from pdfminer.pdfparser import PDFParser, PDFDocumentfrom pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreterfrom pdfminer.converter import PDFPageAggregatorfrom pdfminer.layout import LAParams, LTTextBoxfrom pdfminer.pdfinterp import PDFTextExtractionNotAllowedpath = "test.pdf"# 用文件對(duì)象來創(chuàng)建一個(gè)pdf文檔分析器praser = PDFParser(open(path, 'rb'))# 創(chuàng)建一個(gè)PDF文檔doc = PDFDocument()# 連接分析器 與文檔對(duì)象praser.set_document(doc)doc.set_parser(praser)# 提供初始化密碼# 如果沒有密碼 就創(chuàng)建一個(gè)空的字符串doc.initialize()# 檢測(cè)文檔是否提供txt轉(zhuǎn)換，不提供就忽略if not doc.is_extractable:    raise PDFTextExtractionNotAllowedelse:    # 創(chuàng)建PDf 資源管理器 來管理共享資源    rsrcmgr = PDFResourceManager()    # 創(chuàng)建一個(gè)PDF設(shè)備對(duì)象    laparams = LAParams()    device = PDFPageAggregator(rsrcmgr, laparams=laparams)    # 創(chuàng)建一個(gè)PDF解釋器對(duì)象    interpreter = PDFPageInterpreter(rsrcmgr, device)    # 循環(huán)遍歷列表，每次處理一個(gè)page的內(nèi)容    for page in doc.get_pages():        interpreter.process_page(page)                                # 接受該頁(yè)面的LTPage對(duì)象        layout = device.get_result()        # 這里layout是一個(gè)LTPage對(duì)象，里面存放著這個(gè) page 解析出的各種對(duì)象        # 包括 LTTextBox, LTFigure, LTImage, LTTextBoxHorizontal 等                                    for x in layout:            if isinstance(x, LTTextBox):                print(x.get_text().strip())

import tabulapath = 'test.pdf'df = tabula.read_pdf(path, encoding='gbk', pages='all')for indexs in df.index:    print(df.loc[indexs].values)# tabula.convert_into(path, os.path.splitext(path)[0]+'.csv', pages='all')

import pdfplumberpath = 'test.pdf'pdf = pdfplumber.open(path)for page in pdf.pages:    # 獲取當(dāng)前頁(yè)面的全部文本信息，包括表格中的文字    # print(page.extract_text())                            for table in page.extract_tables():        # print(table)        for row in table:            print(row)        print('---------- 分割線 ----------')pdf.close()

import pdfplumberimport repath = 'test1.pdf'pdf = pdfplumber.open(path)for page in pdf.pages:    print(page.extract_text())    for pdf_table in page.extract_tables():        table = []        cells = []        for row in pdf_table:            if not any(row):                # 如果一行全為空，則視為一條記錄結(jié)束                if any(cells):                    table.append(cells)                    cells = []            elif all(row):                # 如果一行全不為空，則本條為新行，上一條結(jié)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:                            cells[i] = row[i] if cells[i] is None else cells[i] + row[i]        for row in table:            print([re.sub('\s+', '', cell) if cell is not None else None for cell in row])        print('---------- 分割線 ----------')pdf.close()