1,目的
通過(guò)萬(wàn)能的Python把一個(gè)目錄下的所有Word文件轉(zhuǎn)換為PDF文件。
Word to PDF .jpg
2,遍歷目錄
作者總結(jié)了三種遍歷目錄的方法,分別如下。
2.1,調(diào)用glob
遍歷指定目錄下的所有文件和文件夾,不遞歸遍歷,需要手動(dòng)完成遞歸遍歷功能。
import glob as gb
path = gb.glob('d:\\2\\*')
for path in path:
print path
2.2,調(diào)用os.walk
遍歷指定目錄下的所有文件和文件夾,遞歸遍歷,功能強(qiáng)大,推薦使用。
import os
for dirpath, dirnames, filenames in os.walk('d:\\2\\'):
for file in filenames:
fullpath = os.path.join(dirpath, file)
print fullpath, file
2.3,自己DIY
遍歷指定目錄下的所有文件和文件夾,遞歸遍歷,自主編寫(xiě),擴(kuò)展性強(qiáng),可以學(xué)習(xí)練手。
import os;
files = list();
def DirAll(pathName):
if os.path.exists(pathName):
fileList = os.listdir(pathName);
for f in fileList:
if f=="$RECYCLE.BIN" or f=="System Volume Information":
continue;
f=os.path.join(pathName,f);
if os.path.isdir(f):
DirAll(f);
else:
dirName=os.path.dirname(f);
baseName=os.path.basename(f);
if dirName.endswith(os.sep):
files.append(dirName+baseName);
else:
files.append(dirName+os.sep+baseName);
DirAll("D:\\2\\");
for f in files:
print f
# print f.decode('gbk').encode('utf-8');
2.4,備注
注意,如果遍歷過(guò)程中,出現(xiàn)文件名稱或文件路徑亂碼問(wèn)題,可以查看本文的參考資料來(lái)解決。
3,轉(zhuǎn)換Word文件為PDF
通過(guò)Windows Com組件(win32com),調(diào)用Word服務(wù)(Word.Application),實(shí)現(xiàn)Word到PDF文件的轉(zhuǎn)換。因此,要求該P(yáng)ython程序需要在有Word服務(wù)(可能至少要求2007版本)的Windows機(jī)器上運(yùn)行。
#coding:utf8
import os, sys
reload(sys)
sys.setdefaultencoding('utf8')
from win32com.client import Dispatch, constants, gencache
input = 'D:\\2\\test\\11.docx'
output = 'D:\\2\\test\\22.pdf'
print 'input file', input
print 'output file', output
# enable python COM support for Word 2007
# this is generated by: makepy.py -i "Microsoft Word 12.0 Object Library"
gencache.EnsureModule('{00020905-0000-0000-C000-000000000046}', 0, 8, 4)
# 開(kāi)始轉(zhuǎn)換
w = Dispatch("Word.Application")
try:
doc = w.Documents.Open(input, ReadOnly=1)
doc.ExportAsFixedFormat(output, constants.wdExportFormatPDF, \
Item=constants.wdExportDocumentWithMarkup,
CreateBookmarks=constants.wdExportCreateHeadingBookmarks)
except:
print ' exception'
finally:
w.Quit(constants.wdDoNotSaveChanges)
if os.path.isfile(output):
print 'translate success'
else:
print 'translate fail'
4,批量轉(zhuǎn)換
要實(shí)現(xiàn)批量準(zhǔn)換,將第2步和第3步的功能組合在一起即可,直接上代碼。
# -*- coding:utf-8 -*-
# doc2pdf.py: python script to convert doc to pdf with bookmarks!
# Requires Office 2007 SP2
# Requires python for win32 extension
import glob as gb
import sys
reload(sys)
sys.setdefaultencoding('utf8')
'''
參考:http://blog.csdn.net/rumswell/article/details/7434302
'''
import sys, os
from win32com.client import Dispatch, constants, gencache
# from config import REPORT_DOC_PATH,REPORT_PDF_PATH
REPORT_DOC_PATH = 'D:/2/doc/'
REPORT_PDF_PATH = 'D:/2/doc/'
# Word轉(zhuǎn)換為PDF
def word2pdf(filename):
input = filename + '.docx'
output = filename + '.pdf'
pdf_name = output
# 判斷文件是否存在
os.chdir(REPORT_DOC_PATH)
if not os.path.isfile(input):
print u'%s not exist' % input
return False
# 文檔路徑需要為絕對(duì)路徑,因?yàn)閃ord啟動(dòng)后當(dāng)前路徑不是調(diào)用腳本時(shí)的當(dāng)前路徑。
if (not os.path.isabs(input)): # 判斷是否為絕對(duì)路徑
# os.chdir(REPORT_DOC_PATH)
input = os.path.abspath(input) # 返回絕對(duì)路徑
else:
print u'%s not absolute path' % input
return False
if (not os.path.isabs(output)):
os.chdir(REPORT_PDF_PATH)
output = os.path.abspath(output)
else:
print u'%s not absolute path' % output
return False
try:
print input, output
# enable python COM support for Word 2007
# this is generated by: makepy.py -i "Microsoft Word 12.0 Object Library"
gencache.EnsureModule('{00020905-0000-0000-C000-000000000046}', 0, 8, 4)
# 開(kāi)始轉(zhuǎn)換
w = Dispatch("Word.Application")
try:
doc = w.Documents.Open(input, ReadOnly=1)
doc.ExportAsFixedFormat(output, constants.wdExportFormatPDF, \
Item=constants.wdExportDocumentWithMarkup,
CreateBookmarks=constants.wdExportCreateHeadingBookmarks)
except:
print ' exception'
finally:
w.Quit(constants.wdDoNotSaveChanges)
if os.path.isfile(pdf_name):
print 'translate success'
return True
else:
print 'translate fail'
return False
except:
print ' exception'
return -1
if __name__ == '__main__':
# img_path = gb.glob(REPORT_DOC_PATH + "*")
# for path in img_path:
# print path
# rc = word2pdf(path)
# rc = word2pdf('1')
# print rc,
# if rc:
# sys.exit(rc)
# sys.exit(0)
import os
for dirpath, dirnames, filenames in os.walk(REPORT_DOC_PATH):
for file in filenames:
fullpath = os.path.join(dirpath, file)
print fullpath, file
rc = word2pdf(file.rstrip('.docx'))
5,參考資料
- 利用Python將word 2007的文檔轉(zhuǎn)為pdf文件
http://blog.csdn.net/rumswell/article/details/7434302 - Python 將word文件轉(zhuǎn)換為PDF文件
http://blog.csdn.net/lis_12/article/details/54603298 - 遍歷某目錄下的所有文件夾與文件的路徑、輸出中文亂碼問(wèn)題
http://blog.csdn.net/yongh701/article/details/46907383