.GetDirectory()
+		fn = [ path + '\\' + f for f in fileDialog.GetFilenames() ]
+		split_fn(fn)
+
+def update_state():
+	message.SetValue(pdfdo.message or word2pdf.message)
+	message2 = pdfdo.message + word2pdf.message;
+	if ('完成' not in message2) and ('出错了' not in message2):
+		time.sleep(1)
+		update_state()
+	elif message2:
+		print(message2)
+		message.SetValue(pdfdo.message or word2pdf.message)
+	pdfdo.message = '';
+	word2pdf.message = '';
+
+def btn_callback(event):
+	id_ = event.GetId()
+
+	if id_ == 1:
+		select_files()
+		return
+	if ( not(pdfdo.infn) and (id_ in list(range(1, 17, 2))) ) or ( not(word2pdf.infn) and id_ == 17 ):
+		message.SetValue('请选择文件')
+		return
+
+	pdfdo.message = ''
+	param_ = wx.FindWindowById(id_ - 1).GetValue()
+	param = []
+	if id_ not in [3, 7, 13, 17]:
+		try:
+			param = eval(param_)
+		except:
+			message.SetValue('输入格式有误')
+			return
+
+	Thread(target = update_state).start()	
+
+	pdfdo.params = param;
+
+	if id_ == 3:
+		pdfdo.split_pdf_each()
+	elif id_ == 5:
+		pdfdo.split_pdf_parts()
+	elif id_ == 7:
+		(path, filename) = os.path.split(pdfdo.infn[0])
+		merge_fn = wx.FindWindowById(6).GetValue() or '合并文件.pdf';
+		pdfdo.params = path + '\\' + merge_fn
+		pdfdo.merge_pdf()
+	elif id_ == 9:
+		pdfdo.cut_pdf()
+	elif id_ == 11:
+		pdfdo.rotate_pdf()
+	elif id_ == 13:
+		pdfdo.add_watermark()
+	elif id_ == 15:
+		pdfdo.pdf2image()
+	elif id_ == 17:
+		word2pdf.run()
+
+def create_gui():
+	# input/button: pos = (left, top), size = (width, height).
+	left = 15
+	width = 450
+	top = 20
+	margin = 40
+	height = 30
+	labels = ['选择文件', '拆分每页', '部分拆分', '文件合并', '文件剪切', '文件旋转', '添加页码', '转为图片', 'Word转PDF']
+	default_values = [
+	 '支持拖入文件',
+	 '支持多个文件',
+	 '支持多个文件， 如：[(1,3),(20,25),(30,40)]',
+	 '合并后文件名.pdf',
+	 '支持单个文件，如：[10,20,10,20,"even",1] (注：左, 右, 下, 上, odd/even/all, 0/1: 0为全部, 1为测试10张)',
+	 '支持单个文件，如：[90,1] (注：旋转度数是90的整数倍, 0/1: 1为测试一张, 0为全部)',
+	 '支持多个文件', 
+	 '支持多个文件： 如200, 数值越大，图片越清晰，转换也越慢', 
+	 '支持多个文件'
+	 ]
+	length = len(labels)
+
+	fileDialog = wx.FileDialog(frm, message = '选择文件', wildcard = '*.pdf;*.doc;*.docx', style = wx.FD_OPEN | wx.FD_MULTIPLE, pos = (200, 30), size = (100, 25))	
+
+	for i in range(length):
+		wx.TextCtrl(frm, id = 2 * i, value = default_values[i], pos = (left, top + margin * i), size = (width, height))
+		wx.Button(frm, id = 2 * i + 1, label = labels[i], pos = (width + 20, top + margin * i), size = (100, height)).Bind(wx.EVT_BUTTON, btn_callback)	
+
+	message = wx.TextCtrl(frm, value = "状态框", pos = (left, top + margin * length + 5), size = (555, height))
+	return (fileDialog, message)
+
+class FileDrop(wx.FileDropTarget):
+
+	def __init__(self, window):
+		wx.FileDropTarget.__init__(self)
+		self.window = window
+
+	def OnDropFiles(self, x, y, fn):
+		fn = [f.replace('\\', '\\\\') for f in fn]
+		split_fn(fn)
+		return True
+
+(fileDialog, message) = create_gui()
+drop = FileDrop(wx.FindWindowById(0));
+wx.FindWindowById(0).SetDropTarget(drop);
+
+frm.Center()
+frm.Show()
+app.MainLoop()
+
+
+
+