20211125

文件管理1.ipynb

@@ -596,10 +596,145 @@
     "doc2.save(\"first-and-last-10.pdf\")\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": "ed609077-c179-4041-8ad2-200f02c4ea83",
+   "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": []