177 lines
6.1 KiB
Python
177 lines
6.1 KiB
Python
|
# 读取PDF
|
|||
|
|
import PyPDF2
|
|||
|
|
# 分析PDF的layout，提取文本
|
|||
|
|
from pdfminer.high_level import extract_pages, extract_text
|
|||
|
|
from pdfminer.layout import LTTextContainer, LTChar, LTRect, LTFigure
|
|||
|
|
# 从PDF的表格中提取文本
|
|||
|
|
import pdfplumber
|
|||
|
|
|
|||
|
|
import os
|
|||
|
|
|
|||
|
|
# 创建一个文本提取函数
|
|||
|
|
|
|||
|
|
def text_extraction(element):
|
|||
|
|
# 从行元素中提取文本
|
|||
|
|
line_text = element.get_text()
|
|||
|
|
|
|||
|
|
# 探析文本的格式
|
|||
|
|
# 用文本行中出现的所有格式初始化列表
|
|||
|
|
line_formats = []
|
|||
|
|
for text_line in element:
|
|||
|
|
if isinstance(text_line, LTTextContainer):
|
|||
|
|
# 遍历文本行中的每个字符
|
|||
|
|
for character in text_line:
|
|||
|
|
if isinstance(character, LTChar):
|
|||
|
|
# 追加字符的font-family
|
|||
|
|
line_formats.append(character.fontname)
|
|||
|
|
# 追加字符的font-size
|
|||
|
|
line_formats.append(character.size)
|
|||
|
|
# 找到行中唯一的字体大小和名称
|
|||
|
|
format_per_line = list(set(line_formats))
|
|||
|
|
|
|||
|
|
# 返回包含每行文本及其格式的元组
|
|||
|
|
return (line_text, format_per_line)
|
|||
|
|
|
|||
|
|
# 从页面中提取表格内容
|
|||
|
|
|
|||
|
|
def extract_table(pdf_path, page_num, table_num):
|
|||
|
|
# 打开PDF文件
|
|||
|
|
pdf = pdfplumber.open(pdf_path)
|
|||
|
|
# 查找已检查的页面
|
|||
|
|
table_page = pdf.pages[page_num]
|
|||
|
|
# 提取适当的表格
|
|||
|
|
table = table_page.extract_tables()[table_num]
|
|||
|
|
return table
|
|||
|
|
|
|||
|
|
# 将表格转换为适当的格式
|
|||
|
|
def table_converter(table):
|
|||
|
|
table_string = ''
|
|||
|
|
# 遍历表格的每一行
|
|||
|
|
for row_num in range(len(table)):
|
|||
|
|
row = table[row_num]
|
|||
|
|
# 从warp的文字删除线路断路器
|
|||
|
|
cleaned_row = [item.replace('\n', ' ') if item is not None and '\n' in item else 'None' if item is None else item for item in row]
|
|||
|
|
# 将表格转换为字符串，注意'|'、'\n'
|
|||
|
|
table_string+=('|'+'|'.join(cleaned_row)+'|'+'\n')
|
|||
|
|
# 删除最后一个换行符
|
|||
|
|
table_string = table_string[:-1]
|
|||
|
|
return table_string
|
|||
|
|
|
|||
|
|
# 查找PDF路径
|
|||
|
|
pdf_path = '/Users/zhengfei/Desktop/科润智控.pdf'
|
|||
|
|
|
|||
|
|
# 创建一个PDF文件对象
|
|||
|
|
pdfFileObj = open(pdf_path, 'rb')
|
|||
|
|
# 创建一个PDF阅读器对象
|
|||
|
|
pdfReaded = PyPDF2.PdfReader(pdfFileObj)
|
|||
|
|
|
|||
|
|
# 创建字典以从每个图像中提取文本
|
|||
|
|
text_per_page = {}
|
|||
|
|
# 我们从PDF中提取页面
|
|||
|
|
for pagenum, page in enumerate(extract_pages(pdf_path)):
|
|||
|
|
|
|||
|
|
# 初始化从页面中提取文本所需的变量
|
|||
|
|
pageObj = pdfReaded.pages[pagenum]
|
|||
|
|
page_text = []
|
|||
|
|
line_format = []
|
|||
|
|
text_from_images = []
|
|||
|
|
text_from_tables = []
|
|||
|
|
page_content = []
|
|||
|
|
# 初始化检查表的数量
|
|||
|
|
table_num = 0
|
|||
|
|
first_element= True
|
|||
|
|
table_extraction_flag= False
|
|||
|
|
# 打开pdf文件
|
|||
|
|
pdf = pdfplumber.open(pdf_path)
|
|||
|
|
# 查找已检查的页面
|
|||
|
|
page_tables = pdf.pages[pagenum]
|
|||
|
|
# 找出本页上的表格数目
|
|||
|
|
tables = page_tables.find_tables()
|
|||
|
|
|
|||
|
|
|
|||
|
|
# 找到所有的元素
|
|||
|
|
page_elements = [(element.y1, element) for element in page._objs]
|
|||
|
|
# 对页面中出现的所有元素进行排序
|
|||
|
|
page_elements.sort(key=lambda a: a[0], reverse=True)
|
|||
|
|
|
|||
|
|
# 查找组成页面的元素
|
|||
|
|
for i,component in enumerate(page_elements):
|
|||
|
|
# 提取PDF中元素顶部的位置
|
|||
|
|
pos= component[0]
|
|||
|
|
# 提取页面布局的元素
|
|||
|
|
element = component[1]
|
|||
|
|
|
|||
|
|
# 检查该元素是否为文本元素
|
|||
|
|
if isinstance(element, LTTextContainer):
|
|||
|
|
# 检查文本是否出现在表中
|
|||
|
|
if table_extraction_flag == False:
|
|||
|
|
# 使用该函数提取每个文本元素的文本和格式
|
|||
|
|
(line_text, format_per_line) = text_extraction(element)
|
|||
|
|
# 将每行的文本追加到页文本
|
|||
|
|
page_text.append(line_text)
|
|||
|
|
# 附加每一行包含文本的格式
|
|||
|
|
line_format.append(format_per_line)
|
|||
|
|
page_content.append(line_text)
|
|||
|
|
else:
|
|||
|
|
# 省略表中出现的文本
|
|||
|
|
pass
|
|||
|
|
|
|||
|
|
# 检查表的元素
|
|||
|
|
if isinstance(element, LTRect):
|
|||
|
|
# 如果第一个矩形元素
|
|||
|
|
if first_element == True and (table_num+1) <= len(tables):
|
|||
|
|
# 找到表格的边界框
|
|||
|
|
lower_side = page.bbox[3] - tables[table_num].bbox[3]
|
|||
|
|
upper_side = element.y1
|
|||
|
|
# 从表中提取信息
|
|||
|
|
table = extract_table(pdf_path, pagenum, table_num)
|
|||
|
|
# print('第'+str(pagenum)+'页第'+str(table_num)+'个表格')
|
|||
|
|
# print(table)
|
|||
|
|
# 将表信息转换为结构化字符串格式
|
|||
|
|
table_string = table_converter(table)
|
|||
|
|
# 将表字符串追加到列表中
|
|||
|
|
text_from_tables.append(table_string)
|
|||
|
|
page_content.append(table_string)
|
|||
|
|
# 将标志设置为True以再次避免该内容
|
|||
|
|
table_extraction_flag = True
|
|||
|
|
# 让它成为另一个元素
|
|||
|
|
first_element = False
|
|||
|
|
# 在文本和格式列表中添加占位符
|
|||
|
|
# page_text.append('table')
|
|||
|
|
# line_format.append('table')
|
|||
|
|
|
|||
|
|
# 检查我们是否已经从页面中提取了表
|
|||
|
|
if element.y0 >= lower_side and element.y1 <= upper_side:
|
|||
|
|
pass
|
|||
|
|
elif not isinstance(page_elements[i+1][1], LTRect):
|
|||
|
|
table_extraction_flag = False
|
|||
|
|
first_element = True
|
|||
|
|
table_num+=1
|
|||
|
|
|
|||
|
|
print('第'+str(pagenum)+'部分')
|
|||
|
|
print('page_text:')
|
|||
|
|
print(page_text)
|
|||
|
|
#print('line_format:')
|
|||
|
|
#print(line_format)
|
|||
|
|
#print('text_from_tables:')
|
|||
|
|
#print(text_from_tables)
|
|||
|
|
#print('page_content:')
|
|||
|
|
#print(page_content)
|
|||
|
|
|
|||
|
|
# 创建字典的键
|
|||
|
|
dctkey = 'Page_'+str(pagenum)
|
|||
|
|
# 将list的列表添加为页键的值
|
|||
|
|
|
|||
|
|
# 关闭pdf文件对象
|
|||
|
|
pdfFileObj.close()
|
|||
|
|
|
|||
|
|
# 删除已创建的过程文件
|
|||
|
|
# os.remove('cropped_image.pdf')
|
|||
|
|
# os.remove('PDF_image.png')
|
|||
|
|
|
|||
|
|
# 显示页面内容
|
|||
|
|
# result = ''.join(text_per_page['Page_0'][4])
|
|||
|
|
# print(result)
|
|||
|
|
|
|||
|
|
# result1 = ''.join(text_per_page['Page_1'][4])
|
|||
|
|
# print(result1)
|