python-docx的简单使用示例教程
import docx #pip install python-docx
import re
import json
import requests
import time
import hashlib
from urllib.parse import urlencode
import random
import copy
#字典形式
帮助文件解析结果={"NAME":"","SYNOPSIS":"","DESCRIPTION":"","PARAMETERS":{},"Example":{}};
翻译结果={"NAME":"","SYNOPSIS":"","DESCRIPTION":"","PARAMETERS":{},"Example":{}};
'''
'''
def 解析PowerShell命令的帮助文本(文件路径:str):
with open(文件路径,mode='r',encoding='utf-8') as fd_help:
line = fd_help.readline();
while line:
if(line.strip() == "NAME"):
line = fd_help.readline()
line = line.strip()
帮助文件解析结果['NAME'] = line
elif(line.strip() == "SYNOPSIS"):
line = fd_help.readline()
while line[0:4]==" ":
帮助文件解析结果['SYNOPSIS'] += line.lstrip()
line = fd_help.readline()
elif(line.strip() == "DESCRIPTION"):
line = fd_help.readline()
while line[0:4]==" ":
帮助文件解析结果['DESCRIPTION'] += line.lstrip()
line = fd_help.readline()
elif(line.strip() == "PARAMETERS"):
line = fd_help.readline()
while line[0:4]==" ":
参数名 = line.lstrip()
帮助文件解析结果['PARAMETERS'][参数名] = ""
line = fd_help.readline()
while line[0:8]==" ":
帮助文件解析结果['PARAMETERS'][参数名] += line.lstrip()
line = fd_help.readline()
if(len(re.findall(r'^s*-*s*Example',line))):
break
elif(len(re.findall(r'^s*-*s*Example',line))):
temp=re.sub(r"^s*-*s*([w,.: ]+) *-*",r"1",line)
temp.rstrip()
帮助文件解析结果["Example"][temp]="";
line = fd_help.readline()
while line:
if(len(re.findall(r'^s*-*s*Example',line))):
temp=re.sub(r"^s*-*s*([w,.: ]+) *-*",r"1",line)
temp.rstrip()
帮助文件解析结果["Example"][temp]="";
line = fd_help.readline()
while not (len(re.findall(r'^s*-*s*Example',line))) and line:
帮助文件解析结果["Example"][temp]+=line.lstrip()
line = fd_help.readline()
else:
line = fd_help.readline()
#检查key=""的情况，并删除这样的key
if("" in 帮助文件解析结果):
del 帮助文件解析结果[""]
if("" in 帮助文件解析结果["PARAMETERS"]):
del 帮助文件解析结果["PARAMETERS"][""]
if("" in 帮助文件解析结果["Example"]):
del 帮助文件解析结果["Example"][""]
# 本文件是通过请求有道翻译，去获取翻译结果
'''
i: 你好
from: AUTO
to: AUTO
smartresult: dict
client: fanyideskweb
salt: 16643765479061 //毫秒级别的时间戳后面加上个0-9之间的随机数,js代码：r + parseInt(10 * Math.random(), 10);这里的r表示时间戳字符串
sign: 1d69ce8f7c6258243e573e31e29e0012 //签名，下面找到了
lts: 1664376547906 //毫秒级别的时间戳
bv: 42c8b36dd7d61c619e7b1dc11e44d870 //同设备相同，使用md5加密的（方法是：md5(User-Agent)==>md5（"5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36 Edg/105.0.1343.53"）
doctype: json
version: 2.1
keyfrom: fanyi.web
action: FY_BY_REALTlME
/*
解密出来了：sign的计算如下
define("newweb/common/service", ["http://www.jb51.net/article/utils", "http://www.jb51.net/article/md5", "http://www.jb51.net/article/jquery-1.7"], function(e, t) {
var n = e("http://www.jb51.net/article/jquery-1.7");
e("http://www.jb51.net/article/utils");
e("http://www.jb51.net/article/md5");
var r = function(e) {
var t = n.md5(navigator.appVersion)
, r = "" + (new Date).getTime()
, i = r + parseInt(10 * Math.random(), 10);
return {
ts: r,
bv: t,
salt: i,
sign: n.md5("fanyideskweb" + e + i + "Ygy_4c=r#e#4EX^NUGUc5") //在这里，e是要翻译的内容，i是毫秒级别的时间戳后面加上个0-9之间的随机数；后面这串字符串估计是服务器那边随机生成的，应该会变化。每次抓取的时候，可以查看下js代码
}
};
总体来说，data数据由函数“generateSaltSign”计算出来
*/
'''
'''
获取翻译结果
The_translated_string：被翻译的字符串
由于翻译是以行为单位，所以一行一个结果，函数将解析The_translated_string参数，并以字符串形式返回所有翻译结果
'''
def youdao_translate(The_translated_string:str):
if(The_translated_string == ""):
return {"":""}
url = r'https://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule'
User_Agent = "5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36 Edg/106.0.1370.37"
header = {
"Accept": "application/json, text/javascript, */*; q=0.01",
"Accept-Encoding": "gzip, deflate, br",
"Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6",
"Connection": "keep-alive",
#"Content-Length": "307",
"Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
"Cookie":"OUTFOX_SEARCH_USER_ID=1135160796@10.108.162.134; OUTFOX_SEARCH_USER_ID_NCOO=775555146.507473; JSESSIONID=aaaQ2GYK5N-ozb24rKNcy; SESSION_FROM_COOKIE=unknown; DICT_UGC=be3af0da19b5c5e6aa4e17bd8d90b28a|; JSESSIONID=abcPzon0RcZqc7GltuAgy; ___rl__test__cookies=1665366515354",
"Host": "fanyi.youdao.com",
"Origin": "https://fanyi.youdao.com",
"Referer": "https://fanyi.youdao.com/",
"sec-ch-ua": """"Google Chrome";v="105", "Not)A;Brand";v="8", "Chromium";v="105""""",
"sec-ch-ua-mobile": "?0",
"sec-ch-ua-platform": "Windows",
"Sec-Fetch-Dest": "empty",
"Sec-Fetch-Mode": "cors",
"Sec-Fetch-Site": "same-origin",
"User-Agent": User_Agent,
"X-Requested-With": "XMLHttpRequest"
}
#The_translated_string=input("输入你要翻译的中文信息：
") # 被翻译的字符串
timestamp = str(round(time.time()*1000)) # 毫秒级别的时间戳
salt = timestamp + str(random.randint(0, 9)) # 毫秒级别的时间戳后面加上个0-9之间的随机数
sign_str = "fanyideskweb" + The_translated_string + salt + "Ygy_4c=r#e#4EX^NUGUc5" # 构造签名字符串
# 签名，算法：sign: n.md5("fanyideskweb" + e + i + "Ygy_4c=r#e#4EX^NUGUc5") //在这里，后面这串字符串估计是服务器那边随机生成的，应该会变化。每次抓取的时候，可以查看下js代码
sign = hashlib.md5(str.encode(sign_str)).hexdigest()
# 同设备相同，使用md5加密的（方法是：md5(User-Agent)==>md5（"5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36 Edg/105.0.1343.53"）
bv = hashlib.md5(str.encode(User_Agent)).hexdigest()
cookies = {
"OUTFOX_SEARCH_USER_ID": "1135160796@10.108.162.134",
"OUTFOX_SEARCH_USER_ID_NCOO": "775555146.507473",
"JSESSIONID": "aaaQ2GYK5N-ozb24rKNcy",
"SESSION_FROM_COOKIE": "unknown",
"DICT_UGC": "be3af0da19b5c5e6aa4e17bd8d90b28a|",
"JSESSIONID": "abcPzon0RcZqc7GltuAgy",
"___rl__test__cookies": "1665366515354"
}
data = {
"i": The_translated_string,
"from": "AUTO",
"to": "AUTO",
# 一般来说，是从中文翻译为英文
# "from": "zh-CHS",
# "to": "en",
"smartresult": "dict",
"client": "fanyideskweb",
"salt": salt,
"sign": sign,
"lts": timestamp,
"bv": bv,
"doctype": "json",
"version": "2.1",
"keyfrom": "fanyi.web",
"action": "FY_BY_CLICKBUTTION"
}
data = urlencode(data);
result = requests.post(url, data=data, cookies=cookies,headers=header)
json_result = json.loads(result.text);
#lines = The_translated_string.splitlines(); #按照行边界拆分
if(not json_result["errorCode"]):
ret_list="";
for i in json_result["translateResult"]: #如果源字符串就是存在段落的，则这里就会根据其来分结果
for j in i: #翻译服务器认为该分段的，这里就会再次存在子项
ret_list+=j['tgt']
ret_list+="
"
#ret_list[json_result["translateResult"][i][0]["src"]]=json_result["translateResult"][i][0]["tgt"]
return ret_list;
else:
return "errorCode = "+str(json_result["errorCode"]);
#示例
'''
str_ = "你好
世界
我来了
哈哈"
print(youdao_translate(str_))
-----out-----
{'你好': 'hello', '世界': 'The world', '我来了': "I'm coming", '哈哈': 'Ha ha'}
'''
'''
将变量“帮助文件解析结果”中的value翻译成中文
'''
def 执行翻译():
翻译结果 = copy.deepcopy(帮助文件解析结果) #这里执行了深拷贝了，所以它不再是外面的那个“翻译结果”变量了
翻译结果["SYNOPSIS"] = youdao_translate(翻译结果["SYNOPSIS"])
翻译结果["DESCRIPTION"] = youdao_translate(翻译结果["DESCRIPTION"])
for key,value in 翻译结果["PARAMETERS"].items():
if(value == ""):
continue
翻译结果["PARAMETERS"][key] = youdao_translate(value)
for key,value in 翻译结果["Example"].items():
if(value == ""):
continue
翻译结果["Example"][key] = youdao_translate(value)
temp_dict = {}
for key,value in 翻译结果["Example"].items():
if(key == ""):
continue
temp_dict[youdao_translate(key)] = value
翻译结果["Example"] = temp_dict
return 翻译结果
'''
设置表格所有单元格的四个边为0.5磅，黑色，实线
可以使用返回值，也可以不使用
'''
def 设置表格网格线为黑色实线(table_object:object):
kwargs = {
"top":{"sz": 4, "val": "single", "color": "#000000"},
"bottom":{"sz": 4, "val": "single", "color": "#000000"},
"left":{"sz": 4, "val": "single", "color": "#000000"},
"right":{"sz": 4, "val": "single", "color": "#000000"},
"insideV":{"sz": 4, "val": "single", "color": "#000000"},
"insideH":{"sz": 4, "val": "single", "color": "#000000"}
}
borders = docx.oxml.OxmlElement('w:tblBorders')
for tag in ('bottom', 'top', 'left', 'right', 'insideV', 'insideH'):
edge_data = kwargs.get(tag)
if edge_data:
any_border = docx.oxml.OxmlElement(f'w:{tag}')
for key in ["sz", "val", "color", "space", "shadow"]:
if key in edge_data:
any_border.set(docx.oxml.ns.qn(f'w:{key}'), str(edge_data[key]))
borders.append(any_border)
table_object._tbl.tblPr.append(borders)
return table_object
'''
设置标题样式
'''
def 设置标题样式为黑色宋体(heading_object:object):
heading_object.alignment = docx.enum.text.WD_ALIGN_PARAGRAPH.LEFT #左对齐
for run in heading_object.runs:
run.font.name=u'宋体' #设置为宋体
#run._element.rPr.rFonts.set(qn('w:eastAsia'), u'宋体')#设置为宋体，和上边的一起使用
run.font.color.rgb = docx.shared.RGBColor(0,0,0)#设置颜色为黑色
return heading_object
'''
创建docx文档，将翻译结果和原文写入文档中
'''
def word():
my_word_doc = docx.Document() #打开一个空白文档
# for style in my_word_doc.styles:
# print(style)
heading = my_word_doc.add_heading(翻译结果["NAME"],level=2) #指定样式标题2
设置标题样式为黑色宋体(heading)
heading = my_word_doc.add_heading("描述",level=3) #指定样式标题3
设置标题样式为黑色宋体(heading)
for line in 翻译结果["SYNOPSIS"].split("
"):
my_word_doc.add_paragraph(line)
for line in 翻译结果["DESCRIPTION"].split("
"):
my_word_doc.add_paragraph(line)
heading = my_word_doc.add_heading("参数",level=3) #指定样式标题3
设置标题样式为黑色宋体(heading)
#table = my_word_doc.add_table(rows=len(翻译结果["PARAMETERS"]), cols=3) #指定样式标题3；在末尾添加一个表
table = my_word_doc.add_table(rows=len(翻译结果["PARAMETERS"]), cols=2) #指定样式标题3；在末尾添加一个表
#table.style = my_word_doc.styles['Medium Grid 1']
设置表格网格线为黑色实线(table)
index=0
for key,value in 翻译结果["PARAMETERS"].items():
for line in key.split("
"):
cell = table.cell(index,0)
cell.text += line
for line in value.split("
"):
table.cell(index,1).text += line
#table.cell(index,1).text = 帮助文件解析结果["PARAMETERS"][key]
cell_paragraphs = table.cell(index,0).paragraphs
for i in cell_paragraphs:
i.alignment = docx.enum.text.WD_PARAGRAPH_ALIGNMENT.LEFT #左对齐
cell_paragraphs = table.cell(index,1).paragraphs
for i in cell_paragraphs:
i.alignment = docx.enum.text.WD_PARAGRAPH_ALIGNMENT.LEFT #左对齐
# table.cell(index,2).text = value
# cell_paragraphs = table.cell(index,2).paragraphs
# for i in cell_paragraphs:
# i.alignment = docx.enum.text.WD_PARAGRAPH_ALIGNMENT.LEFT #左对齐
index += 1
heading = my_word_doc.add_heading("示例",level=3) #指定样式标题3
设置标题样式为黑色宋体(heading)
for key,value in 翻译结果["Example"].items():
heading = my_word_doc.add_heading(key[0:-1],level=4) #指定样式标题4
设置标题样式为黑色宋体(heading)
for line in value.split("
"):
my_word_doc.add_paragraph(line)
my_word_doc.save(r"C:UsersxxxDownloads emp.docx")
解析PowerShell命令的帮助文本(r"C:UsersxxxDownloadsGet-CimClass.txt")
#有道翻译的新版翻译结果解析实在是太变态了，我搞不了，是在不行就把格式弄好，使用文档翻译翻译吧。
#翻译结果 = 执行翻译()
翻译结果=帮助文件解析结果
word()