jupyter/文件管理.ipynb

文件管理

数字文件名转换为文本文件名

In [ ]:

import os,sys,shutil
import openpyxl
import math

fi_xls = os.getcwd() + '/data/高新区.xlsx'
fi_path = os.getcwd() + '/file/220720'
old = []
dict1 = {}

wb = openpyxl.load_workbook(fi_xls)
sheet = wb.active
depart = []
for n in range(2,sheet.max_row+1):    
    m_name = str(sheet.cell(n,1).value)
    m_depart = sheet.cell(n,5).value
    if m_depart not in depart:
        depart.append(sheet.cell(n,5).value)
    dict1[int(m_name.split('.')[0])] = [sheet.cell(n,2).value.strip(),sheet.cell(n,5).value.strip()]
    
# 创建部门办公室    
m_path = os.getcwd()+'/file/220427/new'
for pn in depart:
    if not os.path.exists(m_path + '/' + pn):
        os.mkdir(m_path + '/' + pn)
fl=os.listdir(fi_path)
for fn in fl:
    if os.path.isfile(fi_path + '/' + fn):
        ofn = int(fn.split('.')[0])
        old.append(ofn) 
old.sort()
for n in old:    
    o_name = f'{fi_path}/{n}.pdf'
    n_name = f'{fi_path}/new/{dict1[n][1]}/{str(n).rjust(5,"0")}-{dict1[n][0]}.pdf'
    if not os.path.exists(n_name):
        shutil.copyfile(o_name,n_name)
        print(n_name)
#print(dict1)

批量修改文件名

In [3]:

import os,sys,shutil
import json
import glob
from pathlib import Path

filepath = 'file/line/'
new = 'file/Line1/'
files = glob.glob(f'{filepath}*.SAC')
for fn in files:
    fi_name =Path(fn).stem.split('_')[0]
    n_name = Path(new,fi_name+'.SAC')
    shutil.copyfile(fn,n_name)
    
    

汇总目录下所有文件

In [3]:

import os,sys,shutil
from pathlib import Path

fi_path = Path('file/北海/2022年')
new_path = 'file/北海/new/2022年'
pdf_files = list(fi_path.glob('**/*.pdf'))
fls = list(fi_path.glob('**/*.pdf'))
for fn in fls:
    fi_name =Path(fn).name
    n_name = Path(new_path,fi_name)
    shutil.copyfile(fn,n_name)

In [ ]:

import os,sys,shutil
import openpyxl
import math

fi_xls = os.getcwd() + '/data/高新区.xlsx'
fi_path = os.getcwd() + '/file/220720'
old = []
dict1 = {}

wb = openpyxl.load_workbook(fi_xls)
sheet = wb.active
depart = []
for n in range(2,sheet.max_row+1):    
    m_name = str(sheet.cell(n,1).value)
    m_depart = sheet.cell(n,5).value
    if m_depart not in depart:
        depart.append(sheet.cell(n,5).value)
    dict1[sheet.cell(n,4).value] = [sheet.cell(n,6).value,sheet.cell(n,3).value]
#print(dict1)
fl=os.listdir(fi_path)
for fn in fl:
    if os.path.isfile(fi_path + '/' + fn):
        ofn = int(fn.split('.')[0])
        old.append(ofn) 
old.sort()


wb = openpyxl.Workbook()
sheet = wb.active
i = 0
   
for item in old:
    m_bh = item
    m_name = dict1[item][0]
    m_dep = dict1[item][1]
    i += 1
    sheet[f'A{i}'] = m_bh
    sheet[f'B{i}'] = m_name
    sheet[f'C{i}'] = m_dep
    
    
wb.save('data/高新区报告.xlsx')     

低碳院人员信息转换

In [ ]:

import os,sys,shutil
import openpyxl
import math

fi_xls = os.getcwd() + '/data/北京低碳监测.xlsx'
fi_path = os.getcwd() + '/file/220724'
old = []
dict1 = {}

wb = openpyxl.load_workbook(fi_xls)
sheet = wb.active
depart = []
for n in range(2,sheet.max_row):    
    m_name = sheet.cell(n,6).value
    m_depart = sheet.cell(n,3).value
    if sheet.cell(n,4).value is not None:
        dict1[int(sheet.cell(n,4).value)] = [m_name,m_depart]

m_path = os.getcwd()+'/file/220724/new'

fl=os.listdir(fi_path)
for fn in fl:
    if os.path.isfile(fi_path + '/' + fn):
        ofn = int(fn.split('.')[0])
        old.append(ofn) 
old.sort()
for n in old:    
    o_name = f'{fi_path}/{n}.pdf'
    n_name = f'{fi_path}/new/{str(n).rjust(5,"0")}-{dict1[n][0]}.pdf'
    if not os.path.exists(n_name):
        shutil.copyfile(o_name,n_name)
        print(n_name)
#print(dict1)

低碳院人员信息核验

In [ ]:

import os,sys,shutil
import openpyxl
import math
import json

fi_xls = os.getcwd() + '/data/北京低碳监测.xlsx'
fi_path = os.getcwd() + '/file/220724'
old = []
dict1 = {}
dict2 = {}
dict3 = {}
wb = openpyxl.load_workbook(fi_xls)
sheet = wb.active
depart = []
for n in range(2,sheet.max_row+1):    
    m_name = sheet.cell(n,6).value
    m_depart = sheet.cell(n,3).value
    if sheet.cell(n,4).value is not None:
        dict1[int(sheet.cell(n,4).value)] = [m_name,m_depart]

fi_xls = os.getcwd() + '/data/1658883945637.xlsx'
wb = openpyxl.load_workbook(fi_xls)
sheet = wb.active
for n in range(2,sheet.max_row+1):    
    m_dm = sheet.cell(n,3).value
    m_depart = sheet.cell(n,2).value
    m_name = sheet.cell(n,4).value
    if sheet.cell(n,3).value is not None:
        dict2[sheet.cell(n,3).value] = [m_name,m_depart,m_dm]
#print(dict2)
fl=os.listdir(fi_path)
for fn in fl:
    if os.path.isfile(fi_path + '/' + fn):
        ofn = int(fn.split('.')[0])
        old.append(ofn) 
old.sort()
for n in old:
    m_name = dict1[n][0]
    m_depart = dict1[n][1]
    for item in dict2.values():
        if m_name in item and m_depart in item:
            dict3[n] = [m_name,m_depart,item[2]]
            break
for k in old:
    if k not in dict3.keys():
        print(k)
with open('data/低碳院报告.json','w') as fl2:
    json.dump(dict3,fl2,ensure_ascii=False)    

低碳院人员附件核验

In [ ]:

import json
import os

fl_name = 'data/低碳院报告.json'

with open(fl_name,'r') as fl:
     m_xx = json.load(fl)
for k, v in m_xx.items():
    m_bh = str(k).rjust(5,"0")
    fl_name = f'file/220724/new/{m_bh}-{v[0]}.pdf'
    if os.path.exists(fl_name):
        print(fl_name)
    else:
        print(f'{v[0]}不存在')

低碳院人员导出

In [ ]:

import json
import openpyxl
      

fl_name = 'data/低碳院报告.json'

with open(fl_name,'r') as fl:
     m_xx = json.load(fl)
        
wb = openpyxl.Workbook()
sheet = wb.active
i = 0
   
for k, v in m_xx.items():
    m_bh = str(k).rjust(5,"0")
    m_name = v[0]
    fl = f'{m_bh}-{v[0]}.pdf'
    m_rec = v[2]+'@ceic.com'
    i += 1
    sheet[f'A{i}'] = i
    sheet[f'B{i}'] = m_bh
    sheet[f'C{i}'] = m_name
    sheet[f'D{i}'] = m_rec      
    sheet[f'E{i}'] = fl
    
wb.save('data/低碳院邮件.xlsx')     
    

批量更换扩展名

In [ ]:

import glob
import os,shutil

filepath = 'file/yimo/'
old = 'SGF'
new = 'sgf'
files = glob.glob(f'{filepath}*.{old}')
for f in files:
    new_file =os.path.splitext(f)[0]+'.'+new
    os.rename(f,new_file)

PDF文件压缩

In [ ]:

import fitz
import os


def covert2pic(zoom):
    if os.path.exists('.pdf'):       # 临时文件，需为空
         os.removedirs('.pdf')
    os.mkdir('.pdf')
    for pg in range(totaling):
        page = doc[pg]
        zoom = int(zoom)            #值越大，分辨率越高，文件越清晰
        rotate = int(0)
        print(page)
        trans = fitz.Matrix(zoom / 100.0, zoom / 100.0).preRotate(rotate)
        pm = page.getPixmap(matrix=trans, alpha=False)
      
        lurl='.pdf/%s.jpg' % str(pg+1)
        pm.writePNG(lurl)
    doc.close()

def pic2pdf(obj):
    doc = fitz.open()
    for pg in range(totaling):
        img = '.pdf/%s.jpg' % str(pg+1)
        imgdoc = fitz.open(img)                 # 打开图片
        pdfbytes = imgdoc.convertToPDF()        # 使用图片创建单页的 PDF
        os.remove(img)  
        imgpdf = fitz.open("pdf", pdfbytes)
        doc.insertPDF(imgpdf)                   # 将当前页插入文档
    if os.path.exists(obj):         # 若文件存在先删除
        os.remove(obj)
    doc.save(obj)                   # 保存pdf文件
    doc.close()


def pdfz(sor, obj, zoom):    
    covert2pic(zoom)
    pic2pdf(obj)
    


sor = "5.pdf"              # 需要压缩的PDF文件
obj = "new-" + sor
doc = fitz.open(sor) 
totaling = doc.pageCount

zoom = 150                     # 清晰度调节，缩放比率
pdfz(sor, obj, zoom)
os.removedirs('.pdf')

In [ ]:

from pdf2image import convert_from_path, convert_from_bytes
import os,sys
import tempfile
from pdf2image.exceptions import (
    PDFInfoNotInstalledError,
    PDFPageCountError,
    PDFSyntaxError
)
#images = convert_from_path('1.pdf',dpi=200,fmt='jpg', output_folder='./sample_data')
with tempfile.TemporaryDirectory() as path:
    images_from_path = convert_from_path('检查.pdf', dpi=100,fmt='jpg', output_folder='./pic')
print(path)

In [ ]:

import img2pdf  
import os,sys
import glob

fl=glob.glob('./pic/*.jpg')
fl.sort()
a4inpt = (img2pdf.mm_to_pt(210),img2pdf.mm_to_pt(297))
layout_fun = img2pdf.get_layout_fun(a4inpt)
with open("name.pdf","wb") as f:
    f.write(img2pdf.convert(fl,layout_fun=layout_fun))

In [ ]:

import glob
import fitz  # 导入本模块需安装pymupdf库
import os,sys

def pic2pdf_1(img_path, pdf_path, pdf_name):
    doc = fitz.open()
    fl=os.listdir(img_path)
    fl.sort()
    width, height = fitz.PaperSize("a4")
    #width, height = fitz.paper_size("a4")
    for img in fl:
        fn = img_path+'/'+img
        if os.path.isfile(fn):
            imgdoc = fitz.open(img_path+'/'+img)
            pdfbytes = imgdoc.convertToPDF()
            imgpdf = fitz.open("pdf", pdfbytes,width = width, height = height)
            doc.insertPDF(imgpdf)
    doc.save(pdf_path +'/'+ pdf_name)
    doc.close()

img_path = os.getcwd() +'/pic'
pdf_path = os.getcwd()
pic2pdf_1(img_path=img_path, pdf_path=pdf_path, pdf_name='1.pdf')

图片文件扫描识别

In [ ]:

#将指定目录下图片文件进行文字识别
import os,sys
from aip import AipOcr
import glob

""" 你的 APPID AK SK """
APP_ID = '17553946'
API_KEY = 'IMC1ss3Tyo3vEAdVH6jgcdv2'
SECRET_KEY = 'Iua6KdhuDtz159rjzGeFGpqgjhnoU0zZ'

client = AipOcr(APP_ID, API_KEY, SECRET_KEY)
def get_file_content(filePath):
    with open(filePath, 'rb') as fp:
        return fp.read()

options = {}
options["language_type"] = "CHN_ENG"
options["detect_direction"] = "true"
options["detect_language"] = "true"
options["probability"] = "true"

fi_path = os.getcwd()+'/pic'
fl = glob.glob(f'{fi_path}/*.jpg')
fl.sort()
for fl1 in fl:
    file_name =  fl1
    image = get_file_content(file_name)
    result= client.basicGeneral(image, options)
    if 'words_result' in result:
        print('\n'.join([w['words'] for w in result['words_result']]))
        print('\n')
        
        

In [ ]:

In [ ]:

word文档读取

In [ ]:

import docx
import json
Doc = docx.Document(r"症状对症处方选穴.docx")
#print("檔案內含段落數：",len(Doc.paragraphs),"\n")
testList = []
text1 = []
dict1 = {}
for text in Doc.paragraphs:
    testList.append(text)
i = 0
for pg in testList:
    
    if len(pg.text) >0:
        s = ''.join(pg.text.split())        
        if s[0:1] == '第':
            i += 1
            n = 0
            
            dict1.setdefault(i,{})
            dict1[i]['title'] = pg.text.split()[1]
            dict1[i]['sub'] = {}
            
            #dict1[i]['title'].setdefault(i,{})
        elif s[0:1] == '（':
            sub = s.split('）')[1]
            dict2 = {}
            dict1[i]['sub'].setdefault(sub,[])
        else:
            dict1[i]['sub'][sub].append(s)
filename = '症状对症处方选穴.json'
with open(filename,'w') as fl:
    json.dump(dict1, fl,ensure_ascii=False) 
print('ok')  

In [ ]:

import docx
import json
Doc = docx.Document(r"常见疾病辨病处方选穴.docx")
#print("檔案內含段落數：",len(Doc.paragraphs),"\n")
testList = []
text1 = []
dict1 = {}
for text in Doc.paragraphs:
    testList.append(text)
i = 0
for pg in testList:
    
    if len(pg.text) >0:
        s = ''.join(pg.text.split())        
        if s[0:1] == '第':
            i += 1
            n = 0
            
            dict1.setdefault(i,{})
            dict1[i]['title'] = pg.text.split('节')[1]
            dict1[i]['sub'] = {}
            
            #dict1[i]['title'].setdefault(i,{})
        elif s[0:1] == '（':
            sub = s.split('）')[1]
            dict2 = {}
            dict1[i]['sub'].setdefault(sub,[])
        else:
            dict1[i]['sub'][sub].append(s)
filename = '常见疾病辨病处方选穴.json'
with open(filename,'w') as fl:
    json.dump(dict1, fl,ensure_ascii=False)
print('ok')  

In [ ]:

import json
import re
filename = '症状对症处方选穴.json'
pattern = r'[\d\.]'
mo =r'[\u4e00-\u9fa5]+'
dict2 = {}
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
for k,v in dict1.items():
    m_title = v['title']
    for k1,v1 in v['sub'].items():
        sub_title = k1            
        s = ''
        for mx in v1:            
            s = s + mx
        list1 = re.split(pattern, s)
        list2 = []
        for ss in list1:
            if ss != '':
                list3 = re.findall(mo,ss)
                list2.append(list3)
                
        #print(m_title,sub_title,list2)
        dict2.setdefault(m_title,{})
        dict2[m_title][sub_title] = list2
filename = 'new_症状对症处方选穴.json'
with open(filename,'w') as fl:
    json.dump(dict2, fl,ensure_ascii=False) 
print('ok')  
       

word使用模板生成文档

In [ ]:

import openpyxl
from docxtpl import DocxTemplate

wb = openpyxl.load_workbook('file/火车餐厅人员信息表1.xlsx')
sheet = wb.active
# sheets = wb.sheetnames
list1 = []
context = {}
for n in range(2, sheet.max_row+1):
    dict1 = {}
    dict1['xh'] = sheet.cell(n,1).value
    dict1['xm'] = sheet.cell(n,2).value
    dict1['sfzhm'] = sheet.cell(n,3).value
    dict1['dh'] = sheet.cell(n,4).value
    dict1['cx'] = sheet.cell(n,5).value
    dict1['xzdz'] = sheet.cell(n,6).value
    list1.append(dict1)
context['info'] = list1
tpl = DocxTemplate("file/火车餐厅人员信息表.docx")
tpl.render(context)
tpl.save('file/test1.docx')

PDF文件读取

pdfminer读取PDF文件

In [ ]:

from newpdfminer.pdfparser import PDFParser, PDFDocument
from newpdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from newpdfminer.converter import PDFPageAggregator
from newpdfminer.layout import LAParams, LTTextBox
from newpdfminer.pdfinterp import PDFTextExtractionNotAllowed

path = "file/211027/114.pdf"

# 用文件对象来创建一个pdf文档分析器
praser = PDFParser(open(path, 'rb'))
# 创建一个PDF文档
doc = PDFDocument()
# 连接分析器 与文档对象
praser.set_document(doc)
doc.set_parser(praser)

# 提供初始化密码
# 如果没有密码 就创建一个空的字符串
doc.initialize()

# 检测文档是否提供txt转换，不提供就忽略
if not doc.is_extractable:
    raise PDFTextExtractionNotAllowed
else:
    # 创建PDf 资源管理器 来管理共享资源
    rsrcmgr = PDFResourceManager()
    # 创建一个PDF设备对象
    laparams = LAParams()
    device = PDFPageAggregator(rsrcmgr, laparams=laparams)
    # 创建一个PDF解释器对象
    interpreter = PDFPageInterpreter(rsrcmgr, device)

    # 循环遍历列表，每次处理一个page的内容
    for page in doc.get_pages():
        interpreter.process_page(page)                        
        # 接受该页面的LTPage对象
        layout = device.get_result()
        # 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
        # 包括 LTTextBox, LTFigure, LTImage, LTTextBoxHorizontal 等                            
        for x in layout:
            if isinstance(x, LTTextBox):
                print(x.get_text().strip())

pdfplumber读取PDF文件

In [ ]:

import pdfplumber
from PIL import Image

# 读取 PDF 文档
pdf = pdfplumber.open("5.pdf")

# 获取页数
print("总页数：",len(pdf.pages))
print("-----------------------------------------")

# 读取第 4 页；索引从 1 开始
page = pdf.pages[0] 
print("本页：",page.page_number + 1)
print("-----------------------------------------")
# 单页文件存储为图片
#im = page.to_image()
#im.save('./5_1.png', format='PNG')
# 单页文件中原始图片读取，不能读取图表文件
#imgs = page.images
#for i, img in enumerate(imgs):
#    size = img['width'], img['height']
#    data = img['stream'].get_data()
#    out_path = f'003pdf_images_{i}.png'
#    with open(out_path, 'wb') as fimg_out:
#        fimg_out.write(data)
# 导出第 4 页文本
text = page.extract_text()
print(text)

fitz1.8读取PDF文件中的图片

In [ ]:

import fitz
import re
import os

file_path = '5.pdf'  # PDF 文件路径
dir_path = './data' # 存放图片的文件夹

def pdf2image1(path, pic_path):
    checkIM = r"/Subtype(?= */Image)"
    pdf = fitz.open(path)
    lenXREF = pdf.xref_length()
    count = 1
    for i in range(1, lenXREF):
        text = pdf.xref_object(i)
        isImage = re.search(checkIM, text)
        if not isImage:
            continue
        pix = fitz.Pixmap(pdf, i)
        new_name = f"img_{count}.png"
        pix.writePNG(os.path.join(pic_path, new_name))
        count += 1
        pix = None

pdf2image1(file_path, dir_path)

Pdf文件拆分

In [ ]:

import os, sys
from PyPDF2 import PdfFileWriter, PdfFileReader, PdfFileMerger

file = "file/211027/114.pdf"
pdf_reader = PdfFileReader(file)
n = pdf_reader.numPages
print(n)
pdfWriter = PdfFileWriter()
pageObj = pdf_reader.getPage(n-2)
pageObj.scaleBy(1)
pdfWriter.addPage(pageObj)
with open('split_114.pdf', 'wb') as pdfOutputFile:
    pdfWriter.write(pdfOutputFile)

In [ ]:

import fitz
import os

file = "file/211027/114.pdf"
doc = fitz.open(file)
n = doc.page_count
print(n)
doc2 = fitz.open()
page = doc[n - 2]
#doc2.insert_pdf(doc, to_page = n-2)  # first 10 pages
doc2.insert_pdf(doc, from_page = n-2,to_page = n-2)
#print(type(page))
#doc2.insert_pdf(page) # last 10 pages
doc2.save("first-and-last-10.pdf")

提取Pdf页面合并文件

简单提取

In [ ]:

import fitz
import os
import glob

fi_path = 'file/2/'
dict1 = {}
fl = glob.glob(f'{fi_path}*.pdf')
list1 = []
i = 0
doc2 = fitz.open()
for fn in fl:
    doc = fitz.open(fn)
    doc2.insert_pdf(doc, from_page = 1,to_page = 1)
doc2.save("检查.pdf")    

提取页面并压缩

In [ ]:

import fitz
import os
import glob
import img2pdf

fi_path = 'file/2/'
zoom = 100
fl = glob.glob(f'{fi_path}*.pdf')

i = 0
doc2 = fitz.open()
for fn in fl:
    doc = fitz.open(fn)
    page = doc[1]
    trans = fitz.Matrix(zoom / 100.0, zoom / 100.0)
    pm = page.get_pixmap(matrix=trans)
    s = os.path.basename(fn).split('.')[0].rjust(5,'0')    
    lurl=f'pic/{s}.jpg'
    pm.save(lurl)   

fl=glob.glob('./pic/*.jpg')
fl.sort()
a4inpt = (img2pdf.mm_to_pt(210),img2pdf.mm_to_pt(297))
layout_fun = img2pdf.get_layout_fun(a4inpt)
with open("检查.pdf","wb") as f:
    f.write(img2pdf.convert(fl,layout_fun=layout_fun))

print('ok!')

多线程提取图片

In [ ]:

import fitz
import os
import glob
from multiprocessing.dummy import Pool

def get_image(fn):
    doc = fitz.open(fn)
    zoom = 100
    page = doc[1]
    trans = fitz.Matrix(zoom / 100.0, zoom / 100.0)
    pm = page.get_pixmap(matrix=trans)
    s = os.path.basename(fn).split('.')[0].rjust(5,'0')    
    lurl=f'pic1/{s}.jpg'
    pm.save(lurl)
    print(f'{s}已成功生成！')    
fi_path = 'file/2/'
fl = glob.glob(f'{fi_path}*.pdf')
pool = Pool(8)
pool.map(get_image,fl)
pool.close()
pool.join()

提取页面并分卷压缩

In [ ]:

import os
import glob
import img2pdf
import fitz

fi_path = 'file/2022-09-30/'
zoom = 100
fl = glob.glob(f'{fi_path}*.pdf')

for fn in fl:
    doc = fitz.open(fn)
    page = doc[1]
    trans = fitz.Matrix(zoom / 100.0, zoom / 100.0)
    pm = page.get_pixmap(matrix=trans)
    s = os.path.basename(fn).split('.')[0].rjust(5,'0')    
    lurl=f'pic/{s}.jpg'
    pm.save(lurl)   


fl=glob.glob('./pic/*.jpg')
fl.sort()
a4inpt = (img2pdf.mm_to_pt(210),img2pdf.mm_to_pt(297))
layout_fun = img2pdf.get_layout_fun(a4inpt)
i = 1
n = 1
list1 = []
for fl1 in fl:
    list1.append(fl1)
    if len(list1) == 200:
        with open(f"检查{str(i)}.pdf","wb") as f:
            f.write(img2pdf.convert(list1,layout_fun=layout_fun))
        i +=1
        list1 = []
if len(list1)>0:
        with open(f"检查{str(i)}.pdf","wb") as f:
            f.write(img2pdf.convert(list1,layout_fun=layout_fun))

print('ok!')

In [ ]:

import os
import glob
import img2pdf

fi_path = 'file/2/'

fl=glob.glob('./pic/*.jpg')
fl.sort()
a4inpt = (img2pdf.mm_to_pt(210),img2pdf.mm_to_pt(297))
layout_fun = img2pdf.get_layout_fun(a4inpt)
i = 1
n = 1
list1 = []
for fl1 in fl:
    list1.append(fl1)
    if len(list1) == 200:
        with open(f"检查{str(i)}.pdf","wb") as f:
            f.write(img2pdf.convert(list1,layout_fun=layout_fun))
        i +=1
        list1 = []
if len(list1)>0:
        with open(f"检查{str(i)}.pdf","wb") as f:
            f.write(img2pdf.convert(list1,layout_fun=layout_fun))

print('ok!')

使用PyPdf2简单提取

In [ ]:

import os, sys
from PyPDF2 import PdfFileWriter, PdfFileReader, PdfFileMerger
import glob

fi_path = 'file/2/'
fl = glob.glob(f'{fi_path}*.pdf')
pdfWriter = PdfFileWriter()
i = 0
doc2 = fitz.open()
for fn in fl:
    pdf_reader = PdfFileReader(fn)
    pageObj = pdf_reader.getPage(1)
    pdfWriter.addPage(pageObj)
with open('split_114.pdf', 'wb') as pdfOutputFile:    
    pdfWriter.write(pdfOutputFile)   

PDF文件读取表格

In [5]:

import pdfplumber
import json
import re

file = "file/01730823-邵希强.pdf"
pdf = pdfplumber.open(file)
list1 = []
dict1 = {}
n = 1
for page in pdf.pages:
    # print(page.extract_text())
    
    
    for pdf_table in page.extract_tables():
        list2 = []
        table = []
        cells = []
        for row in pdf_table:
            if not any(row):
                # 如果一行全为空，则视为一条记录结束
                if any(cells):
                    table.append(cells)
                    cells = []
            elif all(row):
                # 如果一行全不为空，则本条为新行，上一条结束
                if any(cells):
                    table.append(cells)
                    cells = []
                table.append(row)
            else:
                if len(cells) == 0:
                    cells = row
                else:
                    for i in range(len(row)):
                        if row[i] is not None and not cells[i]:
                            cells[i] = row[i]
                        elif row[i] is not None and cells[i]:                            
                            table.append(cells)
                            cells = row
                            #cells[i] = row[i]
                            break
                        elif row[i] is None and cells[i]:
                            continue
                        elif row[i] is None and not cells[i]:
                            #cells[i] = row[i]
                            continue                        
                        #    cells[i] = row[i] if cells[i] is None else cells[i] + row[i]
       
        list2 = []                    
        for row in table:
            data =[re.sub('\s+', '', cell) if cell is not None else None for cell in row]
            print(data)
            
            #print(json.dumps(data_list, indent=2, ensure_ascii=False))
            #with open('Test1.json','a',encoding="utf-8") as file:   # json文件的存放位置
            #    json.dump(data_list, file, ensure_ascii=False)
            list2.append(data)
        if len(list2) > 0:
            dict1[n] = list2
        #print(dict1)
        #list1.append(list2)
        n +=1
with open('Test1.json','w',encoding="utf-8") as file:
    json.dump(dict1, file, ensure_ascii=False)
            
pdf.close()

<>:51: SyntaxWarning: invalid escape sequence '\s'
<>:51: SyntaxWarning: invalid escape sequence '\s'
/tmp/ipykernel_1730998/3799497539.py:51: SyntaxWarning: invalid escape sequence '\s'
  data =[re.sub('\s+', '', cell) if cell is not None else None for cell in row]

['姓名', '邵希强']
['性别', '男']
['测试标准', '国民体质测定标准']
['身高体重指数', '26.02', '60分']
['握力', '33.5千克', '50分']
['肺活量', '3050毫升', '70分']
['选择反应时', '0.572秒', '75分']
['指标', '您的结果', '亚洲男性平均值']
['臀围', '100', '88.82']
['身高腰围指数', '53.19', '42.79']
['建议类别', '建议项']
['增加摄入', '豆类、水果、蔬菜、坚果类、蛋类、菌类、乳制品、肉类']
['生活习惯', '提高睡眠质量、保持心情舒畅、换季时避开感染源、减少用眼']

In [13]:

import pdfplumber
name = 'file/01730823-邵希强.pdf'

pdf = pdfplumber.open(name)
tables =pdf.pages[1].extract_tables()
df1 = tables
for item in df1:
    print(item)

[['姓名', '邵希强']]
[['性别', '男']]
[['测试标准', '国民体质测定标准']]
[['身高体重指数', '26.02', '60分']]
[['握力', '33.5 千克', '50分']]
[['肺活量', '3050 毫升', '70分']]
[['选择反应时', '0.572 秒', '75分']]

In [30]:

import pdfplumber
name = 'file/01730823-邵希强.pdf'
pdf = pdfplumber.open(name)
text = pdf.pages[1].extract_text()#######页码从0开始计数
#print(text)
list1 = text.split('\n')
print(list1)
for item in list1:
    if '测试标准 国民体质测定标准' in item:
        list_min = list1.index(item)
    if '请注意：以上测试项目' in item:
        list_max = list1.index(item)
print(list_min,list_max)
for i in range(list_min+1,list_max):
    print(list1[i])

['北体乾元健康管理中心', '姓名 邵希强', '中石化(天津)石油化工 编号 01730823', '有限公司 性别 男', '年龄 53', '国民体质检测结果与健康处方', '肺活量', '握力 身高体重指数', '坐位体前屈 选择反应时', '纵跳 闭眼单脚站立', '俯卧撑', '测试标准 国民体质测定标准', '闭眼单脚站立 2.8 秒 10分', '身高体重指数 26.02 60分', '坐位体前屈 13.5 厘米 90分', '握力 33.5 千克 50分', '纵跳 18.0 厘米 30分', '肺活量 3050 毫升 70分', '俯卧撑 5 次 50分', '选择反应时 0.572 秒 75分', '腰臀比 0.90 正常', '请注意：以上测试项目及格线为3分。列表中红色项目需重点关注，建议在专家指导下进行科学锻炼，', '减少潜在的运动风险。', '感谢您完成测试，以《国民体质测定标准》综合评级，您的总分为58分，等级为四级（不合格）。', '（其中项目纵跳因超出年龄范围得分仅供参考，不计入总分）', '北体乾元体质监测报告']
11 21
闭眼单脚站立 2.8 秒 10分
身高体重指数 26.02 60分
坐位体前屈 13.5 厘米 90分
握力 33.5 千克 50分
纵跳 18.0 厘米 30分
肺活量 3050 毫升 70分
俯卧撑 5 次 50分
选择反应时 0.572 秒 75分
腰臀比 0.90 正常

In [ ]: