def get(self):
url = self.request.get('url')
if not url:
url = ""
page = self.request.get('pg')
if not page:
page = 'all'
else:
page = int(page)-1
u = urllib2.urlopen(urllib2.unquote(url))
output = StringIO.StringIO()
output.write(u.read())
p = PdfFileReader(output)
pages = p.getNumPages()
title = p.getDocumentInfo().title
if page == "all":
content=""
for i in range(0, pages):
# Extract text from page and add to content
content += "<page number='%d'><![CDATA[%s]]></page>\n" % (i+1, p.getPage(i).extractText())
else:
content = "<page number='%d'><![CDATA[%s]]></page>\n" % (page+1, p.getPage(page).extractText())
output.close()
result = "<?xml version='1.0' encoding='UTF-8'?>\n<document url='%s' title='%s'>%s</document>" % (url, title, content)
self.response.headers['Content-type'] = 'application/xml'
self.response.out.write(result)
def parse(self, file_full, statdata): pdf = PdfFileReader(file(file_full, 'rb')) pages = pdf.getNumPages() text = '' self._extra['pages'] = pages for pagenr in range(pages): page = pdf.getPage(pagenr-1) text += ' ' + page.extractText() return text
def mergePdf(self):
# self.threadPdfWritingStatus.emit(
# '<font size=4><b>Method "%s": </b></font><b>Setting Title for</b> %s<b>. Please Wait...</b><br />' % (
# self.groupType, self.url))
self.threadPdfWritingStatus.emit(
'<b>Setting Title for</b> %s<b>. Please Wait...</b><br />' % self.url)
packet = StringIO()
# create a new PDF with Reportlab
pdfCanvas = canvas.Canvas(packet, pagesize=A4)
pdfCanvas.setFont('Helvetica', 8)
if len(self.title) is 0:
self.title = str(self.url).split('/')[-1]
self.title = self.regex.getSearchedData('(?i)([a-zA-Z0-9-_ ]*?)\.[a-zA-Z0-9_]*$', self.title)
self.title = self.regex.replaceData('(?i)_', ' ', self.title)
title = unicode(self.title[:57] + '...') if (len(self.title) > 60) else unicode(self.title)
url = self.url[:57] + '...' if (len(self.title) > 60) else self.url
pdfCanvas.drawString(5, 830, title + ' ' + str(url).lower())
d = datetime.datetime.now()
strDate = str(d.strftime("%Y-%m-%d %H-%M-%S %p"))
pdfCanvas.drawString(420, 5, 'Created Date Time: ' + strDate)
pdfCanvas.save()
packet.seek(0)
newPdf = PdfFileReader(packet)
if not os.path.exists(self.tempPdfFile):
return self.printWebHtmlToPdf(self.url, self.filePath, self.fileName)
writer = PdfFileWriter()
tmpPdfFile = file(self.tempPdfFile, 'rb')
reader = PdfFileReader(tmpPdfFile)
for i in range(0, (reader.getNumPages())):
page = reader.getPage(i)
page.mergePage(newPdf.getPage(0))
# page = newPdf.getPage(0)
# page.mergePage(reader.getPage(i))
writer.addPage(page)
print 'Filename: ' + self.fileName
outputStream = file(self.filePath + self.fileName, "wb")
writer.write(outputStream)
outputStream.close()
tmpPdfFile.close()
os.remove(str(self.tempPdfFile))
def extractTextFromPdfStream(stream):
reader = PdfFileReader(stream)
return '\n'.join(
reader.getPage(i).extractText() for i in range(reader.getNumPages()))
def extract_text_from_pdf_stream(stream):
reader = PdfFileReader(stream)
return '\n'.join(
reader.getPage(i).extractText()
for i in range(reader.getNumPages())
)
