word_parse_of_eng/get_word_content/word2html.py

import glob
import os
import shutil

import requests
from pypinyin import lazy_pinyin


def to_pinyin_camel(s):
    py_ls = lazy_pinyin(s)
    py_camel = [py.capitalize() for py in py_ls]
    return "".join(py_camel)


def demo1():
    for i, file_path in enumerate(glob.glob("topic_type_word/topic_type_word_zh/*.docx") +
                                          glob.glob("topic_type_word/topic_type_word_zh/*.doc")):
        file_dir, file_name = os.path.split(file_path)
        base_name, ext = os.path.splitext(file_name)
        new_dir = "topic_type_word/topic_type_word_en/" + to_pinyin_camel(base_name)
        if not os.path.isdir(new_dir):
            os.mkdir(new_dir)

        new_file = os.path.join(new_dir, to_pinyin_camel(base_name) + ext)
        shutil.copy(file_path, new_file)
        new_file = os.path.abspath(new_file)
        requests.get(r"http://localhost:9001/word/?name={}".format(new_file))


def call_c_shape(doc_file, timeout=30):
    r = requests.get(r"http://localhost:9001/word/?name={}".format(doc_file), timeout=timeout)
    return r


def start_word2html_app(kill_mathtype=True):
    if kill_mathtype:
        os.system("taskkill /f /im MathType.exe")
        os.system("taskkill /f /im WINWORD.EXE")
        os.system("taskkill /f /im ConsoleApplication1.exe")
    os.system(
        r"start C:\Users\HJ\Desktop\code\extract_math_test\extract_math_test_online\word_bin\ConsoleApplication1.exe")  # start 在新窗口中打开


def get_call_c_shape_response(doc_file):
    r = None
    for _ in range(2):
        try:
            r = call_c_shape(doc_file)
        except:
            pass
        if r is not None:
            break
        else:
            start_word2html_app()
    return r


def get_call_c_shape_text(doc_file):
    r = get_call_c_shape_response(doc_file)
    clean_html_file = "_clean".join([os.path.splitext(doc_file)[0], ".html"])
    if r.text == "4" or not os.path.isfile(clean_html_file):
        raise ValueError("can not parse {}".format(doc_file))
    else:
        html = ''
        if os.path.exists(clean_html_file):
            with open(clean_html_file, "r", encoding="utf-8") as f:
                html = f.read()
        return html


def word2html(src_filename):
    filename = os.path.abspath(src_filename)
    filepath, filename = os.path.split(filename)
    filename = to_pinyin_camel(filename)
    des_filename = os.path.join(filepath, filename)
    shutil.copy(src_filename, des_filename)
    html = get_call_c_shape_text(des_filename)
    return html


if __name__ == "__main__":
    print(word2html("../upload/哈哈.doc"))