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 printMeta(filename):
f = PdfFileReader(open(filename, "rb"))
info = f.getDocumentInfo()
print("[*] PDF Metadata for:" + filename)
for item in info:
print("[+]", item, ":", info[item])
