引入必要模块:
from pdfminer.converter import TextConverter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfinterp import PDFResourceManager,PDFPageInterpreter
from pdfminer.pdfpage import PDFPage
from pdfminer.pdfparser import PDFParser
from io import StringIO
读取PDF:
output_string = StringIO()
with open('./tests/daily_report.pdf','rb') as f:
ps = PDFParser(f)
doc = PDFDocument(ps)
res = PDFResourceManager()
device = TextConverter(res,output_string,laparams=LAParams())
interparter = PDFPageInterpreter(res,device)
for page in PDFPage.create_pages(doc):
interparter.process_page(page)
print(output_string.getvalue())