Create new file

app.py

@@ -0,0 +1,150 @@
+import streamlit as st
+import math
+import re
+import os
+from PyPDF2 import PdfFileReader, PdfFileWriter
+import pandas as pd
+import pdfplumber
+from docx2pdf import convert
+import fitz
+import base64
+
+st.header('PDF文件处理工具测试')
+
+def fx(x):
+    return sum(x,[])
+fns=st.radio('请选择PDF处理类型：',['拆分','合并','读取','在线预览','转换'])
+if fns=='拆分':
+    uploaded_file = st.text_input("请输入要处理的pdf文件地址:")
+    if uploaded_file !='':
+    
+        pdf_reader = PdfFileReader(uploaded_file)
+        n=pdf_reader.getNumPages()
+        che=st.radio('选择拆分类型',['按固定页数拆分','截取某几页','删除指定页面'])
+        if che=='按固定页数拆分':
+            fn=st.number_input('请输入每组拆分的文档页数：',1,n,1)
+            stre=st.text_input("请输入拆分后文件存放根目录:")
+            zs=math.ceil(n/fn)
+            if st.button('开始拆分>>'):
+                for page in range(1,zs+1):
+                    for pn in range(fn*page-fn,fn*page):
+                        if pn<n:
+                            pdf_writer = PdfFileWriter()
+                            pdf_writer.addPage(pdf_reader.getPage(pn))
+                            with open(stre+'/test-{}.pdf'.format(page), 'wb') as out:
+                                pdf_writer.write(out)
+        elif che=='截取某几页':
+            st_en=st.text_input("请输入截取的起止页码，格式为“1-5”或“1,3,5”:")
+            stre2=st.text_input("请输入截取后pdf文件存放根目录:")
+            if st_en!='':
+                tt=[int(x) for x in re.split(r'[-,\s]\s*',st_en)]
+                if st.button('开始截取>>'):
+                    outw=PdfFileWriter()
+                    for r in (tt if ',' in st_en else range(tt[0]-1,tt[1])):
+                        outw.addPage(pdf_reader.getPage(r))
+                        with open(stre2+'/666.pdf', 'wb') as out:
+                            outw.write(out)
+        else:
+            st_en2=st.text_input("请输入需要删除的页码，格式为“1-5”或“1,3,5”:")
+            stre3=st.text_input("请输入删除指定页面后的pdf文件存放根目录:")
+            if st_en2!='':
+                tt=[int(x) for x in re.split(r'[-,\s]\s*',st_en2)]
+                if st.button('开始删除>>'):
+                    outw2=PdfFileWriter()
+                    for r in range(n):
+                        if r not in (tt if ',' in st_en2 else range(tt[0]-1,tt[1])):
+                            outw2.addPage(pdf_reader.getPage(r))
+                            with open(stre3+'/666.pdf', 'wb') as out:
+                                outw2.write(out)
+elif fns=='合并':
+    path = st.text_input("请输入要处理的pdf文件根目录:")
+    scn = st.text_input("请填写输出文件地址及文件名")
+    if path !='' and scn!='':
+        file_list = os.listdir(path)
+        if st.button('开始合并>>'):
+            file_out = PdfFileWriter()
+            for file in file_list:
+                docdir = os.path.join(path, file)
+                file_read = PdfFileReader(docdir)
+                for pageNum in range(file_read.getNumPages()): 
+                    file_out.addPage(file_read.getPage(pageNum))
+            with open(scn,'wb') as output:
+                file_out.write(output)
+
+
+elif fns=='读取':
+    path3 = st.text_input("请输入要读取的pdf文件地址:")
+    if path3 !='':
+        ms=st.radio('请选择读取模式：',['指定页码','全部'])
+        if ms=='指定页码':
+            ymq= st.number_input("请选择要读取的pdf页码:",1,66,1)
+            dqlx=st.radio('请选择读取类型',['文本内容','表格内容'])    
+            with pdfplumber.open(path3) as p:
+                page = p.pages[ymq-1]
+                if dqlx=='文本内容':
+                    textdata = page.extract_text()
+                    st.write(textdata)
+                else:
+                    n_table=st.number_input('请选择读取页面中第几个表格：',1,3,1)
+                    tables=page.extract_tables()
+                    datan=tables[n_table-1]
+                    st.dataframe(pd.DataFrame(datan[1:],columns=datan[0]))
+        else:
+            dqlx2=st.radio('请选择读取类型',['文本内容','表格内容'])
+            with pdfplumber.open(path3) as p:
+                if dqlx2=='文本内容':
+                    sz='\n'.join([page.extract_text() for page in p.pages])
+                    st.write(sz)
+                else:
+                    st.dataframe(pd.concat([pd.DataFrame(data=y[1:],columns=y[0]) for y in fx([page.extract_tables() for page in p.pages])]))
+
+elif fns=='在线预览':
+    file = st.file_uploader("请上传PDF")
+    if file is not None:
+        base64_pdf = base64.b64encode(file.read()).decode('utf-8')
+        pdf_display = f'<embed src="data:application/pdf;base64,{base64_pdf}" width="100%" height="1000" type="application/pdf">'
+        st.markdown(pdf_display, unsafe_allow_html=True)
+
+else:
+    ms1=st.radio('请选择转换模式：',['word->pdf','ppt->pdf','pdf->jpg/png','jpg/png->pdf'])
+    if ms1=='word->pdf':
+        path4 = st.text_input("请输入要批量转换的word文件根目录:")
+        if path4 !='':
+            FileList = map(lambda x: path4 + '\\' + x, os.listdir(path4))
+            for file in FileList:
+                convert(file, f"{file.split('.')[0]}.pdf")
+            st.success('转换成功！')
+    elif ms1=='pdf->jpg/png':
+        path5 = st.text_input("请输入要转换的pdf文件地址:")
+        dir_1=st.text_input("请输入要输出的图片保存根目录:")
+        if path5 !='' and dir_1 !='':
+            doc = fitz.open(path5)
+            for page in doc:
+                pix = page.get_pixmap()
+                pix.save(dir_1+"/page-%i.png" % page.number)
+
+    elif ms1=='jpg/png->pdf':
+        dir_2=st.text_input("请输入要转换为pdf的图片根目录:")
+        path6 = st.text_input("请输入合成的pdf文件存放地址:")
+        if path6 !='' and dir_2 !='':
+            doc = fitz.open()
+            imglist = os.listdir(dir_2)
+            for i, f in enumerate(imglist):
+                img = fitz.open(os.path.join(dir_2, f))
+                rect = img[0].rect
+                pdfbytes = img.convert_to_pdf()
+                img.close()
+                imgPDF = fitz.open("pdf", pdfbytes)
+                page = doc.new_page(width = rect.width,height = rect.height)
+                page.show_pdf_page(rect, imgPDF, 0)
+            doc.save(path6)
+    elif ms1=='ppt->pdf':
+        dir_3=st.text_input("请输入要转换为pdf的PPT文件地址:")
+        path7 = st.text_input("请输入生成的pdf文件存放地址:")
+        if path7 !='' and dir_3 !='':
+            ppt = fitz.open(dir_3)
+            pdfbytes = ppt.convert_to_pdf()
+            pdf = fitz.open("pdf", pdfbytes)
+            pdf.save(path7)
+    else:
+        ""