<?xml version='1.0' encoding='UTF-8'?><?xml-stylesheet href="http://www.blogger.com/styles/atom.css" type="text/css"?><feed xmlns='http://www.w3.org/2005/Atom' xmlns:openSearch='http://a9.com/-/spec/opensearchrss/1.0/'><id>tag:blogger.com,1999:blog-16840474.post8153824157621127866..comments</id><updated>2008-12-01T11:59:24.824-02:00</updated><title type='text'>Comments on Do not set yourself on fire ...: Extract PDF title from all files on a directory</title><link rel='http://schemas.google.com/g/2005#feed' type='application/atom+xml' href='http://blog.isnotworking.com/feeds/8153824157621127866/comments/default'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/16840474/8153824157621127866/comments/default'/><link rel='alternate' type='text/html' href='http://blog.isnotworking.com/2006/08/extract-pdf-title-from-all-files-on.html'/><author><name>Ricardo Niederberger Cabral</name><uri>http://www.blogger.com/profile/16520043212251579884</uri><email>noreply@blogger.com</email></author><generator version='7.00' uri='http://www.blogger.com'>Blogger</generator><openSearch:totalResults>11</openSearch:totalResults><openSearch:startIndex>1</openSearch:startIndex><openSearch:itemsPerPage>25</openSearch:itemsPerPage><entry><id>tag:blogger.com,1999:blog-16840474.post-700486088675799011</id><published>2008-12-01T11:59:00.000-02:00</published><updated>2008-12-01T11:59:00.000-02:00</updated><title type='text'>I modified the script a little bit to handle some ...</title><summary type='text'>I modified the script a little bit to handle some errors:&lt;BR/&gt;# -*- coding: cp1252 -*-&lt;BR/&gt;# modified script in order to rename files with titles&lt;BR/&gt;# pyPdf available at http://pybrary.net/pyPdf/&lt;BR/&gt;&lt;BR/&gt;from pyPdf import PdfFileWriter, PdfFileReader&lt;BR/&gt;import os&lt;BR/&gt;&lt;BR/&gt;trgtfilename = ""&lt;BR/&gt;&lt;BR/&gt;for fileName in os.listdir('.'):&lt;BR/&gt;        if fileName.lower()[-3:] != "pdf": continue&lt;BR/&gt;</summary><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/16840474/8153824157621127866/comments/default/700486088675799011'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/16840474/8153824157621127866/comments/default/700486088675799011'/><link rel='alternate' type='text/html' href='http://blog.isnotworking.com/2006/08/extract-pdf-title-from-all-files-on.html?showComment=1228139940000#c700486088675799011' title=''/><author><name>Anonymous</name><email>noreply@blogger.com</email></author><thr:in-reply-to xmlns:thr='http://purl.org/syndication/thread/1.0' href='http://blog.isnotworking.com/2006/08/extract-pdf-title-from-all-files-on.html' ref='tag:blogger.com,1999:blog-16840474.post-8153824157621127866' source='http://www.blogger.com/feeds/16840474/posts/default/8153824157621127866' type='text/html'/></entry><entry><id>tag:blogger.com,1999:blog-16840474.post-747756882151214730</id><published>2008-06-23T08:14:00.000-03:00</published><updated>2008-06-23T08:14:00.000-03:00</updated><title type='text'>from pyPdf import PdfFileWriter, PdfFileReaderimpo...</title><summary type='text'>from pyPdf import PdfFileWriter, PdfFileReader&lt;BR/&gt;import osfor fileName in os.listdir('.'):&lt;BR/&gt; try:        if fileName.lower()[-3:] != "pdf":&lt;BR/&gt;  continue        input1 = PdfFileReader(file(fileName, "rb"))           # print the title of document1.pdf&lt;BR/&gt; print '##1', fileName, '##2', input1.getDocumentInfo().title&lt;BR/&gt; except:        print '##1', fileName, '##2'&lt;BR/&gt; &lt;BR/&gt;&gt;&gt;&gt; from pyPdf </summary><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/16840474/8153824157621127866/comments/default/747756882151214730'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/16840474/8153824157621127866/comments/default/747756882151214730'/><link rel='alternate' type='text/html' href='http://blog.isnotworking.com/2006/08/extract-pdf-title-from-all-files-on.html?showComment=1214219640000#c747756882151214730' title=''/><author><name>SeaCat</name><uri>http://www.blogger.com/profile/14825527719712567256</uri><email>noreply@blogger.com</email></author><thr:in-reply-to xmlns:thr='http://purl.org/syndication/thread/1.0' href='http://blog.isnotworking.com/2006/08/extract-pdf-title-from-all-files-on.html' ref='tag:blogger.com,1999:blog-16840474.post-8153824157621127866' source='http://www.blogger.com/feeds/16840474/posts/default/8153824157621127866' type='text/html'/></entry><entry><id>tag:blogger.com,1999:blog-16840474.post-4113483675264243565</id><published>2008-06-23T08:11:00.000-03:00</published><updated>2008-06-23T08:11:00.000-03:00</updated><title type='text'>iam using pathon gui...but the problem is that scr...</title><summary type='text'>iam using pathon gui...but the problem is that scripts run and now error /or any output comes..:(...i have to extract titles and authors from reserach papers :(</summary><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/16840474/8153824157621127866/comments/default/4113483675264243565'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/16840474/8153824157621127866/comments/default/4113483675264243565'/><link rel='alternate' type='text/html' href='http://blog.isnotworking.com/2006/08/extract-pdf-title-from-all-files-on.html?showComment=1214219460000#c4113483675264243565' title=''/><author><name>SeaCat</name><uri>http://www.blogger.com/profile/14825527719712567256</uri><email>noreply@blogger.com</email></author><thr:in-reply-to xmlns:thr='http://purl.org/syndication/thread/1.0' href='http://blog.isnotworking.com/2006/08/extract-pdf-title-from-all-files-on.html' ref='tag:blogger.com,1999:blog-16840474.post-8153824157621127866' source='http://www.blogger.com/feeds/16840474/posts/default/8153824157621127866' type='text/html'/></entry><entry><id>tag:blogger.com,1999:blog-16840474.post-8415626907422348216</id><published>2008-06-23T07:40:00.000-03:00</published><updated>2008-06-23T07:40:00.000-03:00</updated><title type='text'>@SeaCat: you must run it from a command prompt:c:\...</title><summary type='text'>@SeaCat: you must run it from a command prompt:&lt;BR/&gt;&lt;BR/&gt;c:\python25\python script.py</summary><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/16840474/8153824157621127866/comments/default/8415626907422348216'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/16840474/8153824157621127866/comments/default/8415626907422348216'/><link rel='alternate' type='text/html' href='http://blog.isnotworking.com/2006/08/extract-pdf-title-from-all-files-on.html?showComment=1214217600000#c8415626907422348216' title=''/><author><name>Ricardo N. Cabral</name><uri>http://www.blogger.com/profile/16520043212251579884</uri><email>noreply@blogger.com</email><gd:extendedProperty xmlns:gd='http://schemas.google.com/g/2005' name='OpenSocialUserId' value='03280217668849867554'/></author><thr:in-reply-to xmlns:thr='http://purl.org/syndication/thread/1.0' href='http://blog.isnotworking.com/2006/08/extract-pdf-title-from-all-files-on.html' ref='tag:blogger.com,1999:blog-16840474.post-8153824157621127866' source='http://www.blogger.com/feeds/16840474/posts/default/8153824157621127866' type='text/html'/></entry><entry><id>tag:blogger.com,1999:blog-16840474.post-3439696237472261778</id><published>2008-06-23T07:37:00.000-03:00</published><updated>2008-06-23T07:37:00.000-03:00</updated><title type='text'>in the first and second code where you have given ...</title><summary type='text'>in the first and second code where you have given folder path ..iam trying to us ethis script ..it runs but wher eis output...iam new in paython</summary><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/16840474/8153824157621127866/comments/default/3439696237472261778'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/16840474/8153824157621127866/comments/default/3439696237472261778'/><link rel='alternate' type='text/html' href='http://blog.isnotworking.com/2006/08/extract-pdf-title-from-all-files-on.html?showComment=1214217420000#c3439696237472261778' title=''/><author><name>SeaCat</name><uri>http://www.blogger.com/profile/14825527719712567256</uri><email>noreply@blogger.com</email></author><thr:in-reply-to xmlns:thr='http://purl.org/syndication/thread/1.0' href='http://blog.isnotworking.com/2006/08/extract-pdf-title-from-all-files-on.html' ref='tag:blogger.com,1999:blog-16840474.post-8153824157621127866' source='http://www.blogger.com/feeds/16840474/posts/default/8153824157621127866' type='text/html'/></entry><entry><id>tag:blogger.com,1999:blog-16840474.post-978521739243775582</id><published>2008-04-09T12:21:00.000-03:00</published><updated>2008-04-09T12:21:00.000-03:00</updated><title type='text'>Hi,This looks so useful, but I can't make it work....</title><summary type='text'>Hi,&lt;BR/&gt;This looks so useful, but I can't make it work. Really, because I don't know anything of programing. Please help (detailed help).&lt;BR/&gt;I put the pdf files in the python folder&lt;BR/&gt;I run Python Shell&lt;BR/&gt;I copied from the Blog the script and pasted it in the Python window&lt;BR/&gt;Nothing happened.&lt;BR/&gt;I don't know, do I need to change some names in the script according to my data?&lt;BR/&gt;Please </summary><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/16840474/8153824157621127866/comments/default/978521739243775582'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/16840474/8153824157621127866/comments/default/978521739243775582'/><link rel='alternate' type='text/html' href='http://blog.isnotworking.com/2006/08/extract-pdf-title-from-all-files-on.html?showComment=1207754460000#c978521739243775582' title=''/><author><name>Anonymous</name><email>noreply@blogger.com</email></author><thr:in-reply-to xmlns:thr='http://purl.org/syndication/thread/1.0' href='http://blog.isnotworking.com/2006/08/extract-pdf-title-from-all-files-on.html' ref='tag:blogger.com,1999:blog-16840474.post-8153824157621127866' source='http://www.blogger.com/feeds/16840474/posts/default/8153824157621127866' type='text/html'/></entry><entry><id>tag:blogger.com,1999:blog-16840474.post-5519525841563526974</id><published>2008-03-03T04:40:00.000-03:00</published><updated>2008-03-03T04:40:00.000-03:00</updated><title type='text'>Hi, pal.I am facing exactly the same problem as Ca...</title><summary type='text'>Hi, pal.&lt;BR/&gt;&lt;BR/&gt;I am facing exactly the same problem as Cartman's&lt;BR/&gt; &lt;BR/&gt;But it’s far from a neat solution because many pdf creator won’t put real title as metadata that can be seen in native format or document property.&lt;BR/&gt;&lt;BR/&gt;Is there any better way ?&lt;BR/&gt;&lt;BR/&gt;Dexter</summary><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/16840474/8153824157621127866/comments/default/5519525841563526974'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/16840474/8153824157621127866/comments/default/5519525841563526974'/><link rel='alternate' type='text/html' href='http://blog.isnotworking.com/2006/08/extract-pdf-title-from-all-files-on.html?showComment=1204530000000#c5519525841563526974' title=''/><author><name>Anonymous</name><email>noreply@blogger.com</email></author><thr:in-reply-to xmlns:thr='http://purl.org/syndication/thread/1.0' href='http://blog.isnotworking.com/2006/08/extract-pdf-title-from-all-files-on.html' ref='tag:blogger.com,1999:blog-16840474.post-8153824157621127866' source='http://www.blogger.com/feeds/16840474/posts/default/8153824157621127866' type='text/html'/></entry><entry><id>tag:blogger.com,1999:blog-16840474.post-1849391071119801190</id><published>2007-11-16T21:51:00.000-02:00</published><updated>2007-11-16T21:51:00.000-02:00</updated><title type='text'># modified script in order to rename files with ti...</title><summary type='text'># modified script in order to rename files with titles&lt;BR/&gt;# pyPdf available at http://pybrary.net/pyPdf/&lt;BR/&gt;&lt;BR/&gt;from pyPdf import PdfFileWriter, PdfFileReader&lt;BR/&gt;import os&lt;BR/&gt;&lt;BR/&gt;for fileName in os.listdir('.'):&lt;BR/&gt;    try:&lt;BR/&gt;        if fileName.lower()[-3:] != "pdf": continue&lt;BR/&gt;        input1 = PdfFileReader(file(fileName, "rb"))&lt;BR/&gt;   &lt;BR/&gt;# rename the document with it's title&lt;BR/&gt; </summary><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/16840474/8153824157621127866/comments/default/1849391071119801190'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/16840474/8153824157621127866/comments/default/1849391071119801190'/><link rel='alternate' type='text/html' href='http://blog.isnotworking.com/2006/08/extract-pdf-title-from-all-files-on.html?showComment=1195257060000#c1849391071119801190' title=''/><author><name>daui</name><email>noreply@blogger.com</email></author><thr:in-reply-to xmlns:thr='http://purl.org/syndication/thread/1.0' href='http://blog.isnotworking.com/2006/08/extract-pdf-title-from-all-files-on.html' ref='tag:blogger.com,1999:blog-16840474.post-8153824157621127866' source='http://www.blogger.com/feeds/16840474/posts/default/8153824157621127866' type='text/html'/></entry><entry><id>tag:blogger.com,1999:blog-16840474.post-6016857486503512049</id><published>2007-09-30T04:33:00.000-03:00</published><updated>2007-09-30T04:33:00.000-03:00</updated><title type='text'>nice! but the problem is, many pdf files on the in...</title><summary type='text'>nice! but the problem is, many pdf files on the internet do not have the title information inside them! I tried this on my collection, but did not find even one pdf file with "real title"! of course, the dvi file name from which the pdf was created, that was printed out though!</summary><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/16840474/8153824157621127866/comments/default/6016857486503512049'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/16840474/8153824157621127866/comments/default/6016857486503512049'/><link rel='alternate' type='text/html' href='http://blog.isnotworking.com/2006/08/extract-pdf-title-from-all-files-on.html?showComment=1191137580000#c6016857486503512049' title=''/><author><name>Cartman</name><uri>http://www.blogger.com/profile/12812119286609384839</uri><email>noreply@blogger.com</email></author><thr:in-reply-to xmlns:thr='http://purl.org/syndication/thread/1.0' href='http://blog.isnotworking.com/2006/08/extract-pdf-title-from-all-files-on.html' ref='tag:blogger.com,1999:blog-16840474.post-8153824157621127866' source='http://www.blogger.com/feeds/16840474/posts/default/8153824157621127866' type='text/html'/></entry><entry><id>tag:blogger.com,1999:blog-16840474.post-6911501626125844715</id><published>2007-07-19T12:29:00.000-03:00</published><updated>2007-07-19T12:29:00.000-03:00</updated><title type='text'>Thanks a lot, what a good script and library!</title><summary type='text'>Thanks a lot, what a good script and library!</summary><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/16840474/8153824157621127866/comments/default/6911501626125844715'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/16840474/8153824157621127866/comments/default/6911501626125844715'/><link rel='alternate' type='text/html' href='http://blog.isnotworking.com/2006/08/extract-pdf-title-from-all-files-on.html?showComment=1184858940000#c6911501626125844715' title=''/><author><name>Endy</name><uri>http://www.blogger.com/profile/06316078387624015564</uri><email>noreply@blogger.com</email></author><thr:in-reply-to xmlns:thr='http://purl.org/syndication/thread/1.0' href='http://blog.isnotworking.com/2006/08/extract-pdf-title-from-all-files-on.html' ref='tag:blogger.com,1999:blog-16840474.post-8153824157621127866' source='http://www.blogger.com/feeds/16840474/posts/default/8153824157621127866' type='text/html'/></entry><entry><id>tag:blogger.com,1999:blog-16840474.post-530418663604775409</id><published>2006-08-20T09:23:00.000-03:00</published><updated>2006-08-20T09:23:00.000-03:00</updated><title type='text'>That`s what I searched! Thank you very much, very ...</title><summary type='text'>That`s what I searched! Thank you very much, very usefull script!</summary><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/16840474/8153824157621127866/comments/default/530418663604775409'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/16840474/8153824157621127866/comments/default/530418663604775409'/><link rel='alternate' type='text/html' href='http://blog.isnotworking.com/2006/08/extract-pdf-title-from-all-files-on.html?showComment=1156076580000#c530418663604775409' title=''/><author><name>virens</name><uri>http://www.blogger.com/profile/09753073746058450952</uri><email>noreply@blogger.com</email></author><thr:in-reply-to xmlns:thr='http://purl.org/syndication/thread/1.0' href='http://blog.isnotworking.com/2006/08/extract-pdf-title-from-all-files-on.html' ref='tag:blogger.com,1999:blog-16840474.post-8153824157621127866' source='http://www.blogger.com/feeds/16840474/posts/default/8153824157621127866' type='text/html'/></entry></feed>