我想根据文本的坐标从使用 pdfminer 的文件夹中转换多个 PDF 文件并将我的结果存储到列表或字典中来提取文本。我最初设法转换单个文件,并能够根据其坐标提取文本。
我必须说我不是很擅长 Python,但我正在尽力而为。如果有人能告诉我如何修复以下代码,我将不胜感激:
import os
import glob
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfpage import PDFPage
from pdfminer.pdfpage import PDFTextExtractionNotAllowed
from pdfminer.pdfinterp import PDFResourceManager
from pdfminer.pdfinterp import PDFPageInterpreter
from pdfminer.pdfdevice import PDFDevice
from pdfminer.layout import LAParams
from pdfminer.converter import PDFPageAggregator
import pdfminer
from cStringIO import StringIO
directory = os.path.abspath('./')
pdfFiles = glob.glob(os.path.join(directory, '*.pdf'))
resourceManager = PDFResourceManager()
returnString = StringIO()
codec = 'utf-8'
laParams = LAParams()
device = PDFPageAggregator(resourceManager, laparams=laParams)
interpreter = PDFPageInterpreter(resourceManager, device)
maxPages = 0
caching = True
pageNums=set()
for one_pdf in pdfFiles:
print("Processing file: " + str(one_pdf))
fp = file(one_pdf, 'rb')
name = "one_pdf"
lst =[]
def parse_obj(lt_objs):
for one_pdf in enumerate(pdfFiles):
for obj in lt_objs:
if isinstance(obj, pdfminer.layout.LTTextBoxHorizontal):
print "%6d, %6d, %s" % (obj.bbox[0], obj.bbox[1], obj.get_text().replace('\n', '_'))
lst.append([one_pdf,[[obj.bbox[0],obj.bbox[1]], obj.get_text()]])
elif isinstance(obj, pdfminer.layout.LTFigure):
parse_obj(obj._objs)
for page in PDFPage.get_pages(fp, pageNums, maxpages=maxPages,caching=caching, check_extractable=True):
interpreter.process_page(page)
layout = device.get_result()
parse_obj(layout._objs)
device.close()
returnString.close()
代码输出给定文件夹中 PDF 的名称,后跟 PDF 文本布局。这是我无法将结果成功存储到嵌套列表或字典中的地方。
请您参考如下方法:
我想我已经想出了如何将 pdf 名称作为键及其内容连同内容的坐标存储到字典 (pdf_dict) 中。
lst=[]
dicts_from_file =[]
pdf_dict = {}
for one_pdf in pdfFiles:
#print("Processing file: " + str(one_pdf))
fp = file(one_pdf, 'rb')
name = str(one_pdf)
head, tail = os.path.split(name)
dicts_from_file.append({tail})
def parse_obj(lt_objs):
for obj in lt_objs:
if isinstance(obj, pdfminer.layout.LTTextBoxHorizontal):
lst.append([[obj.bbox[0],obj.bbox[1]],obj.get_text().replace('\n', '')])
pdf_dict.update( {tail : lst} )
elif isinstance(obj, pdfminer.layout.LTFigure):
parse_obj(obj._objs)
return []
for page in PDFPage.get_pages(fp, pageNums, maxpages=maxPages, password=password,caching=caching, check_extractable=True):
interpreter.process_page(page)
layout = device.get_result()
parse_obj(layout._objs)
device.close()
returnString.close()
