{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "## 数字文件名转换为文本文件名" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "tags": [] }, "outputs": [], "source": [ "import os,sys,shutil\n", "import openpyxl\n", "import math\n", "\n", "fi_xls = os.getcwd()+'/file/北海石化监测花名册2022 .xlsx'\n", "fi_name = {}\n", "fi_path = os.getcwd()+'/file/221103'\n", "old = []\n", "new = []\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", " if sheet.cell(n,3).value is not None: \n", " m_name = sheet.cell(n,6).value.strip()\n", " m_depart = sheet.cell(n,3).value.strip() \n", " depart.append(m_depart) \n", " dict1[int(sheet.cell(n,4).value)] = [m_name,m_depart]\n", " #print()\n", "# 创建部门办公室 \n", "m_path = os.getcwd()+'/file/221103/new'\n", "for pn in depart:\n", " if not os.path.exists(m_path + '/' + pn):\n", " os.mkdir(m_path + '/' + pn)\n", "#print(dict1)\n", "\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", " #print(fn)\n", "old.sort()\n", " #print(str(nfn)+'.pdf')\n", "\n", "for n in old:\n", " \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(old)\n", "\n", "#print(dict1)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## 目录文件按照文件名排序" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "\n", "import os,sys\n", "\n", "\n", "fi_xls = 'test1.xlsx'\n", "fi_name = {}\n", "#fi_path = 'drive/My Drive/Colab Notebooks'+'/data'\n", "fi_path = os.getcwd()+'/data'\n", "old = []\n", "new = []\n", "\n", "fl=os.listdir(fi_path)\n", "fl.sort()\n", "n = 0\n", "for i in fl:\n", " oldname=fl[n]\n", " name, suffix = os.path.splitext(oldname)\n", " if name in old:\n", " new_name = fi_path+ os.sep + fi_name[name]+suffix\n", " old_name = fi_path+ os.sep + fl[n]\n", " os.rename(old_name,new_name)\n", " n+= 1\n", "fl" ] }, { "cell_type": "markdown", "metadata": { "toc-hr-collapsed": true, "toc-nb-collapsed": true }, "source": [ "## 将pdf文件转为图片" ] }, { "cell_type": "code", "execution_count": null, "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('./data/普通高等学校本科专业目录.pdf', dpi=300,fmt='jpg', output_folder='./data/pic')\n", "print(path)\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## 新建二维码图片pdf文件" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "tags": [] }, "outputs": [], "source": [ "from fpdf import FPDF\n", "import warnings\n", "\n", "\n", "warnings.filterwarnings(\"ignore\")\n", "pdf = FPDF()\n", "# compression is not yet supported in py3k version\n", "pdf.compress = False\n", "pdf.add_page()\n", "# Unicode is not yet supported in the py3k version; use windows-1252 standard font\n", "pdf.add_font('ali-regular', '', r\"fonts/AlibabaPuHuiTi-2-55-Regular.ttf\", uni=True)\n", "pdf.set_font('ali-regular', '', 14) \n", "#pdf.ln(10)\n", "#pdf.write(5, '欢迎')\n", "pdf.text(20,280,'欢迎来到中国，中国欢迎您！')\n", "pdf.image(\"data/water/平和体质.png\", 50, 250,20)\n", "\n", "pdf.output('py3k.pdf', 'F')" ] }, { "cell_type": "markdown", "metadata": { "toc-hr-collapsed": true, "toc-nb-collapsed": true }, "source": [ "## 图像文件夹打包" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import zipfile\n", "from pdf2image import convert_from_path, convert_from_bytes\n", "import os,sys\n", "import tempfile\n", "import shutil\n", "import time\n", "\n", "from pdf2image.exceptions import (\n", " PDFInfoNotInstalledError,\n", " PDFPageCountError,\n", " PDFSyntaxError\n", ")\n", "def compress_file(zipfilename, dirname): # zipfilename是压缩包名字，dirname是要打包的目录\n", " if os.path.isfile(dirname):\n", " with zipfile.ZipFile(zipfilename, 'w') as z:\n", " z.write(dirname)\n", " else:\n", " with zipfile.ZipFile(zipfilename, 'w') as z:\n", " for root, dirs, files in os.walk(dirname):\n", " for single_file in files:\n", " if single_file != zipfilename:\n", " filepath = os.path.join(root, single_file)\n", " z.write(filepath)\n", "\n", "def addfile(zipfilename, dirname):\n", " if os.path.isfile(dirname):\n", " with zipfile.ZipFile(zipfilename, 'a') as z:\n", " z.write(dirname)\n", " else:\n", " with zipfile.ZipFile(zipfilename, 'a') as z:\n", " for root, dirs, files in os.walk(dirname):\n", " for single_file in files:\n", " if single_file != zipfilename:\n", " filepath = os.path.join(root, single_file)\n", " z.write(filepath)\n", "\n", "#images = convert_from_path('1.pdf',dpi=200,fmt='jpg', output_folder='./sample_data')\n", "def make_path(p):\n", " if os.path.exists(p): # 判断文件夹是否存在\n", " shutil.rmtree(p) # 删除文件夹\n", " os.mkdir(p) \n", "pdf_file = '2.pdf'\n", "output_folder='./pic1'\n", "zip_file = 'ribenweiqishihua.zip'\n", "make_path(output_folder)\n", "print (time.strftime(\"%a %b %d %H:%M:%S %Y\", time.localtime()))\n", "with tempfile.TemporaryDirectory() as path:\n", " images_from_path = convert_from_path(pdf_file, dpi=300,fmt='jpg', output_folder=output_folder)\n", "compress_file(zip_file, output_folder) # 执行函数\n", "print (time.strftime(\"%a %b %d %H:%M:%S %Y\", time.localtime()))" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from opencc import OpenCC\n", "\n", "cc = OpenCC('t2s')\n", "cc.convert(\"此亦寶力菱成上所不可缺者兹舉其基本變化十\")\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## PDF文本替换" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import fitz\n", "doc = fitz.open(\"data/19524.pdf\")\n", "page = doc.load_page(0)\n", "# 遍历文本块,找到对应的文本块\n", "def find_textbox(page:fitz.Page,keyword:str)->dict:\n", "\tinfo = page.get_text('dict')\n", "\tfor block in info['blocks']:\n", "\t\tfor line in block['lines']:\n", "\t\t\tfor span in line['spans']:\n", "\t\t\t\ttext = span.get('text','').replace(' ','')\n", "\t\t\t\tif text == keyword:\n", "\t\t\t\t\treturn span\n", "target = find_textbox(page,'北海炼化员工健康提示卡')\n", "page.add_redact_annot(target['bbox'],'青海炼化员工健康提示卡',fontname='china-s',fontsize=40)\n", "page.apply_redactions()\n", "doc.save(\"19524.pdf\")\n" ] }, { "cell_type": "markdown", "metadata": { "toc-hr-collapsed": true, "toc-nb-collapsed": true }, "source": [ "## 文本文件操作" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### 基本读取" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import re\n", "file_name = 'data/2012.txt'\n", "with open(file_name,'r') as fl,open('new_2012_1.txt','w') as fl1:\n", " for l in fl:\n", " l = re.sub('[\\r\\n\\f ]{1,}', '', l)\n", " if l.split():\n", " print(l)\n", " fl1.write(l)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### 读取csv文件" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "tags": [] }, "outputs": [], "source": [ "import csv\n", "import re\n", "\n", "filename = 'data/130.csv'\n", "with open(filename,'r',newline='') as csv_file:\n", " fl = csv.reader(csv_file,delimiter=',')\n", " header = next(fl) \n", " for line in fl:\n", " #line = re.sub('[\\r\\n\\f ]{1,}', '', line)\n", " print(line)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### 读取分隔符分割文件，导入MongoDB" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import pymongo\n", "import re\n", "myclient = pymongo.MongoClient('mongodb://localhost:27017/')\n", "mydb = myclient[\"gaokao\"]\n", "mycol = mydb[\"city\"]\n", "m_mongo = {}\n", "m_xx = []\n", "fl_name = 'china-city-list.txt'\n", "n = 0\n", "with open(fl_name,'r') as fl:\n", " for l in fl:\n", " n += 1\n", " if n >6:\n", " m_mongo = {}\n", " m_xx = re.sub('[ ]{1,}', '', l).split('|')\n", " #print(m_xx[1],m_xx[3],m_xx[8],m_xx[10])\n", " m_mongo['name'] = m_xx[3]\n", " m_mongo['code'] = m_xx[1]\n", " m_mongo['sheng'] = m_xx[8]\n", " m_mongo['shi'] = m_xx[10]\n", " m_mongo['jing'] = m_xx[11]\n", " m_mongo['wei'] = m_xx[12]\n", " mycol.insert_one(m_mongo) \n", " #print(m_mongo)\n", "print('ok!')\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### 整理文件" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "tags": [] }, "outputs": [], "source": [ "import re\n", "file_name = 'file/三国演义.txt'\n", "list1 = []\n", "with open(file_name,'r') as fl:\n", " for l in fl:\n", " if len(l.strip())>0:\n", " list1.append(l.strip()+'\\n')\n", "with open('file/三国演义_new.txt','w') as fl1:\n", " fl1.writelines(list1)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## 读取html文件" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from bs4 import BeautifulSoup\n", "import re\n", "from pathlib import Path\n", "\n", "def get_html_title(html_file_path):\n", " with open(html_file_path, 'r', encoding='utf-8') as f:\n", " html_content = f.read()\n", " \n", " soup = BeautifulSoup(html_content, 'html.parser')\n", " title_tag = soup.title\n", " \n", " if title_tag and hasattr(title_tag, 'string'):\n", " return title_tag.string.strip()\n", " else:\n", " return None # 标签不存在或内容为空\n", "\n", "\n", "path = Path('./file/guzi')\n", "markdown_content = []\n", "files = [file for file in path.iterdir() if file.is_file()]\n", "sorted_files = sorted(files, key=lambda f: f.name)\n", "print(type(sorted_files))\n", "for file in sorted_files:\n", " if file.suffix=='.html':\n", " markdown_content.append('## '+get_html_title(file))\n", " with open(file, 'r', encoding='utf-8') as f:\n", " html_content = f.read() \n", " soup = BeautifulSoup(html_content, 'html.parser')\n", " div = soup.find('div', class_=\"show-content\")\n", " p_elements = div.find_all('p') \n", " for div in p_elements:\n", " markdown_content.append(div.get_text(strip=True))\n", " #markdown_content.append('\\n')\n", " if file.suffix=='.md':\n", " with open(file, 'r', encoding='utf-8') as f:\n", " txt_content = f.read()\n", " lines = txt_content.splitlines()\n", " for line in lines:\n", " line = line.strip()\n", " markdown_content.append(line)\n", " \n", "markdown_content = '\\n'.join(markdown_content)\n", "with open('guzi.md', 'w', encoding='utf-8') as file:\n", " file.write(markdown_content)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from bs4 import BeautifulSoup\n", "import re\n", "from pathlib import Path\n", "\n", "\n", "def get_html_title(html_file_path):\n", " with open(html_file_path, 'r', encoding='utf-8') as f:\n", " html_content = f.read()\n", " \n", " soup = BeautifulSoup(html_content, 'html.parser')\n", " title_tag = soup.title\n", " \n", " if title_tag and hasattr(title_tag, 'string'):\n", " return title_tag.string.strip()\n", " else:\n", " return None # 标签不存在或内容为空\n", "\n", "\n", "file='file/guzi/1-01.html'\n", "markdown_content = []\n", "markdown_content.append('## '+get_html_title(file))\n", "with open(file, 'r', encoding='utf-8') as f:\n", " html_content = f.read()\n", " \n", " soup = BeautifulSoup(html_content, 'html.parser')\n", " div = soup.find('div', class_=\"show-content\")\n", " p_elements = div.find_all('p')\n", " \n", " for div in p_elements:\n", " markdown_content.append(div.get_text(strip=True))\n", " markdown_content.append('\\n')\n", "markdown_content = '\\n'.join(markdown_content)\n", "with open('1-01.md', 'w', encoding='utf-8') as file:\n", " file.write(markdown_content)\n", "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Excel文件修改" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "tags": [] }, "outputs": [], "source": [ "import openpyxl\n", "import json\n", "\n", "filename = 'data/122.json'\n", "with open(filename,'r') as fl:\n", " dict1 = json.load(fl)\n", "dict2 = {}\n", "for k, v in dict1.items():\n", " for item in v:\n", " bh = item['avatar_id']\n", " dict2[bh] = item\n", "print(dict2) \n", " \n", "wb = openpyxl.load_workbook('data/济南炼化职工分组表.xlsx')\n", "sheet = wb.active\n", "person = {}\n", "for n in range(2, sheet.max_row+1):\n", " if sheet.cell(n, 14).value is not None and sheet.cell(n, 14).value in dict2.keys():\n", " code = sheet.cell(n, 14).value\n", " sheet[f'F{n}']=dict2[code]['birth']\n", "wb.save('data/济南炼化职工分组表1.xlsx') \n", "print('ok!') \n", "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Excel文件内容生成markdown格式文本" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import openpyxl\n", "\n", "fi_xls = 'data/对局目录.xlsx'\n", "\n", "wb = openpyxl.load_workbook(fi_xls)\n", "sheet = wb['卷18'] \n", "\n", "\n", "for n in range(sheet.max_row - 1,sheet.max_row+1): \n", " print('## 第'+sheet.cell(n,1).value+'局 ')\n", " print(sheet.cell(n,2).value+' ')\n", " print(sheet.cell(n,3).value+' ')\n", " print('共'+sheet.cell(n,4).value+'着 ')\n", " if sheet.cell(n,5).value is not None:\n", " print(sheet.cell(n,5).value+' ')\n", " print(sheet.cell(n,6).value+' ')\n", " print('\\n')" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import openpyxl\n", "\n", "fi_xls = 'data/对局目录.xlsx'\n", "\n", "wb = openpyxl.load_workbook(fi_xls)\n", "sheet = wb['卷24'] \n", "\n", "\n", "for n in range(50,562): \n", " print(sheet.cell(n,1).value+' ')\n", " if sheet.cell(n,2).value is not None:\n", " print(sheet.cell(n,2).value+' ')\n", " if sheet.cell(n,3).value is not None:\n", " print(sheet.cell(n,3).value+' ')\n", " print('\\n')" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import openpyxl\n", "\n", "fi_xls = 'data/对局目录.xlsx'\n", "\n", "wb = openpyxl.load_workbook(fi_xls)\n", "sheet = wb['卷22'] \n", "\n", "\n", "for n in range(2,sheet.max_row+1): \n", " print('## 第'+sheet.cell(n,1).value+'局 ')\n", " print('第'+sheet.cell(n,2).value+'局 ')\n", " print('共'+sheet.cell(n,3).value+'着 ')\n", " print(sheet.cell(n,4).value+' ')\n", " print(sheet.cell(n,5).value+' ')\n", " print('\\n')" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import openpyxl\n", "\n", "fi_xls = 'data/对局目录.xlsx'\n", "\n", "wb = openpyxl.load_workbook(fi_xls)\n", "sheet = wb['卷24'] \n", "\n", "\n", "for n in range(50,562): \n", " #print(sheet.cell(n,1).value+' ')\n", " if sheet.cell(n,2).value is not None:\n", " print(sheet.cell(n,1).value+' '+sheet.cell(n,2).value+' '+sheet.cell(n,3).value+'局')\n", " else:\n", " print(sheet.cell(n,1).value+' ')\n", " \n", " " ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import openpyxl\n", "\n", "fi_xls = 'data/对局目录.xlsx'\n", "\n", "wb = openpyxl.load_workbook(fi_xls)\n", "sheet = wb['Sheet2'] \n", "\n", "\n", "for n in range(2,sheet.max_row+1): \n", " #print(sheet.cell(n,1).value+' ')\n", " if sheet.cell(n,2).value is not None:\n", " print(sheet.cell(n,1).value+' '+sheet.cell(n,2).value)\n", " else:\n", " print(sheet.cell(n,1).value+' ')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## YALM文件操作" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### YALM文件读取转存JSON文件" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "tags": [] }, "outputs": [], "source": [ "import yaml\n", "import json\n", "\n", "filename = 'data/全维健康中医体质检测问卷.yaml'\n", "with open(filename, 'r', encoding='utf-8') as f:\n", " result = yaml.load(f.read(), Loader=yaml.FullLoader)\n", "i = 1\n", "#print(result)\n", "filename = 'data/全维健康中医体质检测问卷.json'\n", "with open(filename, 'w') as fl:\n", " json.dump(result, fl, ensure_ascii=False)\n", "print('ok')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### 按照年龄分组生成心理问卷" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "tags": [] }, "outputs": [], "source": [ "import json\n", "import os,sys,shutil\n", "import openpyxl\n", "\n", "list1 = [\n", " [1,'完全不正确','有点正确','多数正确','完全正确'],\n", " [2,'从不','极少','偶尔','经常','频繁','非常频繁','每天'],\n", " [3,'不符合','有时符合','常常符合','总是符合'],\n", " [4,'从不','很少','有时','经常','总是'],\n", " [5,'非常不满意','不满意','一般','满意','非常满意'],\n", " [6,'没有或很少时间（少于1天）','一部分时间（1-2天）','相当多时间（3-4天）','绝大部分时间（5-7天）'],\n", " [7,'从来没有这种感觉','很少有这种感觉','有时有这种感觉','经常有这种感觉'],\n", " [8,'完全不同意','不同意','同意','完全同意'], \n", " [10,'晚多了','晚一点','差不多','早一点','早多了']\n", "]\n", "dict1 = {}\n", "for item in list1:\n", " #dict1.setdefault(item[0],[])\n", " list2 =[]\n", " for i in range(1,len(item)):\n", " list2.append(item[i])\n", " dict1[item[0]] = list2\n", "dict_choiced = {}\n", "print(dict1)\n", "wj = {}\n", "wj[\"login\"] = \"phone\"\n", "wj[\"locale\"] = \"zh-cn\"\n", "wj[\"title\"] = '社区心理测评问卷'\n", "list2 =[]\n", "dict2 = {\n", " \"type\": \"radiogroup\",\n", " \"name\": \"Gender\",\n", " \"title\": {\n", " \"zh-cn\": \"您的性别\"\n", " },\n", " \"isRequired\": True,\n", " \"choices\": [\n", " {\n", " \"value\": \"m\",\n", " \"text\": \"男性\"\n", " },\n", " {\n", " \"value\": \"f\",\n", " \"text\": \"女性\"\n", " }\n", " ] \n", "}\n", "list2.append(dict2)\n", "dict2 = {}\n", "dict3 = {}\n", "dict2 = {\n", " \"type\": \"radiogroup\",\n", " \"name\": \"Age\",\n", " \"title\": {\n", " \"zh-cn\": \"您的年龄\"\n", " },\n", " \"isRequired\": True,\n", " \"choices\": [\n", " {\n", " \"value\": \"Y\",\n", " \"text\": \"8-17岁\"\n", " },\n", " {\n", " \"value\": \"M\",\n", " \"text\": \"15-59岁\"\n", " },\n", " {\n", " \"value\": \"O\",\n", " \"text\": \"60岁及以上\"\n", " }\n", " ] \n", "}\n", "list2.append(dict2)\n", "\n", "wb = openpyxl.load_workbook('data/心理问卷.xlsx')\n", "sheet = wb.active\n", "data1 =list(sheet.values)\n", "del data1[0]\n", "for item in data1:\n", " \n", " dict2 = {} \n", " dict2['type'] = item[4] \n", " dict2['name'] = 'q'+str(item[0])+item[3]\n", " dict2['visibleIf'] = '{Age}=\"'+item[3]+'\"'\n", " dict3 = {}\n", " dict3[\"zh-cn\"] = item[1]\n", " dict2['title'] =dict3 \n", " dict2['isRequired'] = True\n", " if item[4] == 'rating':\n", " dict2['rateMin'] = 0\n", " dict2['rateMax'] = 7\n", " dict2['minRateDescription'] = { 'zh-cn':'没有'}\n", " dict2['maxRateDescription'] = { 'zh-cn':'非常同意'}\n", " else:\n", " if int(item[2]) in dict_choiced.keys():\n", " dict2['choicesFromQuestion'] = dict_choiced[int(item[2])]\n", " else:\n", " list3 = []\n", " i = 1\n", " for xm in dict1[int(item[2])]:\n", " dict3 = {}\n", " dict3 = {'value': i,'text' : xm}\n", " list3.append(dict3)\n", " i+=1\n", " dict2['choices'] = list3\n", " dict_choiced[int(item[2])] = dict2['name']\n", " list2.append(dict2)\n", "dict3 = {}\n", "dict3[\"elements\"] = list2\n", "wj[\"pages\"] =[]\n", "\n", "wj[\"pages\"].append(dict3)\n", "#filename = 'data/心理问卷1.json'\n", "#with open(filename, 'w') as fl:\n", "# json.dump(wj, fl, ensure_ascii=False)\n", "#print('ok')\n", "with open('心理问卷.yml', 'w', encoding='utf-8') as f:\n", " yaml.dump(data=wj, stream=f, allow_unicode=True)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import yaml\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# 邮件管理" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## 使用网易邮箱群发邮件" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "tags": [] }, "outputs": [], "source": [ "from email.mime.text import MIMEText\n", "from email.mime.multipart import MIMEMultipart\n", "from email.mime.application import MIMEApplication\n", "from email.header import Header\n", "import smtplib\n", "import requests\n", "import time\n", "import re\n", "import json\n", "\n", "\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", "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", " fl = f'{m_bh}-{v[0]}.pdf'\n", " m_rec = v[2]+'@ceic.com'\n", " \n", " from_addr = 'kmingedu@163.com' #发件邮箱\n", " password = 'GKWUZXMVYKSSUSSL' #邮箱密码\n", " smtp_server = 'smtp.163.com' #SMTP服务器，以新浪为例\n", " server = smtplib.SMTP(smtp_server,25) #第二个参数为默认端口为25，有些邮件有特殊端口\n", " msg = MIMEMultipart()\n", " msg['Subject'] = Header(\"低碳清洁能源研究院体质监测报告\",'utf-8')\n", " msg['From'] = Header('北京坤铭体质监测评估中心')\n", " msg['To'] = Header(m_rec)\n", "\n", " from_addr = 'kmingedu@163.com' #发件邮箱\n", " password = 'GKWUZXMVYKSSUSSL' #邮箱密码\n", " to_addr = m_rec #收件邮箱\n", " att1 =MIMEApplication(open(fl_name, 'rb').read())\n", " #att1[\"Content-Type\"] = 'application/octet-stream'\n", " # 这里的filename可以任意写，写什么名字，邮件中显示什么名字\n", " att1.add_header('Content-Disposition','attachment',filename=fl)\n", " msg.attach(att1)\n", " try:\n", " server.login(from_addr,password) #登录邮箱\n", " server.sendmail(from_addr,to_addr,msg.as_string()) #将msg转化成string发出\n", " server.quit\n", " time.sleep(5)\n", " print(f'{fl}邮件发送成功！')\n", " except smtplib.SMTPException:\n", " print (\"Error: 无法发送邮件\")\n", " \n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## 使用网易邮箱群发测试链接" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "tags": [] }, "outputs": [], "source": [ "from email.mime.text import MIMEText\n", "from email.mime.multipart import MIMEMultipart\n", "from email.mime.application import MIMEApplication\n", "from email.header import Header\n", "import smtplib\n", "import requests\n", "import time\n", "import re\n", "import json\n", "import jwt\n", "\n", "key = \"Xixi1234\"\n", "encoded = jwt.encode({\"email\": \"eygsoft@gmail.com\"}, key, algorithm='HS256')\n", "#print(encoded)\n", "\n", "\n", " \n", "list1 = [\n", " {'name':'lillianwong','E_mail':'lillianwong73@gmail.com'},\n", " {'name':'杨玉冰','E_mail':'lkyyb@126.com'}]\n", "\n", "\n", "for item in list1:\n", " m_mail = item['E_mail']\n", " m_name = item['name']\n", " encoded = jwt.encode({\"email\": m_mail}, key, algorithm='HS256')\n", " lianjie = f'https://www.forraid.com/survey/token/{encoded}/tcm0'\n", " mail_msg = f\"\"\"\n", "

欢迎参加北京坤铭体质监测评估中心中医体质检测

\n", "

点击参加测试

\n", "\"\"\"\n", " from_addr = 'kmingedu@163.com' #发件邮箱\n", " password = 'GKWUZXMVYKSSUSSL' #邮箱密码\n", " smtp_server = 'smtp.163.com' #SMTP服务器，以新浪为例\n", " server = smtplib.SMTP(smtp_server,25) #第二个参数为默认端口为25，有些邮件有特殊端口\n", " msg = MIMEText(mail_msg, 'html', 'utf-8')\n", " msg['Subject'] = Header(\"中医体质检测测试链接\",'utf-8')\n", " msg['From'] = Header('北京坤铭体质监测评估中心')\n", " msg['To'] = Header(m_mail)\n", "\n", " \n", " to_addr = m_mail #收件邮箱\n", " try:\n", " server.login(from_addr,password) #登录邮箱\n", " server.sendmail(from_addr,to_addr,msg.as_string()) #将msg转化成string发出\n", " server.quit\n", " time.sleep(5)\n", " print('邮件发送成功！')\n", " except smtplib.SMTPException:\n", " print (\"Error: 无法发送邮件\")\n", " " ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "try:\n", " server.login(from_addr,password) #登录邮箱\n", " server.sendmail(from_addr,to_addr,msg.as_string()) #将msg转化成string发出\n", " server.quit\n", " time.sleep(5)\n", " print(f'{fl}邮件发送成功！')\n", " except smtplib.SMTPException:\n", " print (\"Error: 无法发送邮件\")\n", " " ] }, { "cell_type": "markdown", "metadata": { "toc-hr-collapsed": true, "toc-nb-collapsed": true }, "source": [ "# Twilio使用" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import os\n", "from twilio.rest import Client\n", "\n", "\n", "# Your Account Sid and Auth Token from twilio.com/console\n", "# and set the environment variables. See http://twil.io/secure\n", "account_sid = 'AC1aac8c18078bf371992fda0f924860c8'\n", "auth_token = '956199d0f1b724d00ef8bb934fcaefe9'\n", "client = Client(account_sid, auth_token)\n", "\n", "message = client.messages \\\n", " .create(\n", " body=\"I'm back.\",\n", " from_='+12056066931',\n", " to='+8613793180751'\n", " )\n", "\n", "print(message.sid)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import time\n", "\n", "localtime = time.localtime(time.time())\n", "#type(localtime)\n", "print (\"本地时间为 :\", localtime)\n", "jyr = '12345'\n", "if time.strftime(\"%w\", time.localtime()) in jyr:\n", " print('ok')\n", "else:\n", " print('今日不是交易日！')\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from email.mime.text import MIMEText\n", "from email.header import Header\n", "import smtplib\n", "import requests\n", "import time\n", "import re\n", "\n", "def sendmail(message):\n", " msg = MIMEText(message,'plain','utf-8')\n", " msg['Subject'] = Header(\"外汇价格已经到达预期价位！\",'utf-8')\n", " msg['From'] = Header('512song@sina.com')\n", " msg['To'] = Header('songyi@yeah.net','utf-8')\n", "\n", " from_addr = '512song@sina.com' #发件邮箱\n", " password = '409fe5d8471da663' #邮箱密码\n", " to_addr = 'songyi@yeah.net' #收件邮箱\n", " smtp_server = 'smtp.sina.com' #SMTP服务器，以新浪为例\n", " server = smtplib.SMTP(smtp_server,25) #第二个参数为默认端口为25，有些邮件有特殊端口\n", " server.login(from_addr,password) #登录邮箱\n", " server.sendmail(from_addr,to_addr,msg.as_string()) #将msg转化成string发出\n", " server.quit() \n", " \n", " \n", "\n", "pattern = re.compile(r'\\\"(.*)\\\"')\n", "url = 'http://hq.sinajs.cn/list=USDCAD'\n", "strhtml = requests.get(url)\n", "data = strhtml.text\n", "if pattern.findall(data):\n", " for data1 in pattern.findall(data):\n", " data2 = data1.split(',')\n", "#print(data2)\n", "with open('price.txt','r') as fl:\n", " for line in fl:\n", " p_high = line.split(',')[0]\n", " p_low = line.split(',')[1]\n", "m_message = '当前美元加元买入价：{}'.format(data2[1])\n", "while time.strftime(\"%w\", time.localtime()) in '12345':\n", " \n", " print(p_high,p_low)\n", " time.sleep(10)\n", " strhtml = requests.get(url)\n", " data = strhtml.text\n", " if pattern.findall(data):\n", " for data1 in pattern.findall(data):\n", " data2 = data1.split(',')\n", " if float(data2[1]) > float(p_high):\n", " m_message = '当前美元加元买入价：{}'.format(data2[1])\n", " sendmail(m_message)\n", " p_high = str(float(p_high) + 0.04) \n", " if float(data2[1]) > float(p_high):\n", " m_message = '当前美元加元卖出价：{}'.format(data2[2])\n", " p_low = str(float(p_low) - 0.04)\n", " sendmail(m_message)\n", " time.sleep(900)\n", " " ] }, { "cell_type": "markdown", "metadata": { "toc-hr-collapsed": true, "toc-nb-collapsed": true }, "source": [ "# AWS应用" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## AWS获取sns信息" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import boto3\n", "\n", "# Create an SNS client\n", "sns = boto3.client('sns')\n", "\n", "# Call SNS to list topics\n", "response = sns.list_topics()\n", "\n", "# Get a list of all topic ARNs from the response\n", "topics = [topic['TopicArn'] for topic in response['Topics']]\n", "\n", "# Print out the topic list\n", "print(\"Topic List: %s\" % topics)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## AWS操作DynamoDB" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import boto3\n", "\n", "# Get the service resource.\n", "dynamodb = boto3.resource('dynamodb')\n", "\n", "# Create the DynamoDB table.\n", "table = dynamodb.create_table(\n", " TableName='waihui',\n", " \n", " AttributeDefinitions=[ \n", " {\n", " 'AttributeName': 'code',\n", " 'AttributeType': 'S'\n", " }\n", " \n", " \n", " ],\n", " KeySchema=[\n", " {\n", " 'AttributeName': 'code',\n", " 'KeyType': 'HASH'\n", " }\n", " \n", " ],\n", " ProvisionedThroughput={\n", " 'ReadCapacityUnits': 5,\n", " 'WriteCapacityUnits': 5\n", " }\n", " \n", ")\n", "\n", "# Wait until the table exists.\n", "table.meta.client.get_waiter('table_exists').wait(TableName='waihui')\n", "\n", "# Print out some data about the table.\n", "print(table.item_count)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import boto3\n", "import decimal\n", "# Get the service resource.\n", "dynamodb = boto3.resource('dynamodb')\n", "\n", "table = dynamodb.Table('waihui')\n", "\n", "table.put_item(\n", " Item={\n", " 'code': 'USDCAD',\n", " 'high': Decimal('1.3200'),\n", " 'low': Decimal('1.3000'),\n", " }\n", ")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import boto3\n", "# Get the service resource.\n", "dynamodb = boto3.resource('dynamodb')\n", "\n", "table = dynamodb.Table('waihui')\n", "\n", "response = table.get_item(\n", " Key={\n", " 'code': 'USDCAD' \n", " }\n", ")\n", "item = response['Item']\n", "print(item)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import boto3\n", "# Get the service resource.\n", "dynamodb = boto3.resource('dynamodb')\n", "\n", "table = dynamodb.Table('waihui')\n", "\n", "table.delete_item(\n", " Key={\n", " 'code': 'USDCAD' \n", " }\n", ")\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import boto3\n", "import decimal\n", "# Get the service resource.\n", "dynamodb = boto3.resource('dynamodb')\n", "\n", "table = dynamodb.Table('waihui')\n", "table.update_item(\n", " Key={\n", " 'code': 'USDCAD'\n", " },\n", " UpdateExpression='SET low = :val1',\n", " ExpressionAttributeValues={\n", " ':val1': decimal.Decimal('1.2900')\n", " }\n", ")\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import boto3\n", "\n", "# Create SQS client\n", "sqs = boto3.client('sqs')\n", "\n", "queue_url = 'https://sqs.us-east-1.amazonaws.com/915521803346/MySqs1'\n", "\n", "# Receive message from SQS queue\n", "response = sqs.receive_message(\n", " QueueUrl=queue_url,\n", " AttributeNames=[\n", " 'SentTimestamp'\n", " ],\n", " MaxNumberOfMessages=1,\n", " MessageAttributeNames=[\n", " 'All'\n", " ],\n", " VisibilityTimeout=0,\n", " WaitTimeSeconds=0\n", ")\n", "\n", "message = response['Messages'][0]\n", "receipt_handle = message['ReceiptHandle']\n", "\n", "# Delete received message from queue\n", "sqs.delete_message(\n", " QueueUrl=queue_url,\n", " ReceiptHandle=receipt_handle\n", ")\n", "print('Received and deleted message: %s' % message)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# MongoDB系统GridFS文件管理" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## 文件上传" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "tags": [] }, "outputs": [], "source": [ "import pymongo\n", "from gridfs import GridFS\n", "from bson.objectid import ObjectId\n", "import os\n", "\n", "myclient = pymongo.MongoClient('mongodb://localhost:27017/')\n", "mydb = myclient[\"gaokao\"]\n", "mycol = mydb[\"college\"]\n", "\n", "UploadCache = \"uploadcache\"\n", "dbURL = \"mongodb://localhost:27017\"\n", "\n", "#上传文件\n", "def upLoadFile(file_coll,file_name,data_link):\n", " client = pymongo.MongoClient('mongodb://localhost:27017/')\n", "\n", " db = client[\"gaokao\"]\n", "\n", " filter_condition = {\"filename\": os.path.basename(file_name), \"url\": data_link}\n", " gridfs_col = GridFS(db, collection=file_coll)\n", " file_ = \"0\"\n", " query = {\"filename\":\"\"}\n", " query[\"filename\"] = file_name\n", "\n", " if gridfs_col.exists(query):\n", " print('已经存在该文件')\n", " else:\n", "\n", " with open(file_name, 'rb') as file_r:\n", " file_data = file_r.read()\n", " file_ = gridfs_col.put(data=file_data, **filter_condition) # 上传到gridfs\n", "\n", " print(file_)\n", "\n", "\n", " return file_ \n", "# 按文件名获取文档\n", "def downLoadFile(self,file_coll,file_name,out_name,ver):\n", " client = pymongo.MongoClient(self.dbURL)\n", "\n", " db = client[\"store\"]\n", "\n", " gridfs_col = GridFS(db, collection=file_coll)\n", "\n", " file_data = gridfs_col.get_version(filename=file_name, version=ver).read()\n", "\n", " with open(out_name, 'wb') as file_w:\n", " file_w.write(file_data)\n", "\n", "# 按文件_Id获取文档 \n", "def downLoadFilebyID(self,file_coll,_id,out_name):\n", " client = pymongo.MongoClient(self.dbURL)\n", "\n", " db = client[\"store\"]\n", "\n", " gridfs_col = GridFS(db, collection=file_coll)\n", "\n", " O_Id = ObjectId(_id)\n", "\n", " gf = gridfs_col.get(file_id=O_Id)\n", " file_data = gf.read()\n", " with open(out_name, 'wb') as file_w:\n", "\n", " file_w.write(file_data) \n", "\n", "\n", " return gf.filename \n", "m_dir = './data/tmp'\n", "fls=os.listdir(m_dir)\n", "n = 0\n", "for fl in fls:\n", " #oldname=fl[n]\n", " name, suffix = os.path.splitext(fl)\n", " #if name in old:\n", " # new_name = fi_path+ os.sep + fi_name[name]+suffix\n", " # old_name = fi_path+ os.sep + fl[n]\n", " # os.rename(old_name,new_name)\n", " #print(os.path.basename(fl))\n", " #print(fl,suffix[1:])\n", " full_path = m_dir+ '/' + fl\n", " upLoadFile(\"document\",full_path,\"\")\n", "#a = MongoGridFS(\"\")\n", "#a.upLoadFile(\"pdf\",\"MongoGridFS.py\",\"\")\n", "#a.downLoadFile(\"pdf\",\"MongoGridFS.py\",\"out2.p\",2)\n", "#ll = a.downLoadFilebyID(\"pdf\",\"5d70a5b283a3c5104cd39346\",\"out3.p\")\n", "#print (ll)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import pymongo\n", "from gridfs import GridFS\n", "from bson.objectid import ObjectId\n", "import os\n", "\n", "myclient = pymongo.MongoClient('mongodb://localhost:27017/')\n", "mydb = myclient[\"gaokao\"]\n", "mycol = mydb[\"college\"]\n", "\n", "UploadCache = \"uploadcache\"\n", "dbURL = \"mongodb://localhost:27017\"\n", "\n", "#上传文件\n", "def upLoadFile(file_coll,file_name,data_link):\n", " client = pymongo.MongoClient('mongodb://localhost:27017/')\n", "\n", " db = client[\"gaokao\"]\n", "\n", " filter_condition = {\"filename\": file_name, \"url\": data_link}\n", " gridfs_col = GridFS(db, collection=file_coll)\n", " file_ = \"0\"\n", " query = {\"filename\":\"\"}\n", " query[\"filename\"] = file_name\n", "\n", " if gridfs_col.exists(query):\n", " print('已经存在该文件')\n", " else:\n", "\n", " with open(file_name, 'rb') as file_r:\n", " file_data = file_r.read()\n", " file_ = gridfs_col.put(data=file_data, **filter_condition) # 上传到gridfs\n", "\n", " print(file_)\n", "\n", "\n", " return file_ \n", "# 按文件名获取文档\n", "def downLoadFile(self,file_coll,file_name,out_name,ver):\n", " client = pymongo.MongoClient(self.dbURL)\n", "\n", " db = client[\"store\"]\n", "\n", " gridfs_col = GridFS(db, collection=file_coll)\n", "\n", " file_data = gridfs_col.get_version(filename=file_name, version=ver).read()\n", "\n", " with open(out_name, 'wb') as file_w:\n", " file_w.write(file_data)\n", "\n", "# 按文件_Id获取文档 \n", "def downLoadFilebyID(file_coll,_id,out_name):\n", " client = pymongo.MongoClient('mongodb://localhost:27017/')\n", "\n", " db = client[\"gaokao\"]\n", "\n", " gridfs_col = GridFS(db, collection=file_coll)\n", "\n", " O_Id = ObjectId(_id)\n", "\n", " gf = gridfs_col.get(file_id=O_Id)\n", " file_data = gf.read()\n", " with open(out_name, 'wb') as file_w:\n", "\n", " file_w.write(file_data) \n", "\n", "\n", " return gf.filename \n", "ll = downLoadFilebyID(\"pdf\",\"5fbf351b62452a56d7d16603\",\"out3.pdf\")\n", "print (ll)\n", "#a = MongoGridFS(\"\")\n", "#a.upLoadFile(\"pdf\",\"MongoGridFS.py\",\"\")\n", "#a.downLoadFile(\"pdf\",\"MongoGridFS.py\",\"out2.p\",2)\n", "#ll = a.downLoadFilebyID(\"pdf\",\"5d70a5b283a3c5104cd39346\",\"out3.pdf\")\n", "#print (ll)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# 腾讯文字识别" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import json\n", "import types\n", "from tencentcloud.common import credential\n", "from tencentcloud.common.profile.client_profile import ClientProfile\n", "from tencentcloud.common.profile.http_profile import HttpProfile\n", "from tencentcloud.common.exception.tencent_cloud_sdk_exception import TencentCloudSDKException\n", "from tencentcloud.ocr.v20181119 import ocr_client, models\n", "import base64\n", " \n", "cred = credential.Credential(\"AKIDoZHHEB2lHbluEZvN8uYHwcdvacqfmDeJ\",\"fEkr2VucwEQXXVN8jCd0CFBxdAe6Xny9\")\n", "httpProfile = HttpProfile()\n", "httpProfile.endpoint = \"ocr.tencentcloudapi.com\" \n", "clientProfile = ClientProfile()\n", "clientProfile.httpProfile = httpProfile \n", "client = ocr_client.OcrClient(cred, \"ap-beijing\", clientProfile) \n", "req = models.GeneralAccurateOCRRequest()\n", "with open(\"001.jpg\",\"rb\") as f:\n", " img_data = f.read()\n", "img_base64 = base64.b64encode(img_data)\n", "params = {\n", " \"ImageBase64\": img_base64.decode('utf-8')\n", "}\n", "req.from_json_string(json.dumps(params))\n", "\n", "# 返回的resp是一个GeneralAccurateOCRResponse的实例，与请求对象对应\n", "resp = client.GeneralAccurateOCR(req)\n", "print(resp.to_json_string())\n", "\n", "#except TencentCloudSDKException as err:\n", "# print(err)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import pymupdf4llm\n", "#md_text = pymupdf4llm.to_markdown(\"data/1782596-唐荣.pdf\")\n", "llama_reader = pymupdf4llm.LlamaMarkdownReader()\n", "llama_docs = llama_reader.load_data(\"data/1782596-唐荣.pdf\")\n", "\n", "print(llama_docs)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import pymupdf4llm\n", "md_text = pymupdf4llm.to_markdown(\"data/1782596-唐荣.pdf\")\n", "#llama_reader = pymupdf4llm.LlamaMarkdownReader()\n", "#llama_docs = llama_reader.load_data(\"data/1782596-唐荣.pdf\")\n", "\n", "print(md_text)" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "execution": { "iopub.execute_input": "2025-08-05T04:13:25.191718Z", "iopub.status.busy": "2025-08-05T04:13:25.191013Z", "iopub.status.idle": "2025-08-05T04:13:26.589724Z", "shell.execute_reply": "2025-08-05T04:13:26.589155Z", "shell.execute_reply.started": "2025-08-05T04:13:25.191654Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[{'metadata': {'format': 'PDF 1.5', 'title': '', 'author': 'FastReport', 'subject': 'FastReport PDF export', 'keywords': '', 'creator': '', 'producer': '', 'creationDate': 'D:20250628093605', 'modDate': 'D:20250628093605', 'trapped': '', 'encryption': None, 'file_path': 'data/1782596-唐荣.pdf', 'page_count': 12, 'page': 1}, 'toc_items': [], 'tables': [], 'images': [{'number': 4, 'bbox': Rect(233.94000244140625, 713.0, 375.66998291015625, 854.72998046875), 'transform': (141.72999572753906, 0.0, -0.0, 141.72999572753906, 233.94000244140625, 713.0), 'width': 190, 'height': 190, 'colorspace': 3, 'cs-name': 'DeviceRGB', 'xres': 96, 'yres': 96, 'bpc': 8, 'size': 15730, 'has-mask': False}, {'number': 11, 'bbox': Rect(251.69000244140625, 279.6000061035156, 353.739990234375, 387.32000732421875), 'transform': (102.05000305175781, 0.0, -0.0, 107.72000122070312, 251.69000244140625, 279.6000061035156), 'width': 137, 'height': 145, 'colorspace': 3, 'cs-name': 'DeviceRGB', 'xres': 96, 'yres': 96, 'bpc': 8, 'size': 7001, 'has-mask': False}], 'graphics': [], 'text': '```\\n 医保卡号：\\n\\n 体检号：325031000089\\n 检查类型：在岗期间\\n\\n# **`南京江北医院`** **`职业健康检查表`**\\n\\n```\\n\\n#### `体检编号` `姓 名`\\n\\n\\n#### `325031000089` `唐荣`\\n\\n\\n#### `身 份 证 32011219771117****`\\n\\n\\n#### `用人单位`\\n\\n\\n```\\n南化公司苯化工部\\n\\n```\\n\\n#### `联系电话 13382785142`\\n\\n\\n', 'words': []}, {'metadata': {'format': 'PDF 1.5', 'title': '', 'author': 'FastReport', 'subject': 'FastReport PDF export', 'keywords': '', 'creator': '', 'producer': '', 'creationDate': 'D:20250628093605', 'modDate': 'D:20250628093605', 'trapped': '', 'encryption': None, 'file_path': 'data/1782596-唐荣.pdf', 'page_count': 12, 'page': 2}, 'toc_items': [], 'tables': [], 'images': [], 'graphics': [], 'text': '## **`职业健康检查表说明`**\\n\\n#### `一、本单位保证职业健康检查的科学性、公正性和准确性。` `二、本单位职业健康检查活动依据国家《职业健康检查管理办法》、《` `职业健康监护技术规范》等规定进行。` `三、本单位《江苏省职业健康检查机构备案回执》的编号：苏卫职检` `备字[2021]BG第016号` `四、本检查表涂改、增删无效，未加盖单位印章无效。` `五、未经本单位同意，不得部分复制本检查表。` `六、用人单位和劳动者应确保一般项目、职业史、接触的职业病危害` `因素、既往病史等项目的真实性。` `七、发现健康损害或者疑似职业病病人时，用人单位应根据本单位的` `主检意见及国家法律法规要求安排复查或医学观察或进行职业病` `诊断。` `八、对检查结果若有异议，可直接向本单位进行咨询。` `地址（Address）：南京市化工园区葛关路552号` `邮政编码（Post Coad）：210048` `电话（Tel）：025-57067000`\\n\\n\\n', 'words': []}, {'metadata': {'format': 'PDF 1.5', 'title': '', 'author': 'FastReport', 'subject': 'FastReport PDF export', 'keywords': '', 'creator': '', 'producer': '', 'creationDate': 'D:20250628093605', 'modDate': 'D:20250628093605', 'trapped': '', 'encryption': None, 'file_path': 'data/1782596-唐荣.pdf', 'page_count': 12, 'page': 3}, 'toc_items': [], 'tables': [{'bbox': (57.689998626708984, 206.18099975585938, 562.260009765625, 297.70001220703125), 'rows': 2, 'columns': 6}, {'bbox': (57.689998626708984, 315.7010192871094, 562.260009765625, 367.9800109863281), 'rows': 2, 'columns': 5}], 'images': [], 'graphics': [], 'text': '```\\n 中华人民共和国预防性健康检查用表\\n\\n### **`有害作业人员健康检查表`**\\n\\n```\\n\\n```\\n单位名称：\\n\\n```\\n\\n```\\n南化公司苯化工部\\n\\n```\\n\\n```\\n1977年11月17日\\n\\n```\\n\\n```\\n姓 名： 唐荣 性 别：男\\n\\n```\\n\\n```\\n出生年月：\\n\\n```\\n\\n```\\n国 籍：中华人民共和国\\n\\n```\\n\\n```\\n民 族：汉族 婚 否： /\\n\\n```\\n\\n```\\n0 月 接害工龄：20 年 0 月\\n\\n```\\n\\n```\\n体检日期：\\n\\n```\\n\\n```\\n总 工 龄： 29 年 0 月 接害工龄：\\n\\n```\\n\\n```\\n年 0 月 接害工龄：20 年\\n\\n```\\n\\n```\\n2025年03月10日\\n\\n```\\n\\n```\\n29 0 20\\n\\n```\\n\\n```\\n接触有害因素：\\n\\n```\\n\\n```\\n苯,苯胺,硝基苯,硫酸及三氧化硫,硝酸,氮氧化物,氢氧化钠,氢气\\n\\n```\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n|一、职业史|Col2|Col3|Col4|Col5|Col6|\\n|---|---|---|---|---|---|\\n|`起止日期`|`工作单位`|`部门`|`工种`|` 有害因素种类、`
`名称`|`防护措施`|\\n|`2005-03-10-`
`至今`|`南化公司苯化工部`|`苯胺作业区`|`有机合成工`|`苯,苯胺,硝基苯,`
`硫酸及三氧化硫,`
`硝酸,氮氧化物,氢`
`氧化钠,氢气`|`口罩,手套,耳塞`|\\n\\n\\n\\n|二、既往病史|Col2|Col3|Col4|Col5|\\n|---|---|---|---|---|\\n|`疾病名称`|`诊断日期`|`诊断单位`|`治疗经过`|`转归`|\\n|`无`|`/`|`/`|`/`|`/`|\\n\\n```\\n三、月经史 初潮： / 岁 经期： / 天 周期： / 天 停经年龄： / 岁\\n\\n 是否经期: /\\n\\n四、生育史 现有子女 / 人、流产 / 次、早产/ 次、死产/ 次、异常胎/ 次\\n\\n五、烟酒史 现在每天吸 10 支/天、共 29 年；\\n\\n 不饮酒 / ml/日、共 / 年。\\n\\n六、其他 无特殊情况\\n\\n七、自觉症状\\n\\n症状 症状 症状 症状\\n\\n目前无不适症状\\n\\n问诊者： 录入日期：2025年03月10日\\n\\n 第1页\\n\\n```\\n\\n', 'words': []}, {'metadata': {'format': 'PDF 1.5', 'title': '', 'author': 'FastReport', 'subject': 'FastReport PDF export', 'keywords': '', 'creator': '', 'producer': '', 'creationDate': 'D:20250628093605', 'modDate': 'D:20250628093605', 'trapped': '', 'encryption': None, 'file_path': 'data/1782596-唐荣.pdf', 'page_count': 12, 'page': 4}, 'toc_items': [], 'tables': [], 'images': [], 'graphics': [], 'text': '```\\n 第4页 共12页\\n\\n 姓名: 唐荣 性别: 男 年龄:47 体检编号:325031000089 体检日期: 2025-03-10\\n\\n八、临床\\n\\n体重视力检查\\n\\n项目 结果 项目 结果\\n\\n身高 173cm 体重 86kg\\n\\n体重指数(BMI) 28.73↑ 裸眼视力左 4.5\\n\\n裸眼视力右 4.5 矫正视力(左) \\n矫正视力(右) \\n检查者： 体检日期：2025年03月10日\\n\\n内科检查\\n\\n项目 结果 项目 结果\\n\\n肺 双肺呼吸音清晰,未闻及干湿性啰音 心律 正常\\n\\n杂音 正常 腹部压痛 正常\\n\\n心率 96次/分 内科其它 \\\\\\n\\n医生： 体检日期：2025年03月10日\\n\\n血压\\n\\n项目 结果 项目 结果\\n\\n收缩压 155mmHg↑ 脉搏 96次/分\\n\\n舒张压 99mmHg↑\\n\\n医生： 体检日期：2025年03月10日\\n\\n耳鼻喉科\\n\\n项目 结果 项目 结果\\n\\n扁桃体 扁桃体Ⅱ度 咽喉 慢性咽炎\\n\\n鼻腔 正常 听力(右) 正常\\n\\n听力(左) 正常 耳疾 无\\n\\n嗅觉 正常\\n\\n医生： 体检日期：2025年03月10日\\n\\n眼科常规检查\\n\\n项目 结果 项目 结果\\n\\n辨色力 正常 眼结膜 正常\\n\\n眼部病变 \\\\\\n\\n备注：请仔细阅读体检总检和体检报告！！！\\n\\n 第2页\\n\\n```\\n\\n', 'words': []}, {'metadata': {'format': 'PDF 1.5', 'title': '', 'author': 'FastReport', 'subject': 'FastReport PDF export', 'keywords': '', 'creator': '', 'producer': '', 'creationDate': 'D:20250628093605', 'modDate': 'D:20250628093605', 'trapped': '', 'encryption': None, 'file_path': 'data/1782596-唐荣.pdf', 'page_count': 12, 'page': 5}, 'toc_items': [], 'tables': [], 'images': [], 'graphics': [], 'text': '```\\n 第5页 共12页\\n\\n 姓名: 唐荣 性别: 男 年龄:47 体检编号:325031000089 体检日期: 2025-03-10\\n\\n医生： 体检日期：2025年03月10日\\n\\n外科检查\\n\\n项目 结果 项目 结果\\n\\n皮肤 未见明显异常 淋巴结 未见明显异常\\n\\n甲状腺 未见明显异常 四肢 未见明显异常\\n\\n脊椎 未见明显异常 腋下 未见明显异常\\n\\n指甲 未见明显异常 骨关节 未见明显异常\\n\\n外科其它 /\\n\\n医生： 体检日期：2025年03月10日\\n\\n口腔检查\\n\\n项目 结果 项目 结果\\n\\n口腔粘膜 正常 唇腭 正常\\n\\n舌体 正常 牙周 正常\\n\\n牙齿 龋齿、残根 口腔科其它 /\\n\\n医生： 体检日期：2025年03月10日\\n\\n神经科\\n\\n项目 结果 项目 结果\\n\\n膝腱反射 正常反射 病理反射 未引出\\n\\n肌力 Ⅴ级 三颤 阴性\\n\\n皮肤划痕症 阴性 跟腱反射 正常反射\\n\\n前庭功能检查 阴性 肌张力 阴性\\n\\n共济运动 未见明显异常 感觉异常 未见明显异常\\n\\n运动功能 未见明显异常\\n\\n医生： 体检日期：2025年03月10日\\n\\n尿常规\\n\\n项目 结果 项目 结果\\n\\n结晶 0.00/μl 尿白细胞脂酶(LEU) 阴性Cell/uL\\n\\n医生： 体检日期：2025年03月10日\\n\\n九、器械类检查\\n\\n备注：请仔细阅读体检总检和体检报告！！！\\n\\n 第3页\\n\\n```\\n\\n', 'words': []}, {'metadata': {'format': 'PDF 1.5', 'title': '', 'author': 'FastReport', 'subject': 'FastReport PDF export', 'keywords': '', 'creator': '', 'producer': '', 'creationDate': 'D:20250628093605', 'modDate': 'D:20250628093605', 'trapped': '', 'encryption': None, 'file_path': 'data/1782596-唐荣.pdf', 'page_count': 12, 'page': 6}, 'toc_items': [], 'tables': [], 'images': [], 'graphics': [], 'text': '```\\n 第6页 共12页\\n\\n 姓名: 唐荣 性别: 男 年龄:47 体检编号:325031000089 体检日期: 2025-03-10\\n\\n彩超\\n\\n项目 结果\\n\\n彩超(双肾) 左肾强光点多个\\n\\n彩超(甲状腺) 甲状腺右叶囊性结节一个，大小约3.0*1.8*2.3毫米,TI-RADS 2类\\n\\n彩超（前列腺） 前列腺大小约44*33毫米，内见部分增强光斑（前列腺稍大伴部分钙化）\\n\\n肝 轻-中度脂肪肝；肝内低回声区一个，大小约10*10毫米,考虑低脂区可能\\n\\n胆囊 未见明显异常\\n\\n胰 未见明显异常\\n\\n脾 未见明显异常\\n\\n```\\n\\n```\\n小结：\\n\\n```\\n\\n```\\n彩超(双肾)：左肾强光点多个；彩超(甲状腺)：甲状腺右叶囊性结节一个，大小约3.0*1.8*2.3毫米,T\\nI-RADS\\n2类；彩超（前列腺）：前列腺大小约44*33毫米，内见部分增强光斑（前列腺稍大伴部分钙化）；肝\\n：轻-中度脂肪肝；肝内低回声区一个，大小约10*10毫米,考虑低脂区可能。\\n\\n```\\n\\n```\\n医生： 体检日期：2025年03月10日\\n\\n心电图\\n\\n项目 结果\\n\\n心电图 窦性心律;\\n\\n 小结： 窦性心律\\n\\n医生： 体检日期：2025年03月10日\\n\\n肺功能\\n\\n项目 结果 参考值\\n\\nFVC% 80.1 % ≥80\\n\\nFEV1% 81.7 % ≥70\\n\\nFEV1/FVC% 90.07 % 70-100\\n\\n 小结： 无明显异常\\n\\n检查者： 体检日期：2025年03月10日\\n\\n胸部平扫CT\\n\\n项目 结果\\n\\n胸部平扫CT 胸廓对称，纵隔气管居中。两侧肋骨走行自然，胸壁肌间隙清晰，胸壁软组织形态如常，未\\n 见异常密度影。右肺中叶外侧段（IM35）、左肺上叶前段（IM18、IM20）、左肺上叶下舌段\\n （IM41）见多发实性小结节，较大者位于右肺中叶外侧段（IM35），大小约为5mm×4mm。余\\n 肺未见异常密度影。两侧肺门未见增大。气管、支气管通畅。胸腺区呈脂肪密度影，未见增\\n 宽。两侧肺门及纵隔内未见明显肿大淋巴结影。两侧胸腔未见积液影，两侧胸膜未见增厚。\\n 心脏形态、大小如常，主动脉壁见钙化影。所及肝实质密度稍减低。\\n\\n 小结：\\n\\n医生： 体检日期：2025年03月10日\\n\\n备注：请仔细阅读体检总检和体检报告！！！\\n\\n 第4页\\n\\n```\\n\\n', 'words': []}, {'metadata': {'format': 'PDF 1.5', 'title': '', 'author': 'FastReport', 'subject': 'FastReport PDF export', 'keywords': '', 'creator': '', 'producer': '', 'creationDate': 'D:20250628093605', 'modDate': 'D:20250628093605', 'trapped': '', 'encryption': None, 'file_path': 'data/1782596-唐荣.pdf', 'page_count': 12, 'page': 7}, 'toc_items': [], 'tables': [], 'images': [], 'graphics': [], 'text': '```\\n 第7页 共12页\\n\\n 姓名: 唐荣 性别: 男 年龄:47 体检编号:325031000089 体检日期: 2025-03-10\\n\\n十、化验室项目\\n\\n血常规\\n\\n项目 结果 参考值 计量单位 项目 结果 参考值 计量单位\\n\\n白细胞计数 7.1 3.5-9.5 10^9/L 红细胞计数 4.70 4.3-5.8 10^12/L\\n\\n血红蛋白 139.00 130-175 g/L 红细胞压积 42.1 40-50 %\\n\\n红细胞平均体积 89.50 82-100 fL 平均血红蛋白量 29.70 27.00-34.00 pg\\n\\n平均血红蛋白浓度 330.00 316-354 g/L 血小板计数 340.00 125-350 10^9/L\\n\\n淋巴细胞百分数 34.40 20-50 % 淋巴细胞绝对值 2.44 1.1-3.2 10^9/L\\n\\n中性粒细胞绝对值 4.11 1.8-6.3 10^9/L 中性粒细胞百分数 57.90 40-75 %\\n\\n血小板比积 0.33↑ 0.11-0.28 % 红细胞分布宽度(SD) 44.10 39-46 fl\\n\\n平均血小板体积 9.80 6.00-14.00 fL 血小板分布宽度 16.40 9.00-18.00 fl\\n\\n单核细胞绝对值 0.38 0.1-0.6 10^9/L 单核细胞百分数 5.40 3.0-10.0 %\\n\\n嗜酸性粒细胞 0.15 0.02-0.52 10^9/L 嗜碱性粒细胞 0.01 0-0.06 10^9/L\\n\\n嗜酸性粒细胞百分数 2.10 0.5-5 % 嗜碱性粒细胞百分数 0.20 0-1 %\\n\\n检验员： 复核员： 报告日期： 2025年03月10日\\n\\n尿常规\\n\\n项目 结果 参考值 计量单位 项目 结果 参考值 计量单位\\n\\n尿维生素C +3 阴性 mmol/L 尿比重(SG) 1.030↑ 1.003-1.03\\n\\n尿胆原(URO) 正常 正常 umol/L 尿胆红素 阴性 阴性 umol/L\\n\\n尿酮体(KET) 阴性 阴性 mmol/L 尿隐血（BLD） +- 阴性 Cell/ul\\n\\n尿蛋白（PRO） +1 0.03-0.14 g/L 亚硝酸盐 阴性 阴性\\n\\n尿葡萄糖（GLU） 阴性 阴性 mmol/L 尿酸碱度测定 5.00 4.60-8.00\\n\\n微白蛋白 150.00↑ 0.00-20.00 mg/L 尿钙 1.00↓ 2.50-7.50 mmol/L\\n\\n尿肌酐 17.60 2.00-22.00 mmol/L 尿红细胞 2.50 0-10 /μl\\n\\n透明度 透明 清晰透明 鳞状上皮 0.00 0-23 /μl\\n\\n非鳞状上皮细胞 0.00 0-3 /uL 草酸钙结晶 0.00 0-10 /ul\\n\\n颜色 淡黄色 淡黄色 管型 0.00 0-1 /ul\\n\\n透明管型 0.00 0-1 /μl 细菌 0.00 0-33 /ul\\n\\n酵母菌 0.00 0-0 粘液丝 +- 0-118 /ul\\n微量蛋白/肌酐（ACR +1 正常 尿酸结晶 0.00 0-3 /ul\\n）\\n\\n尿白细胞 阴性 阴性 Cell/uL\\n\\n检验员： 复核员： 报告日期： 2025年03月10日\\n\\n备注：请仔细阅读体检总检和体检报告！！！\\n\\n 第5页\\n\\n```\\n\\n', 'words': []}, {'metadata': {'format': 'PDF 1.5', 'title': '', 'author': 'FastReport', 'subject': 'FastReport PDF export', 'keywords': '', 'creator': '', 'producer': '', 'creationDate': 'D:20250628093605', 'modDate': 'D:20250628093605', 'trapped': '', 'encryption': None, 'file_path': 'data/1782596-唐荣.pdf', 'page_count': 12, 'page': 8}, 'toc_items': [], 'tables': [], 'images': [], 'graphics': [], 'text': '```\\n 第8页 共12页\\n\\n 姓名: 唐荣 性别: 男 年龄:47 体检编号:325031000089 体检日期: 2025-03-10\\n\\n生化\\n\\n项目 结果 参考值 计量单位 项目 结果 参考值 计量单位\\n\\n谷丙转氨酶 24 9-50 U/L 谷草转氨酶 17 15-40 U/L\\n\\n总胆红素 3.1 0-26 μmol/L 总蛋白 80.9 65-85 g/L\\n\\n白蛋白 48.4 40-55 g/L 球蛋白 32.5 20-45 g/L\\n\\nγ-谷氨酰转肽酶 48 10-60 U/L 肌酐 75 57-97 μmol/L\\n\\n尿素氮 5.2 2.76-8.07 mmol/L 尿酸 384.0 202.3-416.5 μmol/L\\n\\n总胆固醇 5.49↑ 0-5.2 mmol/L 甘油三酯 5.32↑ 0-1.7 mmol/L\\n\\n低密度脂蛋白 3.07 0-4.12 mmol/L 高密度脂蛋白 0.88↓ 1-2.0 mmol/L\\n\\n葡萄糖 5.70 3.89-6.1 mmol/L\\n\\n检验员： 复核员： 报告日期： 2025年03月10日\\n\\n甲状腺功能\\n\\n项目 结果 参考值 计量单位 项目 结果 参考值 计量单位\\n游离三碘甲状腺原氨 5.79 3.1-6.8 pmol/L 游离甲状腺素 14.91 12-22 pmol/L\\n酸\\n\\n促甲状腺激素 4.95↑ 0.27-4.2 uIU/ml\\n\\n检验员： 复核员： 报告日期： 2025年03月10日\\n\\n肿瘤标志物\\n\\n项目 结果 参考值 计量单位 项目 结果 参考值 计量单位\\n\\n癌胚抗原 3.47 0-4.7 ng/ml 甲胎蛋白 3.60 0-7.0 ng/ml\\n\\n检验员： 复核员： 报告日期： 2025年03月10日\\n\\n糖化血红蛋白（HbAIC）\\n\\n项目 结果 参考值 计量单位 项目 结果 参考值 计量单位\\n\\n糖化血红蛋白测定（H\\n 6.05↑ 4-6.0 %\\nbAIC）\\n\\n检验员： 复核员： 报告日期： 2025年03月10日\\n\\n备注：请仔细阅读体检总检和体检报告！！！\\n\\n 第6页\\n\\n```\\n\\n', 'words': []}, {'metadata': {'format': 'PDF 1.5', 'title': '', 'author': 'FastReport', 'subject': 'FastReport PDF export', 'keywords': '', 'creator': '', 'producer': '', 'creationDate': 'D:20250628093605', 'modDate': 'D:20250628093605', 'trapped': '', 'encryption': None, 'file_path': 'data/1782596-唐荣.pdf', 'page_count': 12, 'page': 9}, 'toc_items': [], 'tables': [], 'images': [], 'graphics': [], 'text': '```\\n 第9页 共12页\\n\\n 姓名: 唐荣 性别: 男 年龄:47 体检编号:325031000089 体检日期: 2025-03-10\\n\\n幽门螺杆菌抗体\\n\\n项目 结果 参考值 计量单位 项目 结果 参考值 计量单位\\n\\n```\\n\\n```\\n幽门螺杆菌尿素酶抗\\n体检测\\n\\n```\\n\\n```\\n弱阳性（±\\n）\\n\\n```\\n\\n```\\n检验员： 复核员： 报告日期： 2025年03月11日\\n\\n十一、检查结论\\n\\n 检查结果：\\n (1)[体重视力检查]:体重指数偏高：28.73；裸眼视力左：4.5；裸眼视力右：4.5；\\n (2)[血压]:收缩压偏高：155mmHg；舒张压偏高：99mmHg；\\n (3)[耳鼻喉科]:扁桃体：扁桃体Ⅱ度；咽喉：慢性咽炎；\\n (4)[口腔检查]:牙齿：龋齿、残根；\\n (5)[彩超]:彩超(双肾)：左肾强光点多个；彩超(甲状腺)：甲状腺右叶囊性结节一个，大小约3.0*1.8*2.3\\n 毫米,TI-RADS\\n 2类；彩超（前列腺）：前列腺大小约44*33毫米，内见部分增强光斑（前列腺稍大伴部分钙化）；肝：轻 中度脂肪肝；肝内低回声区一个，大小约10*10毫米,考虑低脂区可能；\\n (6)[心电图]:窦性心律；\\n (7)[尿常规]:尿隐血（BLD）：+-；尿蛋白（PRO）：+1；微白蛋白偏高：150.00mg/L；尿钙偏低：1.00mmo\\n l/L；微量蛋白/肌酐（ACR）：+1；\\n (8)[生化]:总胆固醇偏高：5.49mmol/L；甘油三酯偏高：5.32mmol/L；高密度脂蛋白偏低：0.88mmol/L；\\n (9)[甲状腺功能]:促甲状腺激素偏高：4.95uIU/ml；\\n (10)[胸部平扫CT]:胸部CT平扫：\\n 1、两肺多发微小结节，建议年度随访复查；\\n 2、主动脉硬化。\\n 附见：轻度脂肪肝；\\n (11)[糖化血红蛋白（HbAIC）]:糖化血红蛋白测定（HbAIC）偏高：6.05%；\\n (12)[幽门螺杆菌抗体]:幽门螺杆菌尿素酶抗体检测：弱阳性（±）；\\n 其余所检项目未见明显异常。\\n\\n 主检结论：\\n 本次职业健康检查发现除目标疾病以外的其他疾病或某项指标异常。\\n 建议定期复查。\\n\\n 健康建议：\\n 1、糖化血红蛋白测定（HbAIC）偏高：\\n 糖化血红蛋白是血糖检查最常用的监测指标，能反应近2-3个月的平均血糖水平，因此，也是监测糖尿病血\\n 糖控制水平的指标\\n\\n 2、微白蛋白偏高：150.00：\\n 建议注意休息，多饮水，必要时肾内科就诊\\n\\n 3、尿蛋白（PRO）：+1：\\n 尿内出现蛋白称为蛋白尿。引起蛋白尿的原因较多：剧烈运动、发热、寒冷、精神紧张时可出现暂时性蛋\\n 白尿，属于生理性蛋白尿。病理性蛋白尿多由急性肾炎、糖尿病肾病、系统性红斑狼疮、肾小管受炎症或\\n 药物刺激引起，膀胱炎、尿道炎、尿道出血及尿液内混入阴道分泌物也可出现假性蛋白尿。建议您肾内科\\n 专科就诊。\\n\\n 4、甲状腺右叶囊性结节：\\n 建议门诊内分泌科或甲乳外科诊疗。\\n\\n 5、两肺多发微小结节：\\n 建议定期复查\\n\\n备注：请仔细阅读体检总检和体检报告！！！\\n\\n 第7页\\n\\n```\\n\\n', 'words': []}, {'metadata': {'format': 'PDF 1.5', 'title': '', 'author': 'FastReport', 'subject': 'FastReport PDF export', 'keywords': '', 'creator': '', 'producer': '', 'creationDate': 'D:20250628093605', 'modDate': 'D:20250628093605', 'trapped': '', 'encryption': None, 'file_path': 'data/1782596-唐荣.pdf', 'page_count': 12, 'page': 10}, 'toc_items': [], 'tables': [], 'images': [], 'graphics': [], 'text': '```\\n 第10页 共12页\\n\\n 姓名: 唐荣 性别: 男 年龄:47 体检编号:325031000089 体检日期: 2025-03-10\\n\\n 6、促甲状腺激素偏高：\\n 建议内分泌科诊疗。\\n\\n 7、高密度脂蛋白偏低：\\n 当发生HDL降低时，动脉血管壁胆固醇沉积的机会增加，导致血管硬化，诱发冠心病，定期复查。\\n\\n 8、轻-中度脂肪肝：\\n 肝脏脂肪含量高于5％称为脂肪肝，引起脂肪肝的主要原因有：营养失调（营养过量）、饮酒、糖尿病、高\\n 脂血症、中毒和药物等。脂肪肝是可逆性的，合理饮食、运动及治疗后可恢复。\\n 建议：①低脂饮食,少吃动物内脏,多进食蔬菜、水果 ②严格限酒，适当运动\\n ③定期复查彩超及血脂，必要时肝病科诊疗。\\n\\n 9、甘油三酯偏高：\\n 甘油三酯测定是脂类代谢的重要指标之一。采血前2-3天尽可能少食含脂质类的食物，空腹12小时抽血，以\\n 排除和减少饮食的影响。血清甘油三脂水平受年龄、性别和饮食的影响。甘油三酯的增高与冠心病的发生\\n 有着重要的相关性。增高见于家族性高甘油三酯血症、饮食大量甘油三酯和继发于某些疾病如：糖尿病、\\n 甲状腺功能减退、肾病综合征、动脉硬化病等。\\n 建议：低脂饮食，多进食蔬菜、水果，增加体育锻炼；明显增高者,在医师指导下使用降脂药物。心内科门\\n 诊定期复查。\\n\\n 10、总胆固醇偏高：\\n 总胆固醇测定主要反映体内胆固醇的代谢情况，血清胆固醇受遗传、饮食、季节、生活方式、性别、年龄\\n 和环境诸多因素的影响，需多次检测并动态观察。\\n 建议\\n 1.胆固醇增高：见于脂肪肝、肝脏肿瘤、动脉粥样硬化、糖尿病、肾病综合症、甲状腺功能减退、阻塞性\\n 黄疸、原发性高胆固醇血症及高脂血症等。\\n 2.明显增高者,在医师指导下使用降脂药物治疗。\\n 3.低胆固醇饮食，少食动物内脏、蛋黄、蟹黄等食物，定期复查。\\n\\n 11、肝内低回声区：\\n 建议消化内科诊疗\\n\\n 12、体重指数偏高：\\n 体重指数(BMI)--即体重（公斤）除以身高（米）的平方，BMI正常是18.5～24.9。24.9～29.9\\n 视为超重；>30 视为肥胖。\\n 建议：①合理控制饮食量，合理搭配饮食，低盐、低脂和低糖饮食。②长期坚持体育锻炼，坚持自测体重\\n\\n 。\\n\\n 13、收缩压偏高：\\n 建议心血管内科专科诊疗\\n\\n 14、左肾强光点：\\n 建议：①多饮水排尿，多吃新鲜蔬菜水果，少吃油腻辛辣食物，多做下蹲动作。②定期复查彩超。\\n\\n 15、舒张压偏高：\\n 建议心血管内科专科诊疗\\n\\n 16、主动脉硬化：\\n 建议心内科诊疗\\n\\n 17、前列腺稍大：\\n 1.多吃新鲜蔬菜、水果，忌辛辣刺激性食物，忌酒。2.尽可能少骑自行车，忌长时间憋尿。3.保持心情舒\\n 畅，避免过度劳累，适度进行体育活动。建议定期复查彩超。\\n\\n 主检医师（签字）：\\n\\n备注：请仔细阅读体检总检和体检报告！！！\\n\\n 第8页\\n\\n```\\n\\n', 'words': []}, {'metadata': {'format': 'PDF 1.5', 'title': '', 'author': 'FastReport', 'subject': 'FastReport PDF export', 'keywords': '', 'creator': '', 'producer': '', 'creationDate': 'D:20250628093605', 'modDate': 'D:20250628093605', 'trapped': '', 'encryption': None, 'file_path': 'data/1782596-唐荣.pdf', 'page_count': 12, 'page': 11}, 'toc_items': [], 'tables': [], 'images': [{'number': 4, 'bbox': Rect(377.6499938964844, 142.2300262451172, 519.3800048828125, 283.96002197265625), 'transform': (141.72999572753906, 0.0, -0.0, 141.72999572753906, 377.6499938964844, 142.2300262451172), 'width': 190, 'height': 190, 'colorspace': 3, 'cs-name': 'DeviceRGB', 'xres': 96, 'yres': 96, 'bpc': 8, 'size': 15730, 'has-mask': False}, {'number': 3, 'bbox': Rect(355.3299865722656, 96.88002014160156, 463.04998779296875, 139.4000244140625), 'transform': (107.72000122070312, 0.0, -0.0, 42.52000045776367, 355.3299865722656, 96.88002014160156), 'width': 145, 'height': 58, 'colorspace': 3, 'cs-name': 'DeviceRGB', 'xres': 96, 'yres': 96, 'bpc': 8, 'size': 6109, 'has-mask': False}], 'graphics': [], 'text': '```\\n 第11页 共12页\\n\\n 姓名: 唐荣 性别: 男 年龄:47 体检编号:325031000089 体检日期: 2025-03-10\\n\\n备注：请仔细阅读体检总检和体检报告！！！\\n\\n 第9页\\n\\n```\\n\\n', 'words': []}, {'metadata': {'format': 'PDF 1.5', 'title': '', 'author': 'FastReport', 'subject': 'FastReport PDF export', 'keywords': '', 'creator': '', 'producer': '', 'creationDate': 'D:20250628093605', 'modDate': 'D:20250628093605', 'trapped': '', 'encryption': None, 'file_path': 'data/1782596-唐荣.pdf', 'page_count': 12, 'page': 12}, 'toc_items': [], 'tables': [], 'images': [], 'graphics': [], 'text': '', 'words': []}]\n" ] } ], "source": [ "from pathlib import Path\n", "import json\n", "import shutil\n", "import pymupdf4llm\n", "#md_text = pymupdf4llm.to_markdown(\"data/1782596-唐荣.pdf\")\n", "#llama_reader = pymupdf4llm.LlamaMarkdownReader()\n", "llama_docs = pymupdf4llm.to_markdown(\"data/1782596-唐荣.pdf\",page_chunks=True)\n", "print(llama_docs)" ] }, { "cell_type": "code", "execution_count": null, "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": "3.12.3" } }, "nbformat": 4, "nbformat_minor": 4 }