20221101

体测单位/天津石化.ipynb

@@ -169,6 +169,14 @@
     "## 按照日期进行报告分类"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "3d57ff66-69c3-4c13-811b-f1e13b404077",
+   "metadata": {},
+   "source": [
+    "### 按照体测明细分类"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -218,6 +226,14 @@
     "print('ok!')"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "ae2b17bd-38b9-4809-affb-01441a5581eb",
+   "metadata": {},
+   "source": [
+    "### 按照报告生成日期分类"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -229,24 +245,128 @@
    "source": [
     "import json\n",
     "import time\n",
+    "import csv\n",
     "import os,sys,shutil\n",
     "import glob\n",
     "\n",
-    "fi_list = []\n",
+    "dict1 = {}\n",
-    "m_time = '20221020'\n",
+    "list1 = []\n",
-    "m_path = 'file/134/20221020/'\n",
+    "\n",
-    "fl=glob.glob(f'{m_path}*_????????.pdf')\n",
+    "m_path = 'file/134'\n",
-    "for fn in fl:\n",
+    "mrq = '20221028'\n",
-    "    f_date = os.path.basename(fn).split('_')[1][:8]\n",
+    "if not os.path.exists(m_path + '/' + mrq):\n",
-    "    if m_time <= f_date:\n",
+    "    os.mkdir(m_path + '/' + mrq)\n",
-    "        fi_list.append(fn)\n",
+    "fls = glob.glob(f'file/new/*.pdf')\n",
-    "fi_list"
+    "for fn in fls:\n",
+    "    #old = os.path.basename(fn).split('.')[0].rjust(8,'0') \n",
+    "    old = os.path.basename(fn).split('.')[0]    \n",
+    "    n_name = f'{m_path}/{mrq}/{str(old).rjust(8,\"0\")}_{mrq}.pdf'\n",
+    "    if not os.path.exists(n_name):\n",
+    "        shutil.copyfile(fn,n_name)\n",
+    "print('ok!')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "838ec7d3-137c-4ccd-9f16-7b6312d1ffa6",
+   "metadata": {},
+   "source": [
+    "### PDF文件压缩"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "c758420a-e2a4-4260-a571-ff06ed030076",
+   "id": "a6ab0943-b018-4dd6-9176-85a762f9f60c",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import fitz\n",
+    "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",
+    "import img2pdf  \n",
+    "import glob\n",
+    "import shutil\n",
+    "\n",
+    "def covert2pic(old_fn):\n",
+    "    if os.path.exists('.pdf'):       # 临时文件，需为空\n",
+    "         shutil.rmtree('.pdf')\n",
+    "    os.mkdir('.pdf')\n",
+    "    with tempfile.TemporaryDirectory() as path:\n",
+    "        images_from_path = convert_from_path(old_fn, dpi=100,fmt='jpg', output_folder='.pdf')\n",
+    "\n",
+    "def pic2pdf(new_fn):\n",
+    "    fl1=glob.glob('.pdf/*.jpg')\n",
+    "    fl1.sort()\n",
+    "    a4inpt = (img2pdf.mm_to_pt(210),img2pdf.mm_to_pt(297))\n",
+    "    layout_fun = img2pdf.get_layout_fun(a4inpt)\n",
+    "    with open(new_fn,\"wb\") as f:\n",
+    "        f.write(img2pdf.convert(fl1,layout_fun=layout_fun))\n",
+    "    print(f'{new_fn}转换成功！')\n",
+    "    \n",
+    "\n",
+    "\n",
+    "def pdfz(sor, obj, zoom):    \n",
+    "    covert2pic(zoom)\n",
+    "    pic2pdf(obj)\n",
+    "    \n",
+    "fi_path = 'file/134/20221028/'\n",
+    "fl = glob.glob(f'{fi_path}*.pdf')\n",
+    "\n",
+    "for fn in fl:\n",
+    "    new_fn = fi_path+'new/'+os.path.basename(fn)\n",
+    "    covert2pic(fn)\n",
+    "    pic2pdf(new_fn)\n",
+    "    shutil.rmtree('.pdf')\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "72c693e1-dd7c-40fa-8948-4fd6fbea8ddc",
+   "metadata": {},
+   "source": [
+    "### 区分新文件"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9d06d4f0-364b-438c-844b-7d5badaf3496",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import os,sys,shutil\n",
+    "import glob\n",
+    "import time\n",
+    "\n",
+    "fi_path = 'file/'\n",
+    "fls = glob.glob(f'{fi_path}*.pdf')\n",
+    "m_date = time.strptime('2022-10-28','%Y-%m-%d')\n",
+    "for fn in fls:\n",
+    "    c_time = time.gmtime(os.path.getctime(fn))\n",
+    "    if c_time > m_date:\n",
+    "        n_name = f'{fi_path}new/{os.path.basename(fn)}'\n",
+    "        if not os.path.exists(n_name):\n",
+    "            shutil.copyfile(fn,n_name)\n",
+    "        print(n_name)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "32b61559-4495-4fbe-8eb6-2614e6225b5c",
    "metadata": {},
    "outputs": [],
    "source": []