def deal_pdf(file_path):
"""
批量处理pdf
:param file_path:
:return:
"""
files = os.listdir(file_path)
# List中是所有pdf，每个pdf分为title：content：tables1：tablesi
all_pdf = []
for file in files:
if not os.path.isdir(file) and file.endswith(".pdf"):
parsed_pdf = []
f_path = file_path + file
file_title = "".join(file.split(".pdf"))
pdf_parser = PDFParser(f_path)
logging.info("开始处理文章： %s" % file_title)
print("开始处理文章： %s" % file_title)
try:
pdf_texts, pdf_tables = pdf_parser.parser()
except Exception as e:
logging.warning("处理：*%s*时出错：%s" % (file_title, e))
pdf_texts = ''
pdf_tables = None
# 拼成(title, pdf_text, pdf_tables的形式，表格往后排列)
pdf_texts = "".join(pdf_texts)
parsed_pdf.append(file_title)
parsed_pdf.append(pdf_texts)
if pdf_tables is not None:
for tab in pdf_tables:
parsed_pdf.append(tab)
all_pdf.append(parsed_pdf)
return all_pdf
def server():
print('Compiling assets...')
compile_assets()
app.PDFParser = PDFParser()
return app
def _load_report(self, new_report, old_report, **kwargs):
self.report = []
parser_a = PDFParser()
parse_new_result = parser_a.parse(new_report, kwargs.get("password_a", ""))
new_index_tree = parser_a.analyze("Monetary Report", parse_new_result)
self.report.append(new_index_tree)
parser_b = PDFParser()
parse_old_result = parser_b.parse(old_report, kwargs.get("password_b", ""))
old_index_tree = parser_b.analyze("Monetary Report", parse_old_result)
self.report.append(old_index_tree)