def convert_pdf_to_txt(path):
fp = open(path, 'rb')
txt = ''
parser = PDFParser(fp)
doc = PDFDocument()
parser.set_document(doc)
doc.set_parser(parser)
doc.initialize('')
rsrcmgr = PDFResourceManager()
laparams = LAParams()
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
# Process each page contained in the document.
for page in doc.get_pages():
interpreter.process_page(page)
layout = device.get_result()
for lt_obj in layout:
if isinstance(lt_obj, LTTextBox) or isinstance(lt_obj, LTTextLine):
txt += lt_obj.get_text()
return (txt)
def parse(path):
fp = open(path, 'rb') # 以二进制读模式打开
praser = PDFParser(fp)
# 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)
fulltext = []
# 循环遍历列表，每次处理一个page的内容
for page in doc.get_pages(): # doc.get_pages() 获取page列表
interpreter.process_page(page)
# 接受该页面的LTPage对象
layout = device.get_result()
str_page = ""
for x in layout:
if isinstance(x, LTTextBoxHorizontal):
results = x.get_text()
str_page += results
fulltext.append(str_page)
return fulltext
def extract_pdf(self):
assert self.extension in ['pdf']
self.content = self.file.read()
parser = PDFParser(self.file)
doc = PDFDocument(parser)
available_fields = list(doc.info[0].keys())
self.properties['auteur'] = None
self.properties['creation_date'] = None
self.properties['modification_date'] = None
self.properties['creator'] = None
self.properties['producer'] = None
if 'CreationDate' in available_fields:
if isinstance(doc.info[0]["CreationDate"], PDFObjRef):
doc.info[0]["CreationDate"] = resolve1(
doc.info[0]["CreationDate"])
try:
pdf_creation_date = str(
self.convertPdfDatetime(doc.info[0]["CreationDate"]))
self.properties['creation_date'] = str(pdf_creation_date)
except:
pass
if 'ModDate' in available_fields:
if isinstance(doc.info[0]["ModDate"], PDFObjRef):
doc.info[0]["ModDate"] = resolve1(doc.info[0]["ModDate"])
try:
pdf_modif_date = str(
self.convertPdfDatetime(doc.info[0]["ModDate"]))
self.properties['modification_date'] = str(pdf_modif_date)
except:
pass
if 'Author' in available_fields:
if isinstance(doc.info[0]["Author"], PDFObjRef):
doc.info[0]["Author"] = resolve1(doc.info[0]["Author"])
try:
pdf_auteur = doc.info[0]["Author"].decode("utf-8")
self.properties['auteur'] = pdf_auteur
except:
pass
if 'Creator' in available_fields:
if isinstance(doc.info[0]["Creator"], PDFObjRef):
doc.info[0]["Creator"] = resolve1(doc.info[0]["Creator"])
try:
pdf_creator = doc.info[0]["Creator"].decode("utf-16")
self.properties['creator'] = pdf_creator
except:
pass
if 'Producer' in available_fields:
if isinstance(doc.info[0]["Producer"], PDFObjRef):
doc.info[0]["Producer"] = resolve1(doc.info[0]["Producer"])
try:
pdf_producer = doc.info[0]["Producer"].decode("utf-16")
self.properties['producer'] = pdf_producer
except:
pass
parser.set_document(doc)
pages = resolve1(doc.catalog['Pages'])
pages_count = pages.get('Count', 0)
#Only the first 300 characters for clarity
self.content = self.convert_pdf_to_txt()
self.properties['content'] = self.content[:300] + '(...)'
self.properties['page_count'] = pages_count
return self.properties
