基于Python实现的PDF格式转换器测试版

# -*- 作者：闫浩 -*-# """日期:2022年04月26日""" """ 文件转换 1. pdf 转换 doc 2. doc/docx 转换 pdf """ import requests import string import time import math import random import os from requests_toolbelt import MultipartEncoder class PdfToWord(object): """pdf 转 word""" def __init__(self, pdf_path, word_path=None): self.url = "https://pdf2doc.com" self.uid = None self.id_ = None self.pdf_path = pdf_path self.word_path = word_path self.prepare() def prepare(self): self.uid = self.get_uid() # self.id_ = self.get_id() # id_ ：可以是任意字符串。 self.id_ = "o_1f0b39rqd9c013o8os1rh313s91" @staticmethod def __base32(x): result = "" while x > 0: result = string.printable[x % 32] + result x //= 32 return result def get_id(self): uid = self.__base32(int(time.time() * 1000)) # Python equivalent of new Date().getTime().toString(32) for x in range(5): uid += self.__base32(int(math.floor(random.random() * 65535))) return "o_" + uid + self.__base32(1) @staticmethod def get_uid(): chars = "0123456789abcdefghiklmnopqrstuvwxyz" result = "" for x in range(16): char = int(math.floor(random.random() * len(chars))) result += chars[char:char + 1] return result def process(self): """ 文件处理： 1.上传； 2.转换； 3.查看转换状态； 4.下载； :return: """ # pdf 文件上传 self.upload(self.pdf_path) # pdf 转换 Word self.convert() def upload(self, file_path): """ pdf文件上传操作 :param file_path: :return: """ # file_name = file_path.split("\\")[-1] # print(file_name) file_name = "a.pdf" f = open(file_path, "rb") param = { "id": self.id_, "name": file_name, "file": (file_name, f, "application/pdf") } form_data = MultipartEncoder(fields=param) header = { "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.190 Safari/537.36", "Content-Type": form_data.content_type } new_url = "{}/upload/{}".format(self.url, self.uid) requests.post(new_url, data=form_data, headers=header) """ response.text: {"data":{"file":"a.pdf","file_size_human":"146K"},"id":"o_1f0b39rqd9c013o8os1rh313s91","jsonrpc":"2.0","result":null} """ f.close() def convert(self): """上传pdf 转换 word""" url = "{}/convert/{}/{}".format(self.url, self.uid, self.id_) response = requests.get(url) result = response.json() if result.get("status") == "success": # 转换成功，查看转换状态，获取word文件名 word_file_name = self.status() if not word_file_name: print("转换失败") # 下载word 文件 self.download_(word_file_name) time.sleep(1) def status(self): """ 查看文件转换状态 :return: 文件名 """ url = "{}/status/{}/{}".format(self.url, self.uid, self.id_) response = requests.get(url) result = response.json() return result.get("convert_result") def download_(self, word_file): """ 下载模块 :param word_file: :return: """ url = "{}/download/{}/{}/{}".format(self.url, self.uid, self.id_, word_file) response = requests.get(url) with open(self.word_path, "wb") as f: f.write(response.content) class WordToPdf(object): """doc/docx 转换 pdf""" def __init__(self, word_path, pdf_path): self.url = "https://doctopdf.com" self.word_path = word_path self.pdf_path = pdf_path self.uid = None self.id_ = None self.prepare() def prepare(self): self.uid = self.get_uid() # self.id_ = self.get_id() # id_ ：可以是任意字符串。 self.id_ = "o_1f0b39rqd9c013o8os1rh313s91" @staticmethod def get_uid(): chars = "0123456789abcdefghiklmnopqrstuvwxyz" result = "" for x in range(16): char = int(math.floor(random.random() * len(chars))) result += chars[char:char + 1] return result def process(self): """ 文件处理： 1.上传； 2.转换； 3.查看转换状态； 4.下载； :return: """ # word 文件上传 self.upload(self.word_path) # doc/docx 转换 pdf self.convert() def upload(self, file_path): """ pdf文件上传操作 :param file_path: :return: """ # file_name = file_path.split("\\")[-1] # print(file_name) ext = file_path.split(".")[-1] file_name = f"a.{ext}" f = open(file_path, "rb") param = { "id": self.id_, "name": file_name, "file": (file_name, f, "application/doc") } form_data = MultipartEncoder(fields=param) header = { "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.190 Safari/537.36", "Content-Type": form_data.content_type } new_url = "{}/upload/{}".format(self.url, self.uid) res = requests.post(new_url, data=form_data, headers=header) """ response.text: {"data":{"file":"a.pdf","file_size_human":"146K"},"id":"o_1f0b39rqd9c013o8os1rh313s91","jsonrpc":"2.0","result":null} """ f.close() def convert(self): """上传pdf 转换 word""" url = "{}/convert/{}/{}".format(self.url, self.uid, self.id_) response = requests.get(url) result = response.json() if result.get("status") == "success": # 转换成功，查看转换状态，获取word文件名 word_file_name = self.status() if not word_file_name: print("转换失败") # 下载word 文件 self.download_(word_file_name) time.sleep(1) def status(self): """ 查看文件转换状态 :return: 文件名 """ url = "{}/status/{}/{}".format(self.url, self.uid, self.id_) response = requests.get(url) result = response.json() return result.get("convert_result") def download_(self, d_file): """ 下载模块 :param d_file: :return: """ url = "{}/download/{}/{}/{}".format(self.url, self.uid, self.id_, d_file) response = requests.get(url) with open(self.pdf_path, "wb") as f: f.write(response.content) # def main(): # print("1111") # if len(sys.argv) < 2: # print("Usage : python3 {} [user_name]".format(sys.argv[0])) # return # pdf_list = sys.argv[1:] # print(pdf_list) # new_pdf_list = [] # for pdf in pdf_list: # if not os.path.exists(pdf): # continue # file_name, ext = None, None # try: # file_name, ext = pdf.split(".") # except ValueError as e: # print("异常：{}".format(e)) # except Exception as e: # print("未知错误：{}".format(e)) # print(file_name, ext) # if ext not in ("pdf",): # continue # new_pdf_list.append(pdf) # p = PdfToWord() # p.process(new_pdf_list) if __name__ == '__main__': pdf_path = r"C:\Users\小胖\Desktop\abc.pdf" # pdf_path = "D:\\python\\test\\test3\\