python提取pdf一页中多个表格

要在Python中提取PDF一页中的多个表格，可以使用第三方库，如PyPDF2或pdfminer。以下是一个使用pdfminer解析PDF并提取表格的示例代码：

import pdfminer
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfpage import PDFPage
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import LTTextBoxHorizontal, LAParams, LTChar, LTTextLineHorizontal, LTTextBoxVertical, LTTextLine

# 获取PDF页面布局信息
def getPageLayout(page):
    layout = []
    for lt_obj in page:
        if isinstance(lt_obj, LTTextBoxHorizontal):
            layout.append(lt_obj)
        elif isinstance(lt_obj, LTTextLineHorizontal):
            layout.append(lt_obj)
    return layout

# 获取PDF页面中的表格
def getTables(layout):
    tables = []
    for lt_obj in layout:
        if isinstance(lt_obj, LTTextLineHorizontal) and lt_obj.get_text().startswith('Table'):
            table = []
            for child in lt_obj._objs:
                if isinstance(child, LTTextLineHorizontal):
                    table.append(child)
            tables.append(table)
    return tables

# 解析PDF文件并提取表格
def extractTablesFromPDF(pdf_path, page_num):
    tables = []
    fp = open(pdf_path, 'rb')
    parser = PDFParser(fp)
    doc = PDFDocument(parser)
    rsrcmgr = PDFResourceManager()
    laparams = LAParams()
    device = PDFPageAggregator(rsrcmgr, laparams=laparams)
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    for i, page in enumerate(PDFPage.create_pages(doc)):
        if i == page_num:
            interpreter.process_page(page)
            layout = device.get_result()
            tables = getTables(getPageLayout(layout))
            break
    fp.close()
    return tables

# 指定要提取表格的PDF文件路径和页面编号
pdf_path = 'example.pdf'
page_num = 0
tables = extractTablesFromPDF(pdf_path, page_num)

# 打印提取到的表格
for i, table in enumerate(tables):
    print('Table', i+1, ':')
    for line in table:
        print(line.get_text().strip())
    print('\n')

你可以根据自己的需求对这个示例代码进行进一步修改和优化。