20211108

文件管理1.ipynb

@@ -29,8 +29,8 @@
     "import openpyxl\n",
     "import math\n",
     "\n",
-    "fi_xls = os.getcwd() + '/file/中国石油化工股份有限公司安庆炼化分公司员工在职人员名单.xlsx'\n",
-    "fi_path = os.getcwd() + '/file/210924'\n",
+    "fi_xls = os.getcwd() + '/北海炼化名单表(202110).xlsx'\n",
+    "fi_path = os.getcwd() + '/file/211028'\n",
     "old = []\n",
     "dict1 = {}\n",
     "\n",
@@ -38,14 +38,14 @@
     "sheet = wb.active\n",
     "depart = []\n",
     "for n in range(2,sheet.max_row+1):    \n",
-    "    m_name = sheet.cell(n,1).value.strip()\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/210924/new'\n",
+    "m_path = os.getcwd()+'/file/211028/new'\n",
     "for pn in depart:\n",
     "    if not os.path.exists(m_path + '/' + pn):\n",
     "        os.mkdir(m_path + '/' + pn)\n",
@@ -402,7 +402,9 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "0b0d621c-f2be-4dcb-a1f0-4b16196d25ee",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "from newpdfminer.pdfparser import PDFParser, PDFDocument\n",
@@ -411,7 +413,7 @@
     "from newpdfminer.layout import LAParams, LTTextBox\n",
     "from newpdfminer.pdfinterp import PDFTextExtractionNotAllowed\n",
     "\n",
-    "path = \"5.pdf\"\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",
@@ -504,9 +506,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": null,
    "id": "5ff3d5dd-b8dd-4707-8e29-26ba6cf97070",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "import fitz\n",
@@ -534,6 +538,71 @@
     "\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": "code",
+   "execution_count": null,
+   "id": "ed609077-c179-4041-8ad2-200f02c4ea83",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {