最全總結(jié) | 聊聊 Python 辦公自動化之 Word（下）

from?docx.oxml.xmlchemy?import?BaseOxmlElement,?ZeroOrOne,?ZeroOrMore,?OxmlElement
from?docx.enum.text?import?WD_PARAGRAPH_ALIGNMENT
from?docx.oxml?import?ns

def?create_element(self,?name):
????return?OxmlElement(name)

def?create_attribute(self,?element,?name,?value):
????element.set(ns.qn(name),?value)

def?add_page_number(self,?run):
????"""
????添加頁面索引
????:param?run:
????:return:
????"""
????fldChar1?=?self.create_element('w:fldChar')
????self.create_attribute(fldChar1,?'w:fldCharType',?'begin')

????instrText?=?self.create_element('w:instrText')
????self.create_attribute(instrText,?'xml:space',?'preserve')
????instrText.text?=?"PAGE"

????fldChar2?=?self.create_element('w:fldChar')
????self.create_attribute(fldChar2,?'w:fldCharType',?'end')

????# run._r：class 'docx.oxml.text.run.CT_R'>
????run._r.append(fldChar1)
????run._r.append(instrText)
????run._r.append(fldChar2)

#?注意：要設(shè)置頁眉頁腳的對齊方式，必須設(shè)置到段落上（文字塊不能添加對齊方式）
doc.sections[0].footer.paragraphs[0].alignment?=?WD_PARAGRAPH_ALIGNMENT.CENTER

#?創(chuàng)建一個文字塊樣式，指定字體名稱、大小、顏色
style?=?create_style(document=doc,?style_name="style",?style_type=2,?font_size=10,
?????????????????????font_color=[0x00,?0x00,?0x00],?font_name="黑體")
self.add_page_number(doc.sections[0].footer.paragraphs[0].add_run("",?style))
doc.save("./output.docx")
print('添加頁碼索引成功！')

from?win32com?import?client

def?doc_to_docx_in_win(path_raw,?path_output):
????"""
????doc轉(zhuǎn)為docx（win）
????:param?path_original:
????:param?path_final:
????:return:
????"""
????#?獲取文件的格式后綴
????file_suffix?=?os.path.splitext(path_raw)[1]
????if?file_suffix?==?".doc":
????????word?=?client.Dispatch('Word.Application')
????????#?源文件
????????doc?=?word.Documents.Open(path_raw)
????????#?生成的新文件
????????doc.SaveAs(path_output,?16)
????????doc.Close()
????????word.Quit()
????elif?file_suffix?==?".docx":
????????shutil.copy(path_raw,?path_output)

#?轉(zhuǎn)換格式
./soffice?--headless?--convert-to?docx?源文件.doc?--outdir?/output/path/

import?os

source?=?"./doc/"
dest?=?"./docx/"
g?=?os.walk(source)

#?遍歷文件夾
for?root,?dirs,?files?in?g:
????for?file?in?files:
????????#?源文件完整路徑
????????file_path_raw?=?os.path.join(root,?file)
????????print(file_path_raw)

????????os.system("soffice?--headless?--convert-to?docx?{}?--outdir?{}".format(file_path_raw,?dest))

#?分別獲取段落內(nèi)容
content1?=?''
content2?=?''
for?paragraph?in?file1.paragraphs:
????if?""?==?paragraph.text.strip():
????????continue
????content1?+=?paragraph.text?+?'\n'

for?paragraph?in?file2.paragraphs:
????if?""?==?paragraph.text.strip():
????????continue
????content2?+=?paragraph.text?+?'\n'

#?如果參數(shù) keepends 為 False，不包含換行符，如果為 True，則保留換行符。
print("第二個文檔數(shù)據(jù)如下：\n",?content1.splitlines(keepends=False))
print("第一個文檔數(shù)據(jù)如下：\n",?content1.splitlines(keepends=False))

import?codecs
from?difflib?import?HtmlDiff

#?差異內(nèi)容
diff_html?=?HtmlDiff(wrapcolumn=100).make_file(content1.split("\n"),?content2.split("\n"))

#?寫入到文件中
with?codecs.open('./diff_result.html',?'w',?encoding='utf-8')?as?f:
?????f.write(diff_html)

doc?=?Document(file)

#?關(guān)鍵字的文字塊或單元格標紅，并加粗
#?1、修改段落中包含關(guān)鍵字的文件塊的樣式
for?paragraph?in?doc.paragraphs:
????for?run?in?paragraph.runs:
????????if?keyword?in?run.text:
????????????#?修改顏色為紅色，并加粗顯示
????????????run.font.bold?=?True
????????????run.font.color.rgb?=?RGBColor(255,?0,?0)

tables?=?[table?for?table?in?doc.tables]
for?table?in?tables:
????for?row?in?table.rows:
????????for?cell?in?row.cells:
????????????if?keyword?in?cell.text:
????????????????#?原內(nèi)容
????????????????content_raw?=?cell.text
????????????????#?清空單元格數(shù)據(jù)
????????????????cell.text?=?""
????????????????#?追加數(shù)據(jù)進去，并設(shè)置樣式
????????????????run?=?cell.paragraphs[0].add_run(content_raw)
????????????????run.font.color.rgb?=?RGBColor(255,?0,?0)
????????????????run.font.bold?=?True?

def?replace_content(self,?old_content,?new_content):
????"""
????替換文檔中所有內(nèi)容
????:param?old_content:舊的內(nèi)容
????:param?new_content:新的內(nèi)容
????:return:
????"""
????#?替換段落
????for?paragraph?in?self.doc.paragraphs:
????????if?old_content?in?paragraph.text:
????????????#?替換內(nèi)容后，重新設(shè)置進去
????????????paragraph.text?=?paragraph.text.replace(old_content,?new_content)

????#?替換表格
????# document.tables[表格索引].rows[行索引].cells[單元格列索引].text =?“新的數(shù)據(jù)”。
????tables?=?[table?for?table?in?self.doc.tables]
????for?table?in?tables:
????????for?row?in?table.rows:
????????????for?cell?in?row.cells:
????????????????if?old_content?in?cell.text:
????????????????????#?重新設(shè)置單元格內(nèi)容
????????????????????cell.text?=?cell.text.replace(old_content,?new_content)

????#?保存到一個新的文件中
????self.doc.save('./new.docx')