def ConvertImageToPDF(image_path, docx_path, dest_path, wordapp):
if os.path.exists(dest_path):
return
try:
doc = Document() #以默认模板建立文档对象
doc.add_picture(image_path, width=Inches(6), height=Inches(8))
except Exception as e:
if os.path.exists(docx_path):
os.remove(docx_path)
if os.path.exists(dest_path):
os.remove(dest_path)
print('Error:' + image_path, e)
return
doc.save(docx_path)
#wdFormatDocument = 0
#wdFormatDocument97 = 0
#wdFormatDocumentDefault = 16
#wdFormatDOSText = 4
#wdFormatDOSTextLineBreaks = 5
#wdFormatEncodedText = 7
#wdFormatFilteredHTML = 10
#wdFormatFlatXML = 19
#wdFormatFlatXMLMacroEnabled = 20
#wdFormatFlatXMLTemplate = 21
#wdFormatFlatXMLTemplateMacroEnabled = 22
#wdFormatHTML = 8
wdFormatPDF = 17
#wdFormatRTF = 6
#wdFormatTemplate = 1
#wdFormatTemplate97 = 1
#wdFormatText = 2
#wdFormatTextLineBreaks = 3
#wdFormatUnicodeText = 7
#wdFormatWebArchive = 9
#wdFormatXML = 11
#wdFormatXMLDocument = 12
#wdFormatXMLDocumentMacroEnabled = 13
#wdFormatXMLTemplate = 14
#wdFormatXMLTemplateMacroEnabled = 15
#wdFormatXPS = 18
#wordapp.Visible = True
#doc = wordapp.Documents.Add()
doc = wordapp.Documents.Open(docx_path)
# 插入文字
range = doc.Range(0, 0)
#range.InsertBefore('6b.jpg')
#doc.SaveAs('6b.docx')
#doc.SaveAs('6b.pdf', win32com.client.constants.wdFormatPDF)
doc.SaveAs(dest_path, wdFormatPDF)
print(dest_path)
doc.Close()
def get_text(file_name):
file_name = os.path.abspath(file_name)
_, actual_file_name = os.path.split(file_name)
if actual_file_name.startswith("~"):
return ""
print(file_name)
ext = get_file_ext(file_name)
if ext is None or ext in ["txt", "rst", "text", "adoc"]:
try:
with codecs.open(file_name, "r", "utf-8") as f:
return f.read()
except Exception:
print("File could not be read ", file_name)
traceback.print_exc()
elif ext == "rtf":
try:
with codecs.open(file_name, "r", "utf-8") as f:
return striprtf(f.read())
except Exception:
print("File could not be read ", file_name)
traceback.print_exc()
elif ext in ["pdf"]:
text = extract_text(file_name)
full_text = [text]
with open(file_name, 'rb') as f:
reader = PyPDF2.PdfFileReader(f)
for pageNumber in range(reader.numPages):
page = reader.getPage(pageNumber)
try:
txt = page.extractText()
full_text.append(txt)
except Exception:
print("Error PDF reader ", file_name, pageNumber)
traceback.print_exc()
return "\n".join(full_text)
elif ext in ["docx"]:
full_text = []
try:
doc = Document(file_name)
for para in doc.paragraphs:
full_text.append(para.text)
except Exception:
traceback.print_exc()
return '\n'.join(full_text)
elif ext in ["doc"]:
if os.name == 'nt':
import win32com.client
word = win32com.client.Dispatch("Word.Application")
word.visible = False
_ = word.Documents.Open(file_name)
doc = word.ActiveDocument
return doc.Range().Text
os.system(
"/Applications/LibreOffice.app/Contents/MacOS/soffice --headless --convert-to txt:Text "
+ file_name)
fileX = os.path.split(file_name)[1].split(".") + ".txt"
try:
with codecs.open(fileX, "r", "utf-8") as f:
return f.read()
except Exception:
print("File could not be read ", fileX)
traceback.print_exc()
else:
print("Unknown file extension", file_name)
return ""
