def cleanAllInPath(self, srcDir):
if os.path.exists(srcDir) and os.path.isdir(srcDir):
files = os.listdir(srcDir)
num = len(files)
if num > 0:
for i, f in enumerate(files):
print '%d/%d: %s' % (i, num, f)
fileName = self.getCleanedFileName(f)
srcPath = os.path.join(srcDir, f)
destPath = os.path.join(srcDir, fileName)
if (os.path.isfile(srcPath)):
if self.isCleanedFile(srcPath):
print 'skip [%s]' % srcPath
elif self.hasCleaned(srcPath):
print 'skip [%s]' % srcPath
else:
try:
DuoPdf.cleanPdf(srcPath, destPath)
# print '%s -> ' % srcPath
# print destPath
except:
Log.w(DuoPdf.__name__, 'clean [%s] failed' % (srcPath))
traceback.print_exc()
else:
Log.i(DuoPdf.__name__, 'skip file [%s]' % (srcPath,))
else:
Log.w(DuoPdf.__name__, 'no file in [%s] to clean' % (srcDir))
else:
Log.w(DuoPdf.__name__, 'dir [%s] not exist.' % (srcDir,))
def find_links(self, url, response):
'''Parse the photos news default page and find photos news page urls'''
Log.i(self.TAG, 'find links in %s' % url)
links = ImgPageLinks(response, self.strStart, self.strEnd)
urls = links.getLinks(response)
# urls = links.persistToDB(self.db)
self.spider.add_urls(urls)
def renameAll(self):
path = os.path.join(os.path.curdir, 'books', 'new')
for item in os.listdir(path):
bid, extname = os.path.splitext(item)
title = self.persist.getTitle(bid)
if title:
newName = '%s%s' % (title, extname)
os.rename(os.path.join(path, item), os.path.join(path, newName))
Log.i(self.TAG, '%s -> %s' % (item, newName))
def renameAll(self):
path = os.path.join(os.path.curdir, 'books', 'new')
for item in os.listdir(path):
bid, extname = os.path.splitext(item)
title = self.persist.getTitle(bid)
if title:
newName = '%s%s' % (title, extname)
os.rename(os.path.join(path, item),
os.path.join(path, newName))
Log.i(self.TAG, '%s -> %s' % (item, newName))
def merge(dest, srcDir):
'''merge pdf files in srcDir'''
if os.path.exists(srcDir) and os.path.isdir(srcDir):
files = os.listdir(srcDir)
if len(files) > 0:
merger = PdfFileMerger()
for i,f in enumerate(files):
Log.i(DuoPdf.__name__, 'merge file [%s]' % (f, ))
filePath = os.path.join(srcDir, f)
if (os.path.isfile(filePath)):
try:
srcFileHdl = open(filePath, 'rb')
merger.merge(position=i, fileobj=srcFileHdl)
except:
Log.w(DuoPdf.__name__, 'merge [%s] failed' % (filePath))
traceback.print_exc()
else:
Log.i(DuoPdf.__name__, 'skip file [%s]' % (filePath,))
Log.i(DuoPdf.__name__, 'save to file [%s]...' % (dest, ))
destFileStream = file(dest, 'wb')
merger.write(destFileStream)
destFileStream.close()
Log.i(DuoPdf.__name__, 'done')
else:
Log.w(DuoPdf.__name__, 'no file in [%s] to merge' % (srcDir))
else:
Log.w(DuoPdf.__name__, 'dir [%s] not exist.' % (srcDir,))
def clean(srcDir):
if os.path.exists(srcDir) and os.path.isdir(srcDir):
files = os.listdir(srcDir)
if len(files) > 0:
for i,f in enumerate(files):
filePath = os.path.join(srcDir, f)
if (os.path.isfile(filePath)):
try:
DuoPdf.cleanPdf(filePath, filePath)
except:
Log.w(DuoPdf.__name__, 'clean [%s] failed' % (filePath))
traceback.print_exc()
else:
Log.i(DuoPdf.__name__, 'skip file [%s]' % (filePath,))
else:
Log.w(DuoPdf.__name__, 'no file in [%s] to clean' % (srcDir))
else:
Log.w(DuoPdf.__name__, 'dir [%s] not exist.' % (srcDir,))
def crop2(dest, src, margin1, margin2):
Log.i(DuoPdf.__name__, 'cropping file [%s]' % (src, ))
srcFile = file(src, 'rb')
srcPdf = PdfFileReader(srcFile)
destPdf = PdfFileWriter()
index = 1
for page in srcPdf.pages:
box = page.mediaBox
if index != 1:
if index % 2 == 1: #odd
margin = margin1
else: #even
margin = margin2
# print '%d %d %d %d' % (box.getLowerLeft_x(), box.getLowerLeft_y(), box.getUpperRight_x(), box.getUpperRight_y())
box.upperRight = (box.getUpperRight_x() - margin[2], box.getUpperRight_y() - margin[3])
box.lowerLeft = (box.getLowerLeft_x() + margin[0], box.getLowerLeft_y() + margin[1])
destPdf.addPage(page)
index += 1
Log.i(DuoPdf.__name__, 'saving to file [%s]...' % (dest, ))
destFile = file(dest, 'wb')
destPdf.write(destFile)
destFile.close()
srcFile.close()
Log.i(DuoPdf.__name__, 'done')
def onStop(self, event):
Log.i(self.TAG, 'phantomjs finished...')
self.persist.setDownload(self.id)
Duokan.merge(self.id)
Log.i(self.TAG, 'merged pdf...')
Duokan.crop(self.id)
Log.i(self.TAG, 'croped pdf...')
self.dispatch(Downloader.EVT_STOP)
def onStop(self, event):
Log.i(self.TAG, 'phantomjs finished...')
self.persist.setDownload(self.id)
Duokan.merge(self.id)
Log.i(self.TAG, 'merged pdf...')
Duokan.crop(self.id)
Log.i(self.TAG, 'croped pdf...')
self.dispatch(Downloader.EVT_STOP)
def cropWH(dest, src, destWidth, destHeight):
Log.i(DuoPdf.__name__, 'cropping file [%s]' % (src, ))
srcFile = file(src, 'rb')
srcPdf = PdfFileReader(srcFile)
destPdf = PdfFileWriter()
for page in srcPdf.pages:
box = page.mediaBox
width = box.getUpperRight_x() - box.getUpperRight_x()
height = box.getUpperRight_y() - box.getLowerLeft_y()
box.upperRight = (destWidth, box.getUpperRight_y() - (height - destHeight) / 2)
box.lowerLeft = (0, (height - destHeight) / 2)
destPdf.addPage(page)
Log.i(DuoPdf.__name__, 'saving to file [%s]...' % (dest, ))
destFile = file(dest, 'wb')
destPdf.write(destFile)
destFile.close()
srcFile.close()
Log.i(DuoPdf.__name__, 'done')
def crop(dest, src, left, top, bottom, right):
Log.i(DuoPdf.__name__, 'cropping file [%s]' % (src, ))
margin = (left, top, bottom, right)
srcFile = file(src, 'rb')
srcPdf = PdfFileReader(srcFile)
destPdf = PdfFileWriter()
for page in srcPdf.pages:
box = page.mediaBox
# print '%d %d %d %d' % (box.getLowerLeft_x(), box.getLowerLeft_y(), box.getUpperRight_x(), box.getUpperRight_y())
box.upperRight = (box.getUpperRight_x() - margin[2], box.getUpperRight_y() - margin[3])
box.lowerLeft = (box.getLowerLeft_x() + margin[0], box.getLowerLeft_y() + margin[1])
destPdf.addPage(page)
Log.i(DuoPdf.__name__, 'saving to file [%s]...' % (dest, ))
destFile = file(dest, 'wb')
destPdf.write(destFile)
destFile.close()
srcFile.close()
Log.i(DuoPdf.__name__, 'done')
