From 9fb6c56c483127f060f370f57486017692f078b1 Mon Sep 17 00:00:00 2001 From: "512song@sina.com" Date: Tue, 11 Oct 2022 07:48:22 +0800 Subject: [PATCH] 20221011 --- .ipynb_checkpoints/文件管理-checkpoint.ipynb | 1313 +++++++++++++++++ .ipynb_checkpoints/文件管理1-checkpoint.ipynb | 1313 +++++++++++++++++ 2 files changed, 2626 insertions(+) create mode 100644 .ipynb_checkpoints/文件管理-checkpoint.ipynb create mode 100755 .ipynb_checkpoints/文件管理1-checkpoint.ipynb diff --git a/.ipynb_checkpoints/文件管理-checkpoint.ipynb b/.ipynb_checkpoints/文件管理-checkpoint.ipynb new file mode 100644 index 0000000..bfebbe4 --- /dev/null +++ b/.ipynb_checkpoints/文件管理-checkpoint.ipynb @@ -0,0 +1,1313 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "333a5431-a697-4330-a587-455d6d18ebb0", + "metadata": {}, + "source": [ + "# 文件管理" + ] + }, + { + "cell_type": "markdown", + "id": "bcd48bb6-4756-4748-ac8b-854eeee92a3b", + "metadata": {}, + "source": [ + "## 数字文件名转换为文本文件名" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "54b320e8-c3c1-4214-9a9e-db13c2558604", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import os,sys,shutil\n", + "import openpyxl\n", + "import math\n", + "\n", + "fi_xls = os.getcwd() + '/data/高新区.xlsx'\n", + "fi_path = os.getcwd() + '/file/220720'\n", + "old = []\n", + "dict1 = {}\n", + "\n", + "wb = openpyxl.load_workbook(fi_xls)\n", + "sheet = wb.active\n", + "depart = []\n", + "for n in range(2,sheet.max_row+1): \n", + " m_name = str(sheet.cell(n,1).value)\n", + " m_depart = sheet.cell(n,5).value\n", + " if m_depart not in depart:\n", + " depart.append(sheet.cell(n,5).value)\n", + " dict1[int(m_name.split('.')[0])] = [sheet.cell(n,2).value.strip(),sheet.cell(n,5).value.strip()]\n", + " \n", + "# 创建部门办公室 \n", + "m_path = os.getcwd()+'/file/220427/new'\n", + "for pn in depart:\n", + " if not os.path.exists(m_path + '/' + pn):\n", + " os.mkdir(m_path + '/' + pn)\n", + "fl=os.listdir(fi_path)\n", + "for fn in fl:\n", + " if os.path.isfile(fi_path + '/' + fn):\n", + " ofn = int(fn.split('.')[0])\n", + " old.append(ofn) \n", + "old.sort()\n", + "for n in old: \n", + " o_name = f'{fi_path}/{n}.pdf'\n", + " n_name = f'{fi_path}/new/{dict1[n][1]}/{str(n).rjust(5,\"0\")}-{dict1[n][0]}.pdf'\n", + " if not os.path.exists(n_name):\n", + " shutil.copyfile(o_name,n_name)\n", + " print(n_name)\n", + "#print(dict1)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "4a43668e-47ba-491f-a29c-e289885badb0", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import os,sys,shutil\n", + "import openpyxl\n", + "import math\n", + "\n", + "fi_xls = os.getcwd() + '/data/高新区.xlsx'\n", + "fi_path = os.getcwd() + '/file/220720'\n", + "old = []\n", + "dict1 = {}\n", + "\n", + "wb = openpyxl.load_workbook(fi_xls)\n", + "sheet = wb.active\n", + "depart = []\n", + "for n in range(2,sheet.max_row+1): \n", + " m_name = str(sheet.cell(n,1).value)\n", + " m_depart = sheet.cell(n,5).value\n", + " if m_depart not in depart:\n", + " depart.append(sheet.cell(n,5).value)\n", + " dict1[sheet.cell(n,4).value] = [sheet.cell(n,6).value,sheet.cell(n,3).value]\n", + "#print(dict1)\n", + "fl=os.listdir(fi_path)\n", + "for fn in fl:\n", + " if os.path.isfile(fi_path + '/' + fn):\n", + " ofn = int(fn.split('.')[0])\n", + " old.append(ofn) \n", + "old.sort()\n", + "\n", + "\n", + "wb = openpyxl.Workbook()\n", + "sheet = wb.active\n", + "i = 0\n", + " \n", + "for item in old:\n", + " m_bh = item\n", + " m_name = dict1[item][0]\n", + " m_dep = dict1[item][1]\n", + " i += 1\n", + " sheet[f'A{i}'] = m_bh\n", + " sheet[f'B{i}'] = m_name\n", + " sheet[f'C{i}'] = m_dep\n", + " \n", + " \n", + "wb.save('data/高新区报告.xlsx') " + ] + }, + { + "cell_type": "markdown", + "id": "72866db8-89be-4498-b854-a3aefe4c897a", + "metadata": {}, + "source": [ + "## 低碳院人员信息转换" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "433c3f52-f4ae-4544-8d06-3636feae71ba", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import os,sys,shutil\n", + "import openpyxl\n", + "import math\n", + "\n", + "fi_xls = os.getcwd() + '/data/北京低碳监测.xlsx'\n", + "fi_path = os.getcwd() + '/file/220724'\n", + "old = []\n", + "dict1 = {}\n", + "\n", + "wb = openpyxl.load_workbook(fi_xls)\n", + "sheet = wb.active\n", + "depart = []\n", + "for n in range(2,sheet.max_row): \n", + " m_name = sheet.cell(n,6).value\n", + " m_depart = sheet.cell(n,3).value\n", + " if sheet.cell(n,4).value is not None:\n", + " dict1[int(sheet.cell(n,4).value)] = [m_name,m_depart]\n", + "\n", + "m_path = os.getcwd()+'/file/220724/new'\n", + "\n", + "fl=os.listdir(fi_path)\n", + "for fn in fl:\n", + " if os.path.isfile(fi_path + '/' + fn):\n", + " ofn = int(fn.split('.')[0])\n", + " old.append(ofn) \n", + "old.sort()\n", + "for n in old: \n", + " o_name = f'{fi_path}/{n}.pdf'\n", + " n_name = f'{fi_path}/new/{str(n).rjust(5,\"0\")}-{dict1[n][0]}.pdf'\n", + " if not os.path.exists(n_name):\n", + " shutil.copyfile(o_name,n_name)\n", + " print(n_name)\n", + "#print(dict1)" + ] + }, + { + "cell_type": "markdown", + "id": "cda8fbed-c0f2-4bfc-a23f-6b412bbcd0ba", + "metadata": {}, + "source": [ + "## 低碳院人员信息核验" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "a34c9f6b-4ef3-4678-89bb-8b692e183968", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import os,sys,shutil\n", + "import openpyxl\n", + "import math\n", + "import json\n", + "\n", + "fi_xls = os.getcwd() + '/data/北京低碳监测.xlsx'\n", + "fi_path = os.getcwd() + '/file/220724'\n", + "old = []\n", + "dict1 = {}\n", + "dict2 = {}\n", + "dict3 = {}\n", + "wb = openpyxl.load_workbook(fi_xls)\n", + "sheet = wb.active\n", + "depart = []\n", + "for n in range(2,sheet.max_row+1): \n", + " m_name = sheet.cell(n,6).value\n", + " m_depart = sheet.cell(n,3).value\n", + " if sheet.cell(n,4).value is not None:\n", + " dict1[int(sheet.cell(n,4).value)] = [m_name,m_depart]\n", + "\n", + "fi_xls = os.getcwd() + '/data/1658883945637.xlsx'\n", + "wb = openpyxl.load_workbook(fi_xls)\n", + "sheet = wb.active\n", + "for n in range(2,sheet.max_row+1): \n", + " m_dm = sheet.cell(n,3).value\n", + " m_depart = sheet.cell(n,2).value\n", + " m_name = sheet.cell(n,4).value\n", + " if sheet.cell(n,3).value is not None:\n", + " dict2[sheet.cell(n,3).value] = [m_name,m_depart,m_dm]\n", + "#print(dict2)\n", + "fl=os.listdir(fi_path)\n", + "for fn in fl:\n", + " if os.path.isfile(fi_path + '/' + fn):\n", + " ofn = int(fn.split('.')[0])\n", + " old.append(ofn) \n", + "old.sort()\n", + "for n in old:\n", + " m_name = dict1[n][0]\n", + " m_depart = dict1[n][1]\n", + " for item in dict2.values():\n", + " if m_name in item and m_depart in item:\n", + " dict3[n] = [m_name,m_depart,item[2]]\n", + " break\n", + "for k in old:\n", + " if k not in dict3.keys():\n", + " print(k)\n", + "with open('data/低碳院报告.json','w') as fl2:\n", + " json.dump(dict3,fl2,ensure_ascii=False) " + ] + }, + { + "cell_type": "markdown", + "id": "3244663e-890c-48de-ae6a-1f666cb1bb76", + "metadata": {}, + "source": [ + "## 低碳院人员附件核验" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "8e20ead8-754a-4535-95ea-b103264e3783", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import json\n", + "import os\n", + "\n", + "fl_name = 'data/低碳院报告.json'\n", + "\n", + "with open(fl_name,'r') as fl:\n", + " m_xx = json.load(fl)\n", + "for k, v in m_xx.items():\n", + " m_bh = str(k).rjust(5,\"0\")\n", + " fl_name = f'file/220724/new/{m_bh}-{v[0]}.pdf'\n", + " if os.path.exists(fl_name):\n", + " print(fl_name)\n", + " else:\n", + " print(f'{v[0]}不存在')" + ] + }, + { + "cell_type": "markdown", + "id": "a7976e2e-23fa-4464-89f5-0e96f721bc95", + "metadata": {}, + "source": [ + "## 低碳院人员导出" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "d77c3ff5-91fb-4449-80fb-57bc467c27bd", + "metadata": {}, + "outputs": [], + "source": [ + "import json\n", + "import openpyxl\n", + " \n", + "\n", + "fl_name = 'data/低碳院报告.json'\n", + "\n", + "with open(fl_name,'r') as fl:\n", + " m_xx = json.load(fl)\n", + " \n", + "wb = openpyxl.Workbook()\n", + "sheet = wb.active\n", + "i = 0\n", + " \n", + "for k, v in m_xx.items():\n", + " m_bh = str(k).rjust(5,\"0\")\n", + " m_name = v[0]\n", + " fl = f'{m_bh}-{v[0]}.pdf'\n", + " m_rec = v[2]+'@ceic.com'\n", + " i += 1\n", + " sheet[f'A{i}'] = i\n", + " sheet[f'B{i}'] = m_bh\n", + " sheet[f'C{i}'] = m_name\n", + " sheet[f'D{i}'] = m_rec \n", + " sheet[f'E{i}'] = fl\n", + " \n", + "wb.save('data/低碳院邮件.xlsx') \n", + " " + ] + }, + { + "cell_type": "markdown", + "id": "bbf0b425-c0ce-4608-ae52-85a78ddcd6c0", + "metadata": {}, + "source": [ + "## 批量更换扩展名" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "2c2bd1d1-4d84-4639-ba20-c97c218ae275", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import glob\n", + "import os,shutil\n", + "\n", + "filepath = 'file/yimo/'\n", + "old = 'SGF'\n", + "new = 'sgf'\n", + "files = glob.glob(f'{filepath}*.{old}')\n", + "for f in files:\n", + " new_file =os.path.splitext(f)[0]+'.'+new\n", + " os.rename(f,new_file)" + ] + }, + { + "cell_type": "markdown", + "id": "69712868-6786-430b-8591-f6828d781588", + "metadata": {}, + "source": [ + "## PDF文件压缩" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "8492dc14-739e-4c78-a302-f4b57ae571dd", + "metadata": {}, + "outputs": [], + "source": [ + "import fitz\n", + "import os\n", + "\n", + "\n", + "def covert2pic(zoom):\n", + " if os.path.exists('.pdf'): # 临时文件，需为空\n", + " os.removedirs('.pdf')\n", + " os.mkdir('.pdf')\n", + " for pg in range(totaling):\n", + " page = doc[pg]\n", + " zoom = int(zoom) #值越大，分辨率越高，文件越清晰\n", + " rotate = int(0)\n", + " print(page)\n", + " trans = fitz.Matrix(zoom / 100.0, zoom / 100.0).preRotate(rotate)\n", + " pm = page.getPixmap(matrix=trans, alpha=False)\n", + " \n", + " lurl='.pdf/%s.jpg' % str(pg+1)\n", + " pm.writePNG(lurl)\n", + " doc.close()\n", + "\n", + "def pic2pdf(obj):\n", + " doc = fitz.open()\n", + " for pg in range(totaling):\n", + " img = '.pdf/%s.jpg' % str(pg+1)\n", + " imgdoc = fitz.open(img) # 打开图片\n", + " pdfbytes = imgdoc.convertToPDF() # 使用图片创建单页的 PDF\n", + " os.remove(img) \n", + " imgpdf = fitz.open(\"pdf\", pdfbytes)\n", + " doc.insertPDF(imgpdf) # 将当前页插入文档\n", + " if os.path.exists(obj): # 若文件存在先删除\n", + " os.remove(obj)\n", + " doc.save(obj) # 保存pdf文件\n", + " doc.close()\n", + "\n", + "\n", + "def pdfz(sor, obj, zoom): \n", + " covert2pic(zoom)\n", + " pic2pdf(obj)\n", + " \n", + "\n", + "\n", + "sor = \"5.pdf\" # 需要压缩的PDF文件\n", + "obj = \"new-\" + sor\n", + "doc = fitz.open(sor) \n", + "totaling = doc.pageCount\n", + "\n", + "zoom = 150 # 清晰度调节，缩放比率\n", + "pdfz(sor, obj, zoom)\n", + "os.removedirs('.pdf')\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "88d84849-5b98-48cb-86b1-e96757a8615f", + "metadata": {}, + "outputs": [], + "source": [ + "from pdf2image import convert_from_path, convert_from_bytes\n", + "import os,sys\n", + "import tempfile\n", + "from pdf2image.exceptions import (\n", + " PDFInfoNotInstalledError,\n", + " PDFPageCountError,\n", + " PDFSyntaxError\n", + ")\n", + "#images = convert_from_path('1.pdf',dpi=200,fmt='jpg', output_folder='./sample_data')\n", + "with tempfile.TemporaryDirectory() as path:\n", + " images_from_path = convert_from_path('检查.pdf', dpi=100,fmt='jpg', output_folder='./pic')\n", + "print(path)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "058a40ba-4948-4675-8400-e4c762e836ee", + "metadata": {}, + "outputs": [], + "source": [ + "import img2pdf \n", + "import os,sys\n", + "import glob\n", + "\n", + "fl=glob.glob('./pic/*.jpg')\n", + "fl.sort()\n", + "a4inpt = (img2pdf.mm_to_pt(210),img2pdf.mm_to_pt(297))\n", + "layout_fun = img2pdf.get_layout_fun(a4inpt)\n", + "with open(\"name.pdf\",\"wb\") as f:\n", + " f.write(img2pdf.convert(fl,layout_fun=layout_fun))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "e997ad75-b2d9-43bf-a1de-8833cfe0cf6a", + "metadata": {}, + "outputs": [], + "source": [ + "import glob\n", + "import fitz # 导入本模块需安装pymupdf库\n", + "import os,sys\n", + "\n", + "def pic2pdf_1(img_path, pdf_path, pdf_name):\n", + " doc = fitz.open()\n", + " fl=os.listdir(img_path)\n", + " fl.sort()\n", + " width, height = fitz.PaperSize(\"a4\")\n", + " #width, height = fitz.paper_size(\"a4\")\n", + " for img in fl:\n", + " fn = img_path+'/'+img\n", + " if os.path.isfile(fn):\n", + " imgdoc = fitz.open(img_path+'/'+img)\n", + " pdfbytes = imgdoc.convertToPDF()\n", + " imgpdf = fitz.open(\"pdf\", pdfbytes,width = width, height = height)\n", + " doc.insertPDF(imgpdf)\n", + " doc.save(pdf_path +'/'+ pdf_name)\n", + " doc.close()\n", + "\n", + "img_path = os.getcwd() +'/pic'\n", + "pdf_path = os.getcwd()\n", + "pic2pdf_1(img_path=img_path, pdf_path=pdf_path, pdf_name='1.pdf')" + ] + }, + { + "cell_type": "markdown", + "id": "1f38e4b6-ef20-4fef-801c-ff47951d2ad6", + "metadata": {}, + "source": [ + "## 图片文件扫描识别" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "8c990b6a-7f8e-4527-a150-65f60bd131ac", + "metadata": {}, + "outputs": [], + "source": [ + "#将指定目录下图片文件进行文字识别\n", + "import os,sys\n", + "from aip import AipOcr\n", + "import glob\n", + "\n", + "\"\"\" 你的 APPID AK SK \"\"\"\n", + "APP_ID = '17553946'\n", + "API_KEY = 'IMC1ss3Tyo3vEAdVH6jgcdv2'\n", + "SECRET_KEY = 'Iua6KdhuDtz159rjzGeFGpqgjhnoU0zZ'\n", + "\n", + "client = AipOcr(APP_ID, API_KEY, SECRET_KEY)\n", + "def get_file_content(filePath):\n", + " with open(filePath, 'rb') as fp:\n", + " return fp.read()\n", + "\n", + "options = {}\n", + "options[\"language_type\"] = \"CHN_ENG\"\n", + "options[\"detect_direction\"] = \"true\"\n", + "options[\"detect_language\"] = \"true\"\n", + "options[\"probability\"] = \"true\"\n", + "\n", + "fi_path = os.getcwd()+'/pic'\n", + "fl = glob.glob(f'{fi_path}/*.jpg')\n", + "fl.sort()\n", + "for fl1 in fl:\n", + " file_name = fl1\n", + " image = get_file_content(file_name)\n", + " result= client.basicGeneral(image, options)\n", + " if 'words_result' in result:\n", + " print('\\n'.join([w['words'] for w in result['words_result']]))\n", + " print('\\n')\n", + " \n", + " " + ] + }, + { + "cell_type": "markdown", + "id": "d936ca99-269b-46f8-8582-fb02ed2cd3cc", + "metadata": {}, + "source": [ + "## word文档读取" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "d8043425-be9e-4e9e-bbfc-3a2d8885a860", + "metadata": {}, + "outputs": [], + "source": [ + "import docx\n", + "import json\n", + "Doc = docx.Document(r\"症状对症处方选穴.docx\")\n", + "#print(\"檔案內含段落數：\",len(Doc.paragraphs),\"\\n\")\n", + "testList = []\n", + "text1 = []\n", + "dict1 = {}\n", + "for text in Doc.paragraphs:\n", + " testList.append(text)\n", + "i = 0\n", + "for pg in testList:\n", + " \n", + " if len(pg.text) >0:\n", + " s = ''.join(pg.text.split()) \n", + " if s[0:1] == '第':\n", + " i += 1\n", + " n = 0\n", + " \n", + " dict1.setdefault(i,{})\n", + " dict1[i]['title'] = pg.text.split()[1]\n", + " dict1[i]['sub'] = {}\n", + " \n", + " #dict1[i]['title'].setdefault(i,{})\n", + " elif s[0:1] == '（':\n", + " sub = s.split('）')[1]\n", + " dict2 = {}\n", + " dict1[i]['sub'].setdefault(sub,[])\n", + " else:\n", + " dict1[i]['sub'][sub].append(s)\n", + "filename = '症状对症处方选穴.json'\n", + "with open(filename,'w') as fl:\n", + " json.dump(dict1, fl,ensure_ascii=False) \n", + "print('ok') " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "c440b599-9c80-4072-8543-d9c381214f1d", + "metadata": {}, + "outputs": [], + "source": [ + "import docx\n", + "import json\n", + "Doc = docx.Document(r\"常见疾病辨病处方选穴.docx\")\n", + "#print(\"檔案內含段落數：\",len(Doc.paragraphs),\"\\n\")\n", + "testList = []\n", + "text1 = []\n", + "dict1 = {}\n", + "for text in Doc.paragraphs:\n", + " testList.append(text)\n", + "i = 0\n", + "for pg in testList:\n", + " \n", + " if len(pg.text) >0:\n", + " s = ''.join(pg.text.split()) \n", + " if s[0:1] == '第':\n", + " i += 1\n", + " n = 0\n", + " \n", + " dict1.setdefault(i,{})\n", + " dict1[i]['title'] = pg.text.split('节')[1]\n", + " dict1[i]['sub'] = {}\n", + " \n", + " #dict1[i]['title'].setdefault(i,{})\n", + " elif s[0:1] == '（':\n", + " sub = s.split('）')[1]\n", + " dict2 = {}\n", + " dict1[i]['sub'].setdefault(sub,[])\n", + " else:\n", + " dict1[i]['sub'][sub].append(s)\n", + "filename = '常见疾病辨病处方选穴.json'\n", + "with open(filename,'w') as fl:\n", + " json.dump(dict1, fl,ensure_ascii=False)\n", + "print('ok') " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "b5e500b5-14d4-4417-8b5e-46df71a6b6b8", + "metadata": {}, + "outputs": [], + "source": [ + "import json\n", + "import re\n", + "filename = '症状对症处方选穴.json'\n", + "pattern = r'[\\d\\.]'\n", + "mo =r'[\\u4e00-\\u9fa5]+'\n", + "dict2 = {}\n", + "with open(filename,'r') as fl:\n", + " dict1 = json.load(fl) \n", + "for k,v in dict1.items():\n", + " m_title = v['title']\n", + " for k1,v1 in v['sub'].items():\n", + " sub_title = k1 \n", + " s = ''\n", + " for mx in v1: \n", + " s = s + mx\n", + " list1 = re.split(pattern, s)\n", + " list2 = []\n", + " for ss in list1:\n", + " if ss != '':\n", + " list3 = re.findall(mo,ss)\n", + " list2.append(list3)\n", + " \n", + " #print(m_title,sub_title,list2)\n", + " dict2.setdefault(m_title,{})\n", + " dict2[m_title][sub_title] = list2\n", + "filename = 'new_症状对症处方选穴.json'\n", + "with open(filename,'w') as fl:\n", + " json.dump(dict2, fl,ensure_ascii=False) \n", + "print('ok') \n", + " " + ] + }, + { + "cell_type": "markdown", + "id": "24d3fdb2-65ac-4a2b-b65a-f64a01a3fdf5", + "metadata": {}, + "source": [ + "## word使用模板生成文档" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "9957a90c-7735-4224-b5b5-4a4b1b7688c9", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import openpyxl\n", + "from docxtpl import DocxTemplate\n", + "\n", + "wb = openpyxl.load_workbook('file/火车餐厅人员信息表1.xlsx')\n", + "sheet = wb.active\n", + "# sheets = wb.sheetnames\n", + "list1 = []\n", + "context = {}\n", + "for n in range(2, sheet.max_row+1):\n", + " dict1 = {}\n", + " dict1['xh'] = sheet.cell(n,1).value\n", + " dict1['xm'] = sheet.cell(n,2).value\n", + " dict1['sfzhm'] = sheet.cell(n,3).value\n", + " dict1['dh'] = sheet.cell(n,4).value\n", + " dict1['cx'] = sheet.cell(n,5).value\n", + " dict1['xzdz'] = sheet.cell(n,6).value\n", + " list1.append(dict1)\n", + "context['info'] = list1\n", + "tpl = DocxTemplate(\"file/火车餐厅人员信息表.docx\")\n", + "tpl.render(context)\n", + "tpl.save('file/test1.docx')" + ] + }, + { + "cell_type": "markdown", + "id": "8a555d4f-8b2c-4f2c-af7e-fe8dfbd33f5f", + "metadata": {}, + "source": [ + "## PDF文件读取" + ] + }, + { + "cell_type": "markdown", + "id": "308511e7-0f2d-40bc-a151-68f26ee635a2", + "metadata": {}, + "source": [ + "### pdfminer读取PDF文件" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "0b0d621c-f2be-4dcb-a1f0-4b16196d25ee", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "from newpdfminer.pdfparser import PDFParser, PDFDocument\n", + "from newpdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter\n", + "from newpdfminer.converter import PDFPageAggregator\n", + "from newpdfminer.layout import LAParams, LTTextBox\n", + "from newpdfminer.pdfinterp import PDFTextExtractionNotAllowed\n", + "\n", + "path = \"file/211027/114.pdf\"\n", + "\n", + "# 用文件对象来创建一个pdf文档分析器\n", + "praser = PDFParser(open(path, 'rb'))\n", + "# 创建一个PDF文档\n", + "doc = PDFDocument()\n", + "# 连接分析器 与文档对象\n", + "praser.set_document(doc)\n", + "doc.set_parser(praser)\n", + "\n", + "# 提供初始化密码\n", + "# 如果没有密码 就创建一个空的字符串\n", + "doc.initialize()\n", + "\n", + "# 检测文档是否提供txt转换，不提供就忽略\n", + "if not doc.is_extractable:\n", + " raise PDFTextExtractionNotAllowed\n", + "else:\n", + " # 创建PDf 资源管理器 来管理共享资源\n", + " rsrcmgr = PDFResourceManager()\n", + " # 创建一个PDF设备对象\n", + " laparams = LAParams()\n", + " device = PDFPageAggregator(rsrcmgr, laparams=laparams)\n", + " # 创建一个PDF解释器对象\n", + " interpreter = PDFPageInterpreter(rsrcmgr, device)\n", + "\n", + " # 循环遍历列表，每次处理一个page的内容\n", + " for page in doc.get_pages():\n", + " interpreter.process_page(page) \n", + " # 接受该页面的LTPage对象\n", + " layout = device.get_result()\n", + " # 这里layout是一个LTPage对象，里面存放着这个 page 解析出的各种对象\n", + " # 包括 LTTextBox, LTFigure, LTImage, LTTextBoxHorizontal 等 \n", + " for x in layout:\n", + " if isinstance(x, LTTextBox):\n", + " print(x.get_text().strip())" + ] + }, + { + "cell_type": "markdown", + "id": "8fff7f1e-b52c-4666-8a2c-e9cde85a8e01", + "metadata": {}, + "source": [ + "### pdfplumber读取PDF文件" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "c8685b70-55b3-439e-852d-c4fbb67b6326", + "metadata": {}, + "outputs": [], + "source": [ + "import pdfplumber\n", + "from PIL import Image\n", + "\n", + "# 读取 PDF 文档\n", + "pdf = pdfplumber.open(\"5.pdf\")\n", + "\n", + "# 获取页数\n", + "print(\"总页数：\",len(pdf.pages))\n", + "print(\"-----------------------------------------\")\n", + "\n", + "# 读取第 4 页；索引从 1 开始\n", + "page = pdf.pages[0] \n", + "print(\"本页：\",page.page_number + 1)\n", + "print(\"-----------------------------------------\")\n", + "# 单页文件存储为图片\n", + "#im = page.to_image()\n", + "#im.save('./5_1.png', format='PNG')\n", + "# 单页文件中原始图片读取，不能读取图表文件\n", + "#imgs = page.images\n", + "#for i, img in enumerate(imgs):\n", + "# size = img['width'], img['height']\n", + "# data = img['stream'].get_data()\n", + "# out_path = f'003pdf_images_{i}.png'\n", + "# with open(out_path, 'wb') as fimg_out:\n", + "# fimg_out.write(data)\n", + "# 导出第 4 页文本\n", + "text = page.extract_text()\n", + "print(text)\n" + ] + }, + { + "cell_type": "markdown", + "id": "59e8775b-e2d6-4963-9376-4a944108ec58", + "metadata": {}, + "source": [ + "### fitz1.8读取PDF文件中的图片" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "5ff3d5dd-b8dd-4707-8e29-26ba6cf97070", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import fitz\n", + "import re\n", + "import os\n", + "\n", + "file_path = '5.pdf' # PDF 文件路径\n", + "dir_path = './data' # 存放图片的文件夹\n", + "\n", + "def pdf2image1(path, pic_path):\n", + " checkIM = r\"/Subtype(?= */Image)\"\n", + " pdf = fitz.open(path)\n", + " lenXREF = pdf.xref_length()\n", + " count = 1\n", + " for i in range(1, lenXREF):\n", + " text = pdf.xref_object(i)\n", + " isImage = re.search(checkIM, text)\n", + " if not isImage:\n", + " continue\n", + " pix = fitz.Pixmap(pdf, i)\n", + " new_name = f\"img_{count}.png\"\n", + " pix.writePNG(os.path.join(pic_path, new_name))\n", + " count += 1\n", + " pix = None\n", + "\n", + "pdf2image1(file_path, dir_path)" + ] + }, + { + "cell_type": "markdown", + "id": "7e86692e-43fe-4aaa-a72f-2fe25fc3597e", + "metadata": {}, + "source": [ + "### Pdf文件拆分" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "c4931fc0-7f0b-4f78-8c8f-151dce930a6b", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import os, sys\n", + "from PyPDF2 import PdfFileWriter, PdfFileReader, PdfFileMerger\n", + "\n", + "file = \"file/211027/114.pdf\"\n", + "pdf_reader = PdfFileReader(file)\n", + "n = pdf_reader.numPages\n", + "print(n)\n", + "pdfWriter = PdfFileWriter()\n", + "pageObj = pdf_reader.getPage(n-2)\n", + "pageObj.scaleBy(1)\n", + "pdfWriter.addPage(pageObj)\n", + "with open('split_114.pdf', 'wb') as pdfOutputFile:\n", + " pdfWriter.write(pdfOutputFile)\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "2382429a-7b73-42bc-bef6-67a0b69a449d", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import fitz\n", + "import os\n", + "\n", + "file = \"file/211027/114.pdf\"\n", + "doc = fitz.open(file)\n", + "n = doc.page_count\n", + "print(n)\n", + "doc2 = fitz.open()\n", + "page = doc[n - 2]\n", + "#doc2.insert_pdf(doc, to_page = n-2) # first 10 pages\n", + "doc2.insert_pdf(doc, from_page = n-2,to_page = n-2)\n", + "#print(type(page))\n", + "#doc2.insert_pdf(page) # last 10 pages\n", + "doc2.save(\"first-and-last-10.pdf\")\n" + ] + }, + { + "cell_type": "markdown", + "id": "18a469e6-8c49-425c-8610-7df4bc59248d", + "metadata": {}, + "source": [ + "### 提取Pdf页面合并文件" + ] + }, + { + "cell_type": "markdown", + "id": "21a588fe-cc3c-473b-b9d0-5fcdb0274c5c", + "metadata": {}, + "source": [ + "#### 简单提取" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "id": "52db5faa-ed27-4ac1-a9e0-b260d8737eb6", + "metadata": { + "execution": { + "iopub.execute_input": "2022-10-05T01:52:52.306098Z", + "iopub.status.busy": "2022-10-05T01:52:52.305370Z", + "iopub.status.idle": "2022-10-05T01:52:53.053478Z", + "shell.execute_reply": "2022-10-05T01:52:53.052957Z", + "shell.execute_reply.started": "2022-10-05T01:52:52.305888Z" + }, + "tags": [] + }, + "outputs": [], + "source": [ + "import fitz\n", + "import os\n", + "import glob\n", + "\n", + "fi_path = 'file/2/'\n", + "dict1 = {}\n", + "fl = glob.glob(f'{fi_path}*.pdf')\n", + "list1 = []\n", + "i = 0\n", + "doc2 = fitz.open()\n", + "for fn in fl:\n", + " doc = fitz.open(fn)\n", + " doc2.insert_pdf(doc, from_page = 1,to_page = 1)\n", + "doc2.save(\"检查.pdf\") \n", + " \n", + " \n", + "\n" + ] + }, + { + "cell_type": "markdown", + "id": "bc39eb1c-e321-4816-9bbd-04a639edc924", + "metadata": {}, + "source": [ + "#### 提取页面并压缩" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "5b3482fa-ae72-4513-b76d-f4f059a73ff1", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import fitz\n", + "import os\n", + "import glob\n", + "import img2pdf\n", + "\n", + "fi_path = 'file/2/'\n", + "zoom = 100\n", + "fl = glob.glob(f'{fi_path}*.pdf')\n", + "\n", + "i = 0\n", + "doc2 = fitz.open()\n", + "for fn in fl:\n", + " doc = fitz.open(fn)\n", + " page = doc[1]\n", + " trans = fitz.Matrix(zoom / 100.0, zoom / 100.0)\n", + " pm = page.get_pixmap(matrix=trans)\n", + " s = os.path.basename(fn).split('.')[0].rjust(5,'0') \n", + " lurl=f'pic/{s}.jpg'\n", + " pm.save(lurl) \n", + "fitz.\n", + "fl=glob.glob('./pic/*.jpg')\n", + "fl.sort()\n", + "a4inpt = (img2pdf.mm_to_pt(210),img2pdf.mm_to_pt(297))\n", + "layout_fun = img2pdf.get_layout_fun(a4inpt)\n", + "with open(\"检查.pdf\",\"wb\") as f:\n", + " f.write(img2pdf.convert(fl,layout_fun=layout_fun))\n", + "\n", + "print('ok!')" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "6e7c67f9-0bef-4860-9dc5-2c8fee885fd4", + "metadata": { + "execution": { + "iopub.execute_input": "2022-10-05T01:53:22.899805Z", + "iopub.status.busy": "2022-10-05T01:53:22.899116Z", + "iopub.status.idle": "2022-10-05T01:59:52.903430Z", + "shell.execute_reply": "2022-10-05T01:59:52.902838Z", + "shell.execute_reply.started": "2022-10-05T01:53:22.899730Z" + }, + "tags": [] + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "ok!\n" + ] + } + ], + "source": [ + "import os\n", + "import glob\n", + "import img2pdf\n", + "import fitz\n", + "\n", + "fi_path = 'file/2022-09-30/'\n", + "zoom = 100\n", + "fl = glob.glob(f'{fi_path}*.pdf')\n", + "\n", + "for fn in fl:\n", + " doc = fitz.open(fn)\n", + " page = doc[1]\n", + " trans = fitz.Matrix(zoom / 100.0, zoom / 100.0)\n", + " pm = page.get_pixmap(matrix=trans)\n", + " s = os.path.basename(fn).split('.')[0].rjust(5,'0') \n", + " lurl=f'pic/{s}.jpg'\n", + " pm.save(lurl) \n", + "\n", + "\n", + "fl=glob.glob('./pic/*.jpg')\n", + "fl.sort()\n", + "a4inpt = (img2pdf.mm_to_pt(210),img2pdf.mm_to_pt(297))\n", + "layout_fun = img2pdf.get_layout_fun(a4inpt)\n", + "i = 1\n", + "n = 1\n", + "list1 = []\n", + "for fl1 in fl:\n", + " list1.append(fl1)\n", + " if len(list1) == 200:\n", + " with open(f\"检查{str(i)}.pdf\",\"wb\") as f:\n", + " f.write(img2pdf.convert(list1,layout_fun=layout_fun))\n", + " i +=1\n", + " list1 = []\n", + "if len(list1)>0:\n", + " with open(f\"检查{str(i)}.pdf\",\"wb\") as f:\n", + " f.write(img2pdf.convert(list1,layout_fun=layout_fun))\n", + "\n", + "print('ok!')" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "f4e85968-7f5b-47f6-afd9-17847bc69b16", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import os\n", + "import glob\n", + "import img2pdf\n", + "\n", + "fi_path = 'file/2/'\n", + "\n", + "fl=glob.glob('./pic/*.jpg')\n", + "fl.sort()\n", + "a4inpt = (img2pdf.mm_to_pt(210),img2pdf.mm_to_pt(297))\n", + "layout_fun = img2pdf.get_layout_fun(a4inpt)\n", + "i = 1\n", + "n = 1\n", + "list1 = []\n", + "for fl1 in fl:\n", + " list1.append(fl1)\n", + " if len(list1) == 200:\n", + " with open(f\"检查{str(i)}.pdf\",\"wb\") as f:\n", + " f.write(img2pdf.convert(list1,layout_fun=layout_fun))\n", + " i +=1\n", + " list1 = []\n", + "if len(list1)>0:\n", + " with open(f\"检查{str(i)}.pdf\",\"wb\") as f:\n", + " f.write(img2pdf.convert(list1,layout_fun=layout_fun))\n", + "\n", + "print('ok!')" + ] + }, + { + "cell_type": "markdown", + "id": "224fca0a-f585-424d-8fcb-59a571215fae", + "metadata": {}, + "source": [ + "#### 使用PyPdf2简单提取" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "e4037936-790d-45f8-b50c-6b1300014f32", + "metadata": {}, + "outputs": [], + "source": [ + "import os, sys\n", + "from PyPDF2 import PdfFileWriter, PdfFileReader, PdfFileMerger\n", + "import glob\n", + "\n", + "fi_path = 'file/2/'\n", + "fl = glob.glob(f'{fi_path}*.pdf')\n", + "pdfWriter = PdfFileWriter()\n", + "i = 0\n", + "doc2 = fitz.open()\n", + "for fn in fl:\n", + " pdf_reader = PdfFileReader(fn)\n", + " pageObj = pdf_reader.getPage(1)\n", + " pdfWriter.addPage(pageObj)\n", + "with open('split_114.pdf', 'wb') as pdfOutputFile: \n", + " pdfWriter.write(pdfOutputFile) \n" + ] + }, + { + "cell_type": "markdown", + "id": "917dfa96-aaea-4c40-8b89-0fe093c65c33", + "metadata": {}, + "source": [ + "## PDF文件读取表格" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "2f9f474d-265c-4beb-bd0e-53372ae9e57e", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import pdfplumber\n", + "import json\n", + "import re\n", + "\n", + "file = \"file/1_中石化北海炼化2020年团体体检报告.pdf\"\n", + "pdf = pdfplumber.open(file)\n", + "list1 = []\n", + "dict1 = {}\n", + "n = 1\n", + "for page in pdf.pages:\n", + " # print(page.extract_text())\n", + " \n", + " \n", + " for pdf_table in page.extract_tables():\n", + " list2 = []\n", + " table = []\n", + " cells = []\n", + " for row in pdf_table:\n", + " if not any(row):\n", + " # 如果一行全为空，则视为一条记录结束\n", + " if any(cells):\n", + " table.append(cells)\n", + " cells = []\n", + " elif all(row):\n", + " # 如果一行全不为空，则本条为新行，上一条结束\n", + " if any(cells):\n", + " table.append(cells)\n", + " cells = []\n", + " table.append(row)\n", + " else:\n", + " if len(cells) == 0:\n", + " cells = row\n", + " else:\n", + " for i in range(len(row)):\n", + " if row[i] is not None and not cells[i]:\n", + " cells[i] = row[i]\n", + " elif row[i] is not None and cells[i]: \n", + " table.append(cells)\n", + " cells = row\n", + " #cells[i] = row[i]\n", + " break\n", + " elif row[i] is None and cells[i]:\n", + " continue\n", + " elif row[i] is None and not cells[i]:\n", + " #cells[i] = row[i]\n", + " continue \n", + " # cells[i] = row[i] if cells[i] is None else cells[i] + row[i]\n", + " \n", + " list2 = [] \n", + " for row in table:\n", + " data =[re.sub('\\s+', '', cell) if cell is not None else None for cell in row]\n", + " print(data)\n", + " \n", + " #print(json.dumps(data_list, indent=2, ensure_ascii=False))\n", + " #with open('Test1.json','a',encoding=\"utf-8\") as file: # json文件的存放位置\n", + " # json.dump(data_list, file, ensure_ascii=False)\n", + " list2.append(data)\n", + " if len(list2) > 0:\n", + " dict1[n] = list2\n", + " #print(dict1)\n", + " #list1.append(list2)\n", + " n +=1\n", + "with open('Test1.json','w',encoding=\"utf-8\") as file:\n", + " json.dump(dict1, file, ensure_ascii=False)\n", + " \n", + "pdf.close()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "71e1da77-6744-4d86-a4bc-88feeb3023e8", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import pdfplumber\n", + "import json\n", + "import re\n", + "\n", + "file = \"file/1_中石化北海炼化2020年团体体检报告.pdf\"\n", + "pdf = pdfplumber.open(file)\n", + "list1 = []\n", + "dict1 = {}\n", + "n = 1\n", + "for page in pdf.pages:\n", + " for pdf_table in page.extract_tables():\n", + " list2 = []\n", + " table = []\n", + " cells = []\n", + " for row in pdf_table:\n", + " print(row)\n", + " print('******')\n", + " print('--------')\n", + " " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "b0764366-12cf-4880-8e0f-9ae18b46d392", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import camelot\n", + "import json\n", + "import re\n", + "\n", + "file = \"file/1_中石化北海炼化2020年团体体检报告.pdf\"\n", + "tables = camelot.read_pdf(file, pages='3',flavor='stream')\n", + "# 2.导出pdf所有的表格为csv文件\n", + "tables.export('foo.json', f='json')\n", + "print('ok!')" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "04dd6436-8374-4096-a2a3-d79f4d93a360", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.8.10" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/.ipynb_checkpoints/文件管理1-checkpoint.ipynb b/.ipynb_checkpoints/文件管理1-checkpoint.ipynb new file mode 100755 index 0000000..bfebbe4 --- /dev/null +++ b/.ipynb_checkpoints/文件管理1-checkpoint.ipynb @@ -0,0 +1,1313 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "333a5431-a697-4330-a587-455d6d18ebb0", + "metadata": {}, + "source": [ + "# 文件管理" + ] + }, + { + "cell_type": "markdown", + "id": "bcd48bb6-4756-4748-ac8b-854eeee92a3b", + "metadata": {}, + "source": [ + "## 数字文件名转换为文本文件名" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "54b320e8-c3c1-4214-9a9e-db13c2558604", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import os,sys,shutil\n", + "import openpyxl\n", + "import math\n", + "\n", + "fi_xls = os.getcwd() + '/data/高新区.xlsx'\n", + "fi_path = os.getcwd() + '/file/220720'\n", + "old = []\n", + "dict1 = {}\n", + "\n", + "wb = openpyxl.load_workbook(fi_xls)\n", + "sheet = wb.active\n", + "depart = []\n", + "for n in range(2,sheet.max_row+1): \n", + " m_name = str(sheet.cell(n,1).value)\n", + " m_depart = sheet.cell(n,5).value\n", + " if m_depart not in depart:\n", + " depart.append(sheet.cell(n,5).value)\n", + " dict1[int(m_name.split('.')[0])] = [sheet.cell(n,2).value.strip(),sheet.cell(n,5).value.strip()]\n", + " \n", + "# 创建部门办公室 \n", + "m_path = os.getcwd()+'/file/220427/new'\n", + "for pn in depart:\n", + " if not os.path.exists(m_path + '/' + pn):\n", + " os.mkdir(m_path + '/' + pn)\n", + "fl=os.listdir(fi_path)\n", + "for fn in fl:\n", + " if os.path.isfile(fi_path + '/' + fn):\n", + " ofn = int(fn.split('.')[0])\n", + " old.append(ofn) \n", + "old.sort()\n", + "for n in old: \n", + " o_name = f'{fi_path}/{n}.pdf'\n", + " n_name = f'{fi_path}/new/{dict1[n][1]}/{str(n).rjust(5,\"0\")}-{dict1[n][0]}.pdf'\n", + " if not os.path.exists(n_name):\n", + " shutil.copyfile(o_name,n_name)\n", + " print(n_name)\n", + "#print(dict1)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "4a43668e-47ba-491f-a29c-e289885badb0", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import os,sys,shutil\n", + "import openpyxl\n", + "import math\n", + "\n", + "fi_xls = os.getcwd() + '/data/高新区.xlsx'\n", + "fi_path = os.getcwd() + '/file/220720'\n", + "old = []\n", + "dict1 = {}\n", + "\n", + "wb = openpyxl.load_workbook(fi_xls)\n", + "sheet = wb.active\n", + "depart = []\n", + "for n in range(2,sheet.max_row+1): \n", + " m_name = str(sheet.cell(n,1).value)\n", + " m_depart = sheet.cell(n,5).value\n", + " if m_depart not in depart:\n", + " depart.append(sheet.cell(n,5).value)\n", + " dict1[sheet.cell(n,4).value] = [sheet.cell(n,6).value,sheet.cell(n,3).value]\n", + "#print(dict1)\n", + "fl=os.listdir(fi_path)\n", + "for fn in fl:\n", + " if os.path.isfile(fi_path + '/' + fn):\n", + " ofn = int(fn.split('.')[0])\n", + " old.append(ofn) \n", + "old.sort()\n", + "\n", + "\n", + "wb = openpyxl.Workbook()\n", + "sheet = wb.active\n", + "i = 0\n", + " \n", + "for item in old:\n", + " m_bh = item\n", + " m_name = dict1[item][0]\n", + " m_dep = dict1[item][1]\n", + " i += 1\n", + " sheet[f'A{i}'] = m_bh\n", + " sheet[f'B{i}'] = m_name\n", + " sheet[f'C{i}'] = m_dep\n", + " \n", + " \n", + "wb.save('data/高新区报告.xlsx') " + ] + }, + { + "cell_type": "markdown", + "id": "72866db8-89be-4498-b854-a3aefe4c897a", + "metadata": {}, + "source": [ + "## 低碳院人员信息转换" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "433c3f52-f4ae-4544-8d06-3636feae71ba", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import os,sys,shutil\n", + "import openpyxl\n", + "import math\n", + "\n", + "fi_xls = os.getcwd() + '/data/北京低碳监测.xlsx'\n", + "fi_path = os.getcwd() + '/file/220724'\n", + "old = []\n", + "dict1 = {}\n", + "\n", + "wb = openpyxl.load_workbook(fi_xls)\n", + "sheet = wb.active\n", + "depart = []\n", + "for n in range(2,sheet.max_row): \n", + " m_name = sheet.cell(n,6).value\n", + " m_depart = sheet.cell(n,3).value\n", + " if sheet.cell(n,4).value is not None:\n", + " dict1[int(sheet.cell(n,4).value)] = [m_name,m_depart]\n", + "\n", + "m_path = os.getcwd()+'/file/220724/new'\n", + "\n", + "fl=os.listdir(fi_path)\n", + "for fn in fl:\n", + " if os.path.isfile(fi_path + '/' + fn):\n", + " ofn = int(fn.split('.')[0])\n", + " old.append(ofn) \n", + "old.sort()\n", + "for n in old: \n", + " o_name = f'{fi_path}/{n}.pdf'\n", + " n_name = f'{fi_path}/new/{str(n).rjust(5,\"0\")}-{dict1[n][0]}.pdf'\n", + " if not os.path.exists(n_name):\n", + " shutil.copyfile(o_name,n_name)\n", + " print(n_name)\n", + "#print(dict1)" + ] + }, + { + "cell_type": "markdown", + "id": "cda8fbed-c0f2-4bfc-a23f-6b412bbcd0ba", + "metadata": {}, + "source": [ + "## 低碳院人员信息核验" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "a34c9f6b-4ef3-4678-89bb-8b692e183968", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import os,sys,shutil\n", + "import openpyxl\n", + "import math\n", + "import json\n", + "\n", + "fi_xls = os.getcwd() + '/data/北京低碳监测.xlsx'\n", + "fi_path = os.getcwd() + '/file/220724'\n", + "old = []\n", + "dict1 = {}\n", + "dict2 = {}\n", + "dict3 = {}\n", + "wb = openpyxl.load_workbook(fi_xls)\n", + "sheet = wb.active\n", + "depart = []\n", + "for n in range(2,sheet.max_row+1): \n", + " m_name = sheet.cell(n,6).value\n", + " m_depart = sheet.cell(n,3).value\n", + " if sheet.cell(n,4).value is not None:\n", + " dict1[int(sheet.cell(n,4).value)] = [m_name,m_depart]\n", + "\n", + "fi_xls = os.getcwd() + '/data/1658883945637.xlsx'\n", + "wb = openpyxl.load_workbook(fi_xls)\n", + "sheet = wb.active\n", + "for n in range(2,sheet.max_row+1): \n", + " m_dm = sheet.cell(n,3).value\n", + " m_depart = sheet.cell(n,2).value\n", + " m_name = sheet.cell(n,4).value\n", + " if sheet.cell(n,3).value is not None:\n", + " dict2[sheet.cell(n,3).value] = [m_name,m_depart,m_dm]\n", + "#print(dict2)\n", + "fl=os.listdir(fi_path)\n", + "for fn in fl:\n", + " if os.path.isfile(fi_path + '/' + fn):\n", + " ofn = int(fn.split('.')[0])\n", + " old.append(ofn) \n", + "old.sort()\n", + "for n in old:\n", + " m_name = dict1[n][0]\n", + " m_depart = dict1[n][1]\n", + " for item in dict2.values():\n", + " if m_name in item and m_depart in item:\n", + " dict3[n] = [m_name,m_depart,item[2]]\n", + " break\n", + "for k in old:\n", + " if k not in dict3.keys():\n", + " print(k)\n", + "with open('data/低碳院报告.json','w') as fl2:\n", + " json.dump(dict3,fl2,ensure_ascii=False) " + ] + }, + { + "cell_type": "markdown", + "id": "3244663e-890c-48de-ae6a-1f666cb1bb76", + "metadata": {}, + "source": [ + "## 低碳院人员附件核验" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "8e20ead8-754a-4535-95ea-b103264e3783", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import json\n", + "import os\n", + "\n", + "fl_name = 'data/低碳院报告.json'\n", + "\n", + "with open(fl_name,'r') as fl:\n", + " m_xx = json.load(fl)\n", + "for k, v in m_xx.items():\n", + " m_bh = str(k).rjust(5,\"0\")\n", + " fl_name = f'file/220724/new/{m_bh}-{v[0]}.pdf'\n", + " if os.path.exists(fl_name):\n", + " print(fl_name)\n", + " else:\n", + " print(f'{v[0]}不存在')" + ] + }, + { + "cell_type": "markdown", + "id": "a7976e2e-23fa-4464-89f5-0e96f721bc95", + "metadata": {}, + "source": [ + "## 低碳院人员导出" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "d77c3ff5-91fb-4449-80fb-57bc467c27bd", + "metadata": {}, + "outputs": [], + "source": [ + "import json\n", + "import openpyxl\n", + " \n", + "\n", + "fl_name = 'data/低碳院报告.json'\n", + "\n", + "with open(fl_name,'r') as fl:\n", + " m_xx = json.load(fl)\n", + " \n", + "wb = openpyxl.Workbook()\n", + "sheet = wb.active\n", + "i = 0\n", + " \n", + "for k, v in m_xx.items():\n", + " m_bh = str(k).rjust(5,\"0\")\n", + " m_name = v[0]\n", + " fl = f'{m_bh}-{v[0]}.pdf'\n", + " m_rec = v[2]+'@ceic.com'\n", + " i += 1\n", + " sheet[f'A{i}'] = i\n", + " sheet[f'B{i}'] = m_bh\n", + " sheet[f'C{i}'] = m_name\n", + " sheet[f'D{i}'] = m_rec \n", + " sheet[f'E{i}'] = fl\n", + " \n", + "wb.save('data/低碳院邮件.xlsx') \n", + " " + ] + }, + { + "cell_type": "markdown", + "id": "bbf0b425-c0ce-4608-ae52-85a78ddcd6c0", + "metadata": {}, + "source": [ + "## 批量更换扩展名" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "2c2bd1d1-4d84-4639-ba20-c97c218ae275", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import glob\n", + "import os,shutil\n", + "\n", + "filepath = 'file/yimo/'\n", + "old = 'SGF'\n", + "new = 'sgf'\n", + "files = glob.glob(f'{filepath}*.{old}')\n", + "for f in files:\n", + " new_file =os.path.splitext(f)[0]+'.'+new\n", + " os.rename(f,new_file)" + ] + }, + { + "cell_type": "markdown", + "id": "69712868-6786-430b-8591-f6828d781588", + "metadata": {}, + "source": [ + "## PDF文件压缩" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "8492dc14-739e-4c78-a302-f4b57ae571dd", + "metadata": {}, + "outputs": [], + "source": [ + "import fitz\n", + "import os\n", + "\n", + "\n", + "def covert2pic(zoom):\n", + " if os.path.exists('.pdf'): # 临时文件，需为空\n", + " os.removedirs('.pdf')\n", + " os.mkdir('.pdf')\n", + " for pg in range(totaling):\n", + " page = doc[pg]\n", + " zoom = int(zoom) #值越大，分辨率越高，文件越清晰\n", + " rotate = int(0)\n", + " print(page)\n", + " trans = fitz.Matrix(zoom / 100.0, zoom / 100.0).preRotate(rotate)\n", + " pm = page.getPixmap(matrix=trans, alpha=False)\n", + " \n", + " lurl='.pdf/%s.jpg' % str(pg+1)\n", + " pm.writePNG(lurl)\n", + " doc.close()\n", + "\n", + "def pic2pdf(obj):\n", + " doc = fitz.open()\n", + " for pg in range(totaling):\n", + " img = '.pdf/%s.jpg' % str(pg+1)\n", + " imgdoc = fitz.open(img) # 打开图片\n", + " pdfbytes = imgdoc.convertToPDF() # 使用图片创建单页的 PDF\n", + " os.remove(img) \n", + " imgpdf = fitz.open(\"pdf\", pdfbytes)\n", + " doc.insertPDF(imgpdf) # 将当前页插入文档\n", + " if os.path.exists(obj): # 若文件存在先删除\n", + " os.remove(obj)\n", + " doc.save(obj) # 保存pdf文件\n", + " doc.close()\n", + "\n", + "\n", + "def pdfz(sor, obj, zoom): \n", + " covert2pic(zoom)\n", + " pic2pdf(obj)\n", + " \n", + "\n", + "\n", + "sor = \"5.pdf\" # 需要压缩的PDF文件\n", + "obj = \"new-\" + sor\n", + "doc = fitz.open(sor) \n", + "totaling = doc.pageCount\n", + "\n", + "zoom = 150 # 清晰度调节，缩放比率\n", + "pdfz(sor, obj, zoom)\n", + "os.removedirs('.pdf')\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "88d84849-5b98-48cb-86b1-e96757a8615f", + "metadata": {}, + "outputs": [], + "source": [ + "from pdf2image import convert_from_path, convert_from_bytes\n", + "import os,sys\n", + "import tempfile\n", + "from pdf2image.exceptions import (\n", + " PDFInfoNotInstalledError,\n", + " PDFPageCountError,\n", + " PDFSyntaxError\n", + ")\n", + "#images = convert_from_path('1.pdf',dpi=200,fmt='jpg', output_folder='./sample_data')\n", + "with tempfile.TemporaryDirectory() as path:\n", + " images_from_path = convert_from_path('检查.pdf', dpi=100,fmt='jpg', output_folder='./pic')\n", + "print(path)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "058a40ba-4948-4675-8400-e4c762e836ee", + "metadata": {}, + "outputs": [], + "source": [ + "import img2pdf \n", + "import os,sys\n", + "import glob\n", + "\n", + "fl=glob.glob('./pic/*.jpg')\n", + "fl.sort()\n", + "a4inpt = (img2pdf.mm_to_pt(210),img2pdf.mm_to_pt(297))\n", + "layout_fun = img2pdf.get_layout_fun(a4inpt)\n", + "with open(\"name.pdf\",\"wb\") as f:\n", + " f.write(img2pdf.convert(fl,layout_fun=layout_fun))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "e997ad75-b2d9-43bf-a1de-8833cfe0cf6a", + "metadata": {}, + "outputs": [], + "source": [ + "import glob\n", + "import fitz # 导入本模块需安装pymupdf库\n", + "import os,sys\n", + "\n", + "def pic2pdf_1(img_path, pdf_path, pdf_name):\n", + " doc = fitz.open()\n", + " fl=os.listdir(img_path)\n", + " fl.sort()\n", + " width, height = fitz.PaperSize(\"a4\")\n", + " #width, height = fitz.paper_size(\"a4\")\n", + " for img in fl:\n", + " fn = img_path+'/'+img\n", + " if os.path.isfile(fn):\n", + " imgdoc = fitz.open(img_path+'/'+img)\n", + " pdfbytes = imgdoc.convertToPDF()\n", + " imgpdf = fitz.open(\"pdf\", pdfbytes,width = width, height = height)\n", + " doc.insertPDF(imgpdf)\n", + " doc.save(pdf_path +'/'+ pdf_name)\n", + " doc.close()\n", + "\n", + "img_path = os.getcwd() +'/pic'\n", + "pdf_path = os.getcwd()\n", + "pic2pdf_1(img_path=img_path, pdf_path=pdf_path, pdf_name='1.pdf')" + ] + }, + { + "cell_type": "markdown", + "id": "1f38e4b6-ef20-4fef-801c-ff47951d2ad6", + "metadata": {}, + "source": [ + "## 图片文件扫描识别" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "8c990b6a-7f8e-4527-a150-65f60bd131ac", + "metadata": {}, + "outputs": [], + "source": [ + "#将指定目录下图片文件进行文字识别\n", + "import os,sys\n", + "from aip import AipOcr\n", + "import glob\n", + "\n", + "\"\"\" 你的 APPID AK SK \"\"\"\n", + "APP_ID = '17553946'\n", + "API_KEY = 'IMC1ss3Tyo3vEAdVH6jgcdv2'\n", + "SECRET_KEY = 'Iua6KdhuDtz159rjzGeFGpqgjhnoU0zZ'\n", + "\n", + "client = AipOcr(APP_ID, API_KEY, SECRET_KEY)\n", + "def get_file_content(filePath):\n", + " with open(filePath, 'rb') as fp:\n", + " return fp.read()\n", + "\n", + "options = {}\n", + "options[\"language_type\"] = \"CHN_ENG\"\n", + "options[\"detect_direction\"] = \"true\"\n", + "options[\"detect_language\"] = \"true\"\n", + "options[\"probability\"] = \"true\"\n", + "\n", + "fi_path = os.getcwd()+'/pic'\n", + "fl = glob.glob(f'{fi_path}/*.jpg')\n", + "fl.sort()\n", + "for fl1 in fl:\n", + " file_name = fl1\n", + " image = get_file_content(file_name)\n", + " result= client.basicGeneral(image, options)\n", + " if 'words_result' in result:\n", + " print('\\n'.join([w['words'] for w in result['words_result']]))\n", + " print('\\n')\n", + " \n", + " " + ] + }, + { + "cell_type": "markdown", + "id": "d936ca99-269b-46f8-8582-fb02ed2cd3cc", + "metadata": {}, + "source": [ + "## word文档读取" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "d8043425-be9e-4e9e-bbfc-3a2d8885a860", + "metadata": {}, + "outputs": [], + "source": [ + "import docx\n", + "import json\n", + "Doc = docx.Document(r\"症状对症处方选穴.docx\")\n", + "#print(\"檔案內含段落數：\",len(Doc.paragraphs),\"\\n\")\n", + "testList = []\n", + "text1 = []\n", + "dict1 = {}\n", + "for text in Doc.paragraphs:\n", + " testList.append(text)\n", + "i = 0\n", + "for pg in testList:\n", + " \n", + " if len(pg.text) >0:\n", + " s = ''.join(pg.text.split()) \n", + " if s[0:1] == '第':\n", + " i += 1\n", + " n = 0\n", + " \n", + " dict1.setdefault(i,{})\n", + " dict1[i]['title'] = pg.text.split()[1]\n", + " dict1[i]['sub'] = {}\n", + " \n", + " #dict1[i]['title'].setdefault(i,{})\n", + " elif s[0:1] == '（':\n", + " sub = s.split('）')[1]\n", + " dict2 = {}\n", + " dict1[i]['sub'].setdefault(sub,[])\n", + " else:\n", + " dict1[i]['sub'][sub].append(s)\n", + "filename = '症状对症处方选穴.json'\n", + "with open(filename,'w') as fl:\n", + " json.dump(dict1, fl,ensure_ascii=False) \n", + "print('ok') " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "c440b599-9c80-4072-8543-d9c381214f1d", + "metadata": {}, + "outputs": [], + "source": [ + "import docx\n", + "import json\n", + "Doc = docx.Document(r\"常见疾病辨病处方选穴.docx\")\n", + "#print(\"檔案內含段落數：\",len(Doc.paragraphs),\"\\n\")\n", + "testList = []\n", + "text1 = []\n", + "dict1 = {}\n", + "for text in Doc.paragraphs:\n", + " testList.append(text)\n", + "i = 0\n", + "for pg in testList:\n", + " \n", + " if len(pg.text) >0:\n", + " s = ''.join(pg.text.split()) \n", + " if s[0:1] == '第':\n", + " i += 1\n", + " n = 0\n", + " \n", + " dict1.setdefault(i,{})\n", + " dict1[i]['title'] = pg.text.split('节')[1]\n", + " dict1[i]['sub'] = {}\n", + " \n", + " #dict1[i]['title'].setdefault(i,{})\n", + " elif s[0:1] == '（':\n", + " sub = s.split('）')[1]\n", + " dict2 = {}\n", + " dict1[i]['sub'].setdefault(sub,[])\n", + " else:\n", + " dict1[i]['sub'][sub].append(s)\n", + "filename = '常见疾病辨病处方选穴.json'\n", + "with open(filename,'w') as fl:\n", + " json.dump(dict1, fl,ensure_ascii=False)\n", + "print('ok') " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "b5e500b5-14d4-4417-8b5e-46df71a6b6b8", + "metadata": {}, + "outputs": [], + "source": [ + "import json\n", + "import re\n", + "filename = '症状对症处方选穴.json'\n", + "pattern = r'[\\d\\.]'\n", + "mo =r'[\\u4e00-\\u9fa5]+'\n", + "dict2 = {}\n", + "with open(filename,'r') as fl:\n", + " dict1 = json.load(fl) \n", + "for k,v in dict1.items():\n", + " m_title = v['title']\n", + " for k1,v1 in v['sub'].items():\n", + " sub_title = k1 \n", + " s = ''\n", + " for mx in v1: \n", + " s = s + mx\n", + " list1 = re.split(pattern, s)\n", + " list2 = []\n", + " for ss in list1:\n", + " if ss != '':\n", + " list3 = re.findall(mo,ss)\n", + " list2.append(list3)\n", + " \n", + " #print(m_title,sub_title,list2)\n", + " dict2.setdefault(m_title,{})\n", + " dict2[m_title][sub_title] = list2\n", + "filename = 'new_症状对症处方选穴.json'\n", + "with open(filename,'w') as fl:\n", + " json.dump(dict2, fl,ensure_ascii=False) \n", + "print('ok') \n", + " " + ] + }, + { + "cell_type": "markdown", + "id": "24d3fdb2-65ac-4a2b-b65a-f64a01a3fdf5", + "metadata": {}, + "source": [ + "## word使用模板生成文档" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "9957a90c-7735-4224-b5b5-4a4b1b7688c9", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import openpyxl\n", + "from docxtpl import DocxTemplate\n", + "\n", + "wb = openpyxl.load_workbook('file/火车餐厅人员信息表1.xlsx')\n", + "sheet = wb.active\n", + "# sheets = wb.sheetnames\n", + "list1 = []\n", + "context = {}\n", + "for n in range(2, sheet.max_row+1):\n", + " dict1 = {}\n", + " dict1['xh'] = sheet.cell(n,1).value\n", + " dict1['xm'] = sheet.cell(n,2).value\n", + " dict1['sfzhm'] = sheet.cell(n,3).value\n", + " dict1['dh'] = sheet.cell(n,4).value\n", + " dict1['cx'] = sheet.cell(n,5).value\n", + " dict1['xzdz'] = sheet.cell(n,6).value\n", + " list1.append(dict1)\n", + "context['info'] = list1\n", + "tpl = DocxTemplate(\"file/火车餐厅人员信息表.docx\")\n", + "tpl.render(context)\n", + "tpl.save('file/test1.docx')" + ] + }, + { + "cell_type": "markdown", + "id": "8a555d4f-8b2c-4f2c-af7e-fe8dfbd33f5f", + "metadata": {}, + "source": [ + "## PDF文件读取" + ] + }, + { + "cell_type": "markdown", + "id": "308511e7-0f2d-40bc-a151-68f26ee635a2", + "metadata": {}, + "source": [ + "### pdfminer读取PDF文件" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "0b0d621c-f2be-4dcb-a1f0-4b16196d25ee", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "from newpdfminer.pdfparser import PDFParser, PDFDocument\n", + "from newpdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter\n", + "from newpdfminer.converter import PDFPageAggregator\n", + "from newpdfminer.layout import LAParams, LTTextBox\n", + "from newpdfminer.pdfinterp import PDFTextExtractionNotAllowed\n", + "\n", + "path = \"file/211027/114.pdf\"\n", + "\n", + "# 用文件对象来创建一个pdf文档分析器\n", + "praser = PDFParser(open(path, 'rb'))\n", + "# 创建一个PDF文档\n", + "doc = PDFDocument()\n", + "# 连接分析器 与文档对象\n", + "praser.set_document(doc)\n", + "doc.set_parser(praser)\n", + "\n", + "# 提供初始化密码\n", + "# 如果没有密码 就创建一个空的字符串\n", + "doc.initialize()\n", + "\n", + "# 检测文档是否提供txt转换，不提供就忽略\n", + "if not doc.is_extractable:\n", + " raise PDFTextExtractionNotAllowed\n", + "else:\n", + " # 创建PDf 资源管理器 来管理共享资源\n", + " rsrcmgr = PDFResourceManager()\n", + " # 创建一个PDF设备对象\n", + " laparams = LAParams()\n", + " device = PDFPageAggregator(rsrcmgr, laparams=laparams)\n", + " # 创建一个PDF解释器对象\n", + " interpreter = PDFPageInterpreter(rsrcmgr, device)\n", + "\n", + " # 循环遍历列表，每次处理一个page的内容\n", + " for page in doc.get_pages():\n", + " interpreter.process_page(page) \n", + " # 接受该页面的LTPage对象\n", + " layout = device.get_result()\n", + " # 这里layout是一个LTPage对象，里面存放着这个 page 解析出的各种对象\n", + " # 包括 LTTextBox, LTFigure, LTImage, LTTextBoxHorizontal 等 \n", + " for x in layout:\n", + " if isinstance(x, LTTextBox):\n", + " print(x.get_text().strip())" + ] + }, + { + "cell_type": "markdown", + "id": "8fff7f1e-b52c-4666-8a2c-e9cde85a8e01", + "metadata": {}, + "source": [ + "### pdfplumber读取PDF文件" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "c8685b70-55b3-439e-852d-c4fbb67b6326", + "metadata": {}, + "outputs": [], + "source": [ + "import pdfplumber\n", + "from PIL import Image\n", + "\n", + "# 读取 PDF 文档\n", + "pdf = pdfplumber.open(\"5.pdf\")\n", + "\n", + "# 获取页数\n", + "print(\"总页数：\",len(pdf.pages))\n", + "print(\"-----------------------------------------\")\n", + "\n", + "# 读取第 4 页；索引从 1 开始\n", + "page = pdf.pages[0] \n", + "print(\"本页：\",page.page_number + 1)\n", + "print(\"-----------------------------------------\")\n", + "# 单页文件存储为图片\n", + "#im = page.to_image()\n", + "#im.save('./5_1.png', format='PNG')\n", + "# 单页文件中原始图片读取，不能读取图表文件\n", + "#imgs = page.images\n", + "#for i, img in enumerate(imgs):\n", + "# size = img['width'], img['height']\n", + "# data = img['stream'].get_data()\n", + "# out_path = f'003pdf_images_{i}.png'\n", + "# with open(out_path, 'wb') as fimg_out:\n", + "# fimg_out.write(data)\n", + "# 导出第 4 页文本\n", + "text = page.extract_text()\n", + "print(text)\n" + ] + }, + { + "cell_type": "markdown", + "id": "59e8775b-e2d6-4963-9376-4a944108ec58", + "metadata": {}, + "source": [ + "### fitz1.8读取PDF文件中的图片" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "5ff3d5dd-b8dd-4707-8e29-26ba6cf97070", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import fitz\n", + "import re\n", + "import os\n", + "\n", + "file_path = '5.pdf' # PDF 文件路径\n", + "dir_path = './data' # 存放图片的文件夹\n", + "\n", + "def pdf2image1(path, pic_path):\n", + " checkIM = r\"/Subtype(?= */Image)\"\n", + " pdf = fitz.open(path)\n", + " lenXREF = pdf.xref_length()\n", + " count = 1\n", + " for i in range(1, lenXREF):\n", + " text = pdf.xref_object(i)\n", + " isImage = re.search(checkIM, text)\n", + " if not isImage:\n", + " continue\n", + " pix = fitz.Pixmap(pdf, i)\n", + " new_name = f\"img_{count}.png\"\n", + " pix.writePNG(os.path.join(pic_path, new_name))\n", + " count += 1\n", + " pix = None\n", + "\n", + "pdf2image1(file_path, dir_path)" + ] + }, + { + "cell_type": "markdown", + "id": "7e86692e-43fe-4aaa-a72f-2fe25fc3597e", + "metadata": {}, + "source": [ + "### Pdf文件拆分" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "c4931fc0-7f0b-4f78-8c8f-151dce930a6b", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import os, sys\n", + "from PyPDF2 import PdfFileWriter, PdfFileReader, PdfFileMerger\n", + "\n", + "file = \"file/211027/114.pdf\"\n", + "pdf_reader = PdfFileReader(file)\n", + "n = pdf_reader.numPages\n", + "print(n)\n", + "pdfWriter = PdfFileWriter()\n", + "pageObj = pdf_reader.getPage(n-2)\n", + "pageObj.scaleBy(1)\n", + "pdfWriter.addPage(pageObj)\n", + "with open('split_114.pdf', 'wb') as pdfOutputFile:\n", + " pdfWriter.write(pdfOutputFile)\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "2382429a-7b73-42bc-bef6-67a0b69a449d", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import fitz\n", + "import os\n", + "\n", + "file = \"file/211027/114.pdf\"\n", + "doc = fitz.open(file)\n", + "n = doc.page_count\n", + "print(n)\n", + "doc2 = fitz.open()\n", + "page = doc[n - 2]\n", + "#doc2.insert_pdf(doc, to_page = n-2) # first 10 pages\n", + "doc2.insert_pdf(doc, from_page = n-2,to_page = n-2)\n", + "#print(type(page))\n", + "#doc2.insert_pdf(page) # last 10 pages\n", + "doc2.save(\"first-and-last-10.pdf\")\n" + ] + }, + { + "cell_type": "markdown", + "id": "18a469e6-8c49-425c-8610-7df4bc59248d", + "metadata": {}, + "source": [ + "### 提取Pdf页面合并文件" + ] + }, + { + "cell_type": "markdown", + "id": "21a588fe-cc3c-473b-b9d0-5fcdb0274c5c", + "metadata": {}, + "source": [ + "#### 简单提取" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "id": "52db5faa-ed27-4ac1-a9e0-b260d8737eb6", + "metadata": { + "execution": { + "iopub.execute_input": "2022-10-05T01:52:52.306098Z", + "iopub.status.busy": "2022-10-05T01:52:52.305370Z", + "iopub.status.idle": "2022-10-05T01:52:53.053478Z", + "shell.execute_reply": "2022-10-05T01:52:53.052957Z", + "shell.execute_reply.started": "2022-10-05T01:52:52.305888Z" + }, + "tags": [] + }, + "outputs": [], + "source": [ + "import fitz\n", + "import os\n", + "import glob\n", + "\n", + "fi_path = 'file/2/'\n", + "dict1 = {}\n", + "fl = glob.glob(f'{fi_path}*.pdf')\n", + "list1 = []\n", + "i = 0\n", + "doc2 = fitz.open()\n", + "for fn in fl:\n", + " doc = fitz.open(fn)\n", + " doc2.insert_pdf(doc, from_page = 1,to_page = 1)\n", + "doc2.save(\"检查.pdf\") \n", + " \n", + " \n", + "\n" + ] + }, + { + "cell_type": "markdown", + "id": "bc39eb1c-e321-4816-9bbd-04a639edc924", + "metadata": {}, + "source": [ + "#### 提取页面并压缩" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "5b3482fa-ae72-4513-b76d-f4f059a73ff1", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import fitz\n", + "import os\n", + "import glob\n", + "import img2pdf\n", + "\n", + "fi_path = 'file/2/'\n", + "zoom = 100\n", + "fl = glob.glob(f'{fi_path}*.pdf')\n", + "\n", + "i = 0\n", + "doc2 = fitz.open()\n", + "for fn in fl:\n", + " doc = fitz.open(fn)\n", + " page = doc[1]\n", + " trans = fitz.Matrix(zoom / 100.0, zoom / 100.0)\n", + " pm = page.get_pixmap(matrix=trans)\n", + " s = os.path.basename(fn).split('.')[0].rjust(5,'0') \n", + " lurl=f'pic/{s}.jpg'\n", + " pm.save(lurl) \n", + "fitz.\n", + "fl=glob.glob('./pic/*.jpg')\n", + "fl.sort()\n", + "a4inpt = (img2pdf.mm_to_pt(210),img2pdf.mm_to_pt(297))\n", + "layout_fun = img2pdf.get_layout_fun(a4inpt)\n", + "with open(\"检查.pdf\",\"wb\") as f:\n", + " f.write(img2pdf.convert(fl,layout_fun=layout_fun))\n", + "\n", + "print('ok!')" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "6e7c67f9-0bef-4860-9dc5-2c8fee885fd4", + "metadata": { + "execution": { + "iopub.execute_input": "2022-10-05T01:53:22.899805Z", + "iopub.status.busy": "2022-10-05T01:53:22.899116Z", + "iopub.status.idle": "2022-10-05T01:59:52.903430Z", + "shell.execute_reply": "2022-10-05T01:59:52.902838Z", + "shell.execute_reply.started": "2022-10-05T01:53:22.899730Z" + }, + "tags": [] + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "ok!\n" + ] + } + ], + "source": [ + "import os\n", + "import glob\n", + "import img2pdf\n", + "import fitz\n", + "\n", + "fi_path = 'file/2022-09-30/'\n", + "zoom = 100\n", + "fl = glob.glob(f'{fi_path}*.pdf')\n", + "\n", + "for fn in fl:\n", + " doc = fitz.open(fn)\n", + " page = doc[1]\n", + " trans = fitz.Matrix(zoom / 100.0, zoom / 100.0)\n", + " pm = page.get_pixmap(matrix=trans)\n", + " s = os.path.basename(fn).split('.')[0].rjust(5,'0') \n", + " lurl=f'pic/{s}.jpg'\n", + " pm.save(lurl) \n", + "\n", + "\n", + "fl=glob.glob('./pic/*.jpg')\n", + "fl.sort()\n", + "a4inpt = (img2pdf.mm_to_pt(210),img2pdf.mm_to_pt(297))\n", + "layout_fun = img2pdf.get_layout_fun(a4inpt)\n", + "i = 1\n", + "n = 1\n", + "list1 = []\n", + "for fl1 in fl:\n", + " list1.append(fl1)\n", + " if len(list1) == 200:\n", + " with open(f\"检查{str(i)}.pdf\",\"wb\") as f:\n", + " f.write(img2pdf.convert(list1,layout_fun=layout_fun))\n", + " i +=1\n", + " list1 = []\n", + "if len(list1)>0:\n", + " with open(f\"检查{str(i)}.pdf\",\"wb\") as f:\n", + " f.write(img2pdf.convert(list1,layout_fun=layout_fun))\n", + "\n", + "print('ok!')" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "f4e85968-7f5b-47f6-afd9-17847bc69b16", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import os\n", + "import glob\n", + "import img2pdf\n", + "\n", + "fi_path = 'file/2/'\n", + "\n", + "fl=glob.glob('./pic/*.jpg')\n", + "fl.sort()\n", + "a4inpt = (img2pdf.mm_to_pt(210),img2pdf.mm_to_pt(297))\n", + "layout_fun = img2pdf.get_layout_fun(a4inpt)\n", + "i = 1\n", + "n = 1\n", + "list1 = []\n", + "for fl1 in fl:\n", + " list1.append(fl1)\n", + " if len(list1) == 200:\n", + " with open(f\"检查{str(i)}.pdf\",\"wb\") as f:\n", + " f.write(img2pdf.convert(list1,layout_fun=layout_fun))\n", + " i +=1\n", + " list1 = []\n", + "if len(list1)>0:\n", + " with open(f\"检查{str(i)}.pdf\",\"wb\") as f:\n", + " f.write(img2pdf.convert(list1,layout_fun=layout_fun))\n", + "\n", + "print('ok!')" + ] + }, + { + "cell_type": "markdown", + "id": "224fca0a-f585-424d-8fcb-59a571215fae", + "metadata": {}, + "source": [ + "#### 使用PyPdf2简单提取" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "e4037936-790d-45f8-b50c-6b1300014f32", + "metadata": {}, + "outputs": [], + "source": [ + "import os, sys\n", + "from PyPDF2 import PdfFileWriter, PdfFileReader, PdfFileMerger\n", + "import glob\n", + "\n", + "fi_path = 'file/2/'\n", + "fl = glob.glob(f'{fi_path}*.pdf')\n", + "pdfWriter = PdfFileWriter()\n", + "i = 0\n", + "doc2 = fitz.open()\n", + "for fn in fl:\n", + " pdf_reader = PdfFileReader(fn)\n", + " pageObj = pdf_reader.getPage(1)\n", + " pdfWriter.addPage(pageObj)\n", + "with open('split_114.pdf', 'wb') as pdfOutputFile: \n", + " pdfWriter.write(pdfOutputFile) \n" + ] + }, + { + "cell_type": "markdown", + "id": "917dfa96-aaea-4c40-8b89-0fe093c65c33", + "metadata": {}, + "source": [ + "## PDF文件读取表格" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "2f9f474d-265c-4beb-bd0e-53372ae9e57e", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import pdfplumber\n", + "import json\n", + "import re\n", + "\n", + "file = \"file/1_中石化北海炼化2020年团体体检报告.pdf\"\n", + "pdf = pdfplumber.open(file)\n", + "list1 = []\n", + "dict1 = {}\n", + "n = 1\n", + "for page in pdf.pages:\n", + " # print(page.extract_text())\n", + " \n", + " \n", + " for pdf_table in page.extract_tables():\n", + " list2 = []\n", + " table = []\n", + " cells = []\n", + " for row in pdf_table:\n", + " if not any(row):\n", + " # 如果一行全为空，则视为一条记录结束\n", + " if any(cells):\n", + " table.append(cells)\n", + " cells = []\n", + " elif all(row):\n", + " # 如果一行全不为空，则本条为新行，上一条结束\n", + " if any(cells):\n", + " table.append(cells)\n", + " cells = []\n", + " table.append(row)\n", + " else:\n", + " if len(cells) == 0:\n", + " cells = row\n", + " else:\n", + " for i in range(len(row)):\n", + " if row[i] is not None and not cells[i]:\n", + " cells[i] = row[i]\n", + " elif row[i] is not None and cells[i]: \n", + " table.append(cells)\n", + " cells = row\n", + " #cells[i] = row[i]\n", + " break\n", + " elif row[i] is None and cells[i]:\n", + " continue\n", + " elif row[i] is None and not cells[i]:\n", + " #cells[i] = row[i]\n", + " continue \n", + " # cells[i] = row[i] if cells[i] is None else cells[i] + row[i]\n", + " \n", + " list2 = [] \n", + " for row in table:\n", + " data =[re.sub('\\s+', '', cell) if cell is not None else None for cell in row]\n", + " print(data)\n", + " \n", + " #print(json.dumps(data_list, indent=2, ensure_ascii=False))\n", + " #with open('Test1.json','a',encoding=\"utf-8\") as file: # json文件的存放位置\n", + " # json.dump(data_list, file, ensure_ascii=False)\n", + " list2.append(data)\n", + " if len(list2) > 0:\n", + " dict1[n] = list2\n", + " #print(dict1)\n", + " #list1.append(list2)\n", + " n +=1\n", + "with open('Test1.json','w',encoding=\"utf-8\") as file:\n", + " json.dump(dict1, file, ensure_ascii=False)\n", + " \n", + "pdf.close()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "71e1da77-6744-4d86-a4bc-88feeb3023e8", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import pdfplumber\n", + "import json\n", + "import re\n", + "\n", + "file = \"file/1_中石化北海炼化2020年团体体检报告.pdf\"\n", + "pdf = pdfplumber.open(file)\n", + "list1 = []\n", + "dict1 = {}\n", + "n = 1\n", + "for page in pdf.pages:\n", + " for pdf_table in page.extract_tables():\n", + " list2 = []\n", + " table = []\n", + " cells = []\n", + " for row in pdf_table:\n", + " print(row)\n", + " print('******')\n", + " print('--------')\n", + " " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "b0764366-12cf-4880-8e0f-9ae18b46d392", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import camelot\n", + "import json\n", + "import re\n", + "\n", + "file = \"file/1_中石化北海炼化2020年团体体检报告.pdf\"\n", + "tables = camelot.read_pdf(file, pages='3',flavor='stream')\n", + "# 2.导出pdf所有的表格为csv文件\n", + "tables.export('foo.json', f='json')\n", + "print('ok!')" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "04dd6436-8374-4096-a2a3-d79f4d93a360", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.8.10" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +}