phtyon读取pdf的远程地址解析内容

import xlwt,pymysql,requests,json,datetime,PyPDF2,urllib.request,io,ssl

添加context 解决读取pdf时SSL报错问题

context = ssl._create_unverified_context()

读取pdf地址 获取pdf内容

req = urllib.request.urlopen(contract_download_url,context=context)

remote_file=req.read()

memory_file = io.BytesIO(remote_file)

read_pdf = PyPDF2.PdfReader(memory_file)

获取pdf页数

number_of_pages = len(read_pdf.pages)

for i in range(0, number_of_pages):

pageObj = read_pdf.pagesi

获取当前页数的pdf内容

page = pageObj.extract_text()

处理后续业务流程 .......................