Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

merge from trunk

Browse Source
This commit is contained in:
ldolse 2010-11-16 15:17:09 +08:00
commit 801d26e9ba
258 changed files with 102468 additions and 54082 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

448
Changelog.yaml
View File

@ -4,6 +4,453 @@
# for important features/bug fixes.
# Also, each release can have new and improved recipes.
- version: 0.7.28
date: 2010-11-12
new features:
- title: "Update the version of the grahical toolkit (Qt 4.7.1) used in the calibre binary builds on windows and linux. This should result in a significant speed up for the calibre ebook viewer"
- title: "Driver for Nook Color, Eken M001"
- title: "Add a tweak to turn off double clicking to open viewer"
- title: "Catalog generation: Add indication when a book has no formats"
tickets: [7376]
- title: "Advanced search dialog: Add a tab to allow searching particular metadata fields easily"
- title: "Conversion pipeline: When using the Level x Table of Contents expressions, if a tag is empty but has a non-empty title attribute, use that instead of ignoring the tag"
bug fixes:
- title: "Comic metadata reader: Sort filenames aplhabetically when choosing an image for the cover"
tickets: [7488]
- title: "Bulk convert dialog: Hide useless restore defaults button."
tickets: [7471]
- title: "Conversion pipeline: Handle input documents that encode null bytes as HTML entities correctly"
tickets: [7355]
- title: "Fix some SONY readers not being detected on windows"
tickets: [7413]
- title: "MOBI Input: Fix images missing when converting MOBI news downloads created with Mobipocket reader"
tickets: [7455]
- title: "ODT Input: Handle hyperlinks to headings that have truncated destination specifiers correctly"
tickets: [7506]
- title: "Sony driver: Ignore invalid strings when updating XML database"
- title: "Content Server: Add day to displayed date in /mobile book listing"
- title: "MOBI Input: Do not generate filenames with only extensions if the MOBI file has no internal name"
tickets: [7481]
- title: "MOBI Input: Handle files that has the record sizes set incorrectly to a long integer"
tickets: [7472]
- title: "Fix not enough vertical space for text in the preferences dialog category listing"
- title: "Remove 'sort' from Search and replace destination fields and add it to source fields. S&R is no longer marked experimental"
- title: "Edit metadata dialog: Save dialog geometry on reject as well as on accept"
- title: "E-book viewer: Fix clicking entries in TOC that point to the currently loaded flow not scrolling view to the top of the document"
- title: "Fix bug in regex used to extract charset from <meta> tags"
- title: "MOBI Output: Add support for the <q> tag"
improved recipes:
- Zeit Online
- Gamespot Review
- Ploitika
- Pagina12
- Irish Times
- elektrolese
new recipes:
- title: "Handelsblatt and European Voice"
author: "malfi"
- title: "Polityka and Newsweek"
author: "Mateusz Kielar"
- title: "MarcTV"
author: "Marc Toensings"
- title: "Rolling Stone"
author: "Darko Miletic"
- title: "Vedomosti"
author: "Nikolai Kotchetkov"
- title: "Hola.com"
author: "bmsleight"
- title: "Dnevnik, Siol.net, MMC-RTV and Avto-magazon"
author: "BlonG"
- title: "SC Print Magazine"
author: "Tony Maro"
- title: "Diario Sport"
author: "Jefferson Frantz"
- version: 0.7.27
date: 2010-11-05
new features:
- title: "The book list behavior has changed"
type: major
description: >
"Now double clicking on an entry in the book list will open it in the viewer. To edit metadata single click a previously selected entry instead. This is consistent with
the usage in most operating systems, so should be most intuitive for new users. Also typing any key no longer starts an edit, instead press F2 (Enter on OS X) to start editing
the current cell. Also you now have to double click instead of single clicking the book details panel to open the detailed info dialog for the book."
- title: "Added a new HTML output format plugin, which converts the input document to a ZIP file. The zip file contains HTML pages suitable for display in a website"
- title: "Support for iRiver Cover Story and Digma Q600"
- title: "Add a search button (labelled Go!) to explicitly run a search with the text currently in the quick search box"
- title: "Add author to the calibre geenrated book jacket"
tickets: [7402]
- title: "Add the title of the destination book to the merge dialog warning message"
- title: "calibre-server: Make auto reload control separate from --devlop with a new command line option --auto-reload"
bug fixes:
- title: "Fix book details panel not being updated after a delete-merge"
tickets: [7426]
- title: "Fix clicking in the search box launches a search if you have search as you type enabled"
tickets: [7425]
- title: "Use a browser widget to display book details for more robustness and better performance when vieweing large HTML comments"
- title: "Fix cover browser not updated after copy to library and delete"
tickets: [7416]
- title: "Fix regression that broke sending non calibre EPUB files to the iPad. Also handle failure to set cover in iTunes gracefully"
tickets: [7356]
- title: "News download: Workaround lack of thread safety in python mechanize, causing corrupted network packets (degrading network performance) on Ubuntu Maverick 64bit kernels"
tickets: [7321]
- title: "Convert comments to HTML for book details panel in separate thread to make scrolling through the book list faster when large comments are present"
- title: "calibre-server: Fix regression that broke --daemonize"
- title: "EPUB Input: Handle ncx files that have <navpoint> elements with no content correctly."
tickets: [7396]
- title: "SNBOutput: Fixed a bug in handling pre tag"
- title: "MOBI Output: Don't ignore hidden anchors."
tickets: [7384]
- title: "Fix switching libraries and generating a catalog could generate a catalog for the wrong library"
- title: "MOBI Output: Fix regression that broke conversion of anchors inside superscripts/subscripts."
tickets: [7368]
- title: "Content server: Fix various minor bugs"
tickets: [7379, 6768, 7354]
- title: "Amazon metadata download plugin: Make it more robust and add option to auto convert HTML to text"
- title: "Re-arrange send to device menu to make it harder to accidentally trigger the send and delete actions"
improved recipes:
- Danas
- Fudzilla
- Zeit Online
- New York Times
- Mediapart
new recipes:
- title: "Ynet and Calcalist"
author: "marbs"
- title: "El Faro de Vigo"
author: "Jefferson Frantz"
- title: "Clic_RBS"
author: "avoredo"
- title: "Correio da Manha"
author: "jmst"
- title: "Rue89"
author: "Louis Gesbert"
- version: 0.7.26
date: 2010-10-30
new features:
- title: "Check library: Allow wildcards in ignore names field"
bug fixes:
- title: "Fix regression in 0.7.25 that broke reading metadata from filenames."
- title: "Fix regression in 0.7.25 that caused original files to be mistakenly removed when adding books recursively"
- title: "Fix long series/publisher causing edit metadata in bulk dialog to become very large"
tickets: [7332]
- title: "Only add SONY periodical code to downloaded news if output profile is set to one of the SONY reader profiles. This is needed because the ever delightful Stanza crashes and burns when an EPUB has the periodical code"
improved recipes:
- El Periodico
- New Zealand Herald
new recipes:
- title: "Taggeschau.de"
author: "Florian Andreas Pfaff"
- title: "Gamespot Reviews"
author: "Marc Tonsing"
- version: 0.7.25
date: 2010-10-29
new features:
- title: "Add support for the SONY periodical format."
description: "This means that news downloaded by calibre and sent to a newer SONY device (350/650/900) should appear in the Periodicals section and have the special periodicals navigation user interface"
type: major
- title: "Content server: Make the new browsing interface the default. The old interface can be accessed at /old"
- title: "Content server: Allow running of content server as a WSGI application within another server. Add tutorial for this to the User Manual."
- title: "Support for the Pico Life reader, Kobo Wifi and HTC Aria"
- title: "Content server: Add a new --url-prefix command line option to ease the use of the server with a reverse proxy"
- title: "New social metadata plugin for Amazon that does not rely on AWS. Since Amazon broke AWS, it is recommended you upgrade to this version if you use metadata from Amazon"
- title: "Add a tweak to specify the fonts used when geenrating the default cover"
- title: "Add an output profile for generic Tablet devices"
tickets: [7289]
- title: "SONY driver: Allow sorting of collections by arbitrary field via a new tweak."
- title: "Content server: Make /mobile a little prettier"
- title: "Add button to 'Library Check' to automatically delete spurious files and folders"
bug fixes:
- title: "FB2 Input: Lots of love. Handle stylesheets and style attributes. Make parsinf malformed FB2 files more robust."
tickets: [7219, 7230]
- title: "Fix auto send of news to device with multiple calibre libraries. The fix means that if you have any pending news to be sent, it will be ignored after the update. Future news downloads will once again be automatically sent to the device."
- title: "MOBI Output: Conversion of super/sub scripts now handles nested tags."
tickets: [7264]
- title: "Conversion pipeline: Fix parsing of XML encoding declarations."
tickets: [7328]
- title: "Pandigital (Kobo): Upload thumbnails to correct location"
tickets: [7165]
- title: "Fix auto emailed news with non asci characters in title not being deliverd to Kindle"
tickets: [7322]
- title: "Read metadata only after on import plugins have run when adding books to GUI"
tickets: [7245]
- title: "Various fixes for bugs caused by non ascii temporary paths on windows with non UTF-8 filesystem encodings"
tickets: [7288]
- title: "Various fixes/enhancements to SNB Output"
- title: "Allow Tag editor in edit metadata dialog to be used even if tags have been changed"
tickets: [7298]
- title: "Fix crash on some OS X machines when Preferences->Conversion->Output is clicked"
- title: "MOBI indexing: Fix last entry missing sometimes"
tickets: [6595]
- title: "Fix regression causing books to be deselected after sending to device"
tickets: [7271]
- title: "Conversion pipeline: Fix rescaling of GIF images not working"
tickets: [7306]
- title: "Update PDF metadata/conversion libraries in windows build"
- title: "Fix timezone bug when searching on date fields"
tickets: [7300]
- title: "Fix regression that caused the viewr to crash if the main application is closed"
tickets: [7276]
- title: "Fix bug causing a spurious metadata.opf file to be written at the root of the calibre library when adding books"
- title: "Use the same title casing algorithm in all places"
- title: "Fix bulk edit of dual state boolean custom columns"
- title: "Increase image size for comics in Kindle DX profile for better conversion of comics to PDF"
- title: "Fix restore db to not dies when conflicting custom columns are encountered and report conflicting columns errors. Fix exceptions when referencing invalid _index fields."
- title: "Fix auto merge books not respecting article sort tweak"
tickets: [7147]
- title: "Linux device drivers: Fix udisks based ejecting for devices with multiple nodes"
- title: "Linux device mounting: Mount the drive with the lowest kernel name as main memory"
- title: "Fix use of numeric fields in templates"
- title: "EPUB Input: Handle EPUB files with multiple OPF files."
tickets: [7229]
- title: "Setting EPUB metadata: Fix date format. Fix language being overwritten by und when unspecified. Fix empty ISBN identifier being created"
- title: "Fix cannot delete a Series listing from List view also dismiss fetch metadata dialog when no metadata found automatically"
tickets: [7221, 7220]
- title: "Content server: Handle switch library in GUI gracefully"
- title: "calibre-server: Use cherrypy implementation of --pidfile and --daemonize"
new recipes:
- title: "Ming Pao"
author: "Eddie Lau"
- title: "lenta.ru"
author: "Nikolai Kotchetkov"
- title: "frazpc.pl"
author: "Tomasz Dlugosz"
- title: "Perfil and The Economic Collapse Blog"
author: "Darko Miletic"
- title: "STNN"
author: "Larry Chan"
improved recipes:
- CubaDebate
- El Pais
- Fox News
- New Scientist
- The Economic Times of India
- version: 0.7.24
date: 2010-10-17
new features:
- title: "Content server: New interface that allows browsing via categories, similar to the Tag Browser in the calibre interface."
description: >
"You can access the new interface by going to /browse. So if your calibre content server is available at http://192.168.1.2, use
http://192.168.1.2/browse. The new interface requires a fairly modern browser, so no Internet Explorer 6,7."
type: major
- title: "Support for the SNB e-book format, used by the Bambook e-book reader"
type: major
- title: "Driver for the Wifi Kobo"
- title: "Edit metadata dialog: If metadata is downloaded successfully, set focus to download cover button"
- title: "News download system: Allow recipes with optional subscriptions"
tickets: [7199]
- title: "Templates: Improve the smarten function"
- title: "Linux device mounting: Use udisks, if it is available, to mount devices, so that I no longer have to hear bug reports from users using distro packages that have crippled calibre-mount-helper. You can turn off udisks by setting the environment variable CALIBRE_DISABLE_UDISKS=1"
- title: "Implement Drag'n'drop to tags in user categories"
tickets: [7172]
- title: "Ebook viewer: Add command line option to start in full screen mode"
- title: "Set completion mode on search boxes to popup completion"
- title: "Update version of jQuery used in content server and viewer. Required a little hackery in the viewer, hopefully nothing broke"
bug fixes:
- title: "Linux device drivers: Ignore read only partition exported by the device"
- title: "E-book viewer: Fix scrolling down with mouse wheel not always reaching bottom in windows"
- title: "Smarten punctuation: Fix bug in handling of comments and <style> tags"
- title: "EPUB Input: Handle EPUB files with components encoded in an encoding other than UTF-8 correctly, though why anyone would do that is a mystery."
tickets: [7196]
- title: "OS X commandline tools: Decode non-ascii command line arguments correctly"
tickets: [6964]
- title: "MOBI Output: Fix bug that broke conversion of <svg> elements in the input document when the <svg> element was followed by non-whitespace text."
tickets: [7083]
- title: "CHM Input: Fix handling of relative file paths in <img> tags."
tickets: [7159]
- title: "EPUB Output: Fix incorrect format for xml:lang when specifying a sub language"
tickets: [7198]
- title: "EPUB Input: Make parsing of toc.ncx more robust."
tickets: [7170]
- title: "Content server: Fix searching with non-ascii characters on windows"
tickets: [5249]
- title: "Fix average rating calculation for rating datatype in Tag Browser incorrect"
- title: "Comic Input: Fix image borders becoming yellow on some windows installs"
- title: "Email sending: Fix sending of email with non ascii chars"
tickets: [7137]
- title: "SONY driver: Fix collections created from series not in order with manual metadata management, if all books in the series are not sent at once"
- title: "Content server: Apply the search restriction when generating category lists as well"
- title: "RTF Input: Fix regression in conversion of WMF images on linux at least, maybe on other platforms as wel"
- title: "Fix isbndb.com metadata downloading sometimes yield a title of Unknown"
tickets: [7114]
- title: "Fix edit metadata dialog causing the hour:minute:seconds of the date column being lost, even when date is not changed"
tickets: [7125]
new recipes:
- title: "Revista El Cultural"
author: "Jefferson Frantz"
- title: "Novaya Gazeta"
author: "muwa"
- title: "frazpc.pl"
author: "Tomasz Dlugosz"
- title: "Orsai and Financial Times UK"
author: "Darko Miletic"
- title: "Malayasian Mirror and Rolling Stones"
author: "Tony Stegall"
improved recipes:
- Globe and Mail
- Business Standard
- Miami Herald
- El Mercurio
- volkskrant.nl
- GoComics.com
- The New Yorker
- version: 0.7.23
date: 2010-10-08
@ -51,6 +498,7 @@
- title: "CHM input: handle another class of broken CHM files"
tickets: [7058]
- title: "Make calibre worker processes use the same temp directory as the calibre GUI"
new recipes:
- title: "Communications of the Association for Computing Machinery"

19
resources/catalog/stylesheet.css
View File

@ -81,6 +81,14 @@ p.unread_book {
text-indent:-2em;
}
p.wishlist_item {
text-align:left;
margin-top:0px;
margin-bottom:0px;
margin-left:2em;
text-indent:-2em;
}
p.date_read {
text-align:left;
margin-top:0px;
@ -104,3 +112,14 @@ hr.annotations_divider {
margin-top:0em;
margin-bottom:0em;
}
td.publisher, td.date {
font-weight:bold;
text-align:center;
}
td.rating {
text-align: center;
}
td.thumbnail img {
-webkit-box-shadow: 6px 6px 6px #888;
}

13
resources/content_server/browse/browse.css
View File

@ -208,6 +208,8 @@ h2.library_name {
}
.toplevel li a { text-decoration: none; }
.toplevel li img {
vertical-align: middle;
margin-right: 1em;
@ -261,9 +263,16 @@ h2.library_name {
}
.category div.category-item span.href { display: none }
.category div.category-item a { text-decoration: none; color: inherit; }
#groups span.load_href { display: none }
#groups a.load_href {
text-decoration: none;
color: inherit;
font-size: medium;
font-weight: normal;
padding: 0;
padding-left: 0.5em;
}
#groups h3 {
font-weight: bold;

35
resources/content_server/browse/browse.html
View File

@ -4,28 +4,29 @@
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
<title>..:: calibre library ::.. {title}</title>
<title>..:: calibre {library} ::.. {title}</title>
<meta http-equiv="X-UA-Compatible" content="IE=100" />
<link rel="icon" type="image/x-icon" href="http://calibre-ebook.com/favicon.ico" />
<link rel="stylesheet" type="text/css" href="/static/browse/browse.css" />
<link type="text/css" href="/static/jquery_ui/css/humanity-custom/jquery-ui-1.8.5.custom.css" rel="stylesheet" />
<link rel="stylesheet" type="text/css" href="/static/jquery.multiselect.css" />
<link rel="stylesheet" type="text/css" href="{prefix}/static/browse/browse.css" />
<link type="text/css" href="{prefix}/static/jquery_ui/css/humanity-custom/jquery-ui-1.8.5.custom.css" rel="stylesheet" />
<link rel="stylesheet" type="text/css" href="{prefix}/static/jquery.multiselect.css" />
<script type="text/javascript" src="/static/jquery.js"></script>
<script type="text/javascript" src="/static/jquery.corner.js"></script>
<script type="text/javascript" src="{prefix}/static/jquery.js"></script>
<script type="text/javascript" src="{prefix}/static/jquery.corner.js"></script>
<script type="text/javascript"
src="/static/jquery_ui/js/jquery-ui-1.8.5.custom.min.js"></script>
src="{prefix}/static/jquery_ui/js/jquery-ui-1.8.5.custom.min.js"></script>
<script type="text/javascript"
src="/static/jquery.multiselect.min.js"></script>
src="{prefix}/static/jquery.multiselect.min.js"></script>
<script type="text/javascript" src="/static/browse/browse.js"></script>
<script type="text/javascript" src="{prefix}/static/browse/browse.js"></script>
<script type="text/javascript">
var sort_cookie_name = "{sort_cookie_name}";
var sort_select_label = "{sort_select_label}";
var url_prefix = "{prefix}";
$(document).ready(function() {{
init();
{script}
@ -39,16 +40,16 @@
<div id="header">
<div class="area">
<div class="bubble">
<p><a href="/browse" title="Return to top level"
>&rarr;&nbsp;home&nbsp;&larr;</a></p>
<p><a href="{prefix}/browse" title="Return to top level"
>&rarr;&nbsp;{home}&nbsp;&larr;</a></p>
</div>
</div>
<div id="nav-container">&nbsp;
<ul id="primary-nav">
<li><a id="nav-mobile" href="/mobile" title="A version of this website suited for mobile browsers">Mobile</a></li>
<li><a id="nav-mobile" href="{prefix}/mobile" title="A version of this website suited for mobile browsers">Mobile</a></li>
<li><a id="nav-demo" href="/old" title="The old version of this webiste">Old</a></li>
<li><a id="nav-download" href="/opds" title="An OPDS feed based version of this website, used in special purpose applications">Feed</a></li>
<li><a id="nav-demo" href="{prefix}/old" title="The old version of this webiste">Old</a></li>
<li><a id="nav-download" href="{prefix}/opds" title="An OPDS feed based version of this website, used in special purpose applications">Feed</a></li>
</ul>
</div>
@ -58,7 +59,7 @@
<input type="hidden" name="cmd" value="_s-xclick"></input>
<input type="hidden" name="hosted_button_id" value="3028915"></input>
<input type="image"
src="http://calibre-ebook.com/site_media//img/button-donate.png"
src="{prefix}/static/button-donate.png"
name="submit"></input>
<img alt="" src="https://www.paypal.com/en_US/i/scr/pixel.gif"
width="1" height="1"></img>
@ -76,10 +77,10 @@
</select>
</div>
<div id="search_box">
<form name="search_form" action="/browse/search" method="get" accept-charset="UTF-8">
<form name="search_form" action="{prefix}/browse/search" method="get" accept-charset="UTF-8">
<input value="{initial_search}" type="text" title="Search" name="query"
class="search_input" />&nbsp;
<input type="submit" value="Search" title="Search" alt="Search" />
<input type="submit" value="{Search}" title="{Search}" alt="{Search}" />
</form>
</div>
<div>&nbsp;</div>

13
resources/content_server/browse/browse.js
View File

@ -109,14 +109,14 @@ function toplevel_layout() {
var last = $(".toplevel li").last();
var title = $('.toplevel h3').first();
var bottom = last.position().top + last.height() - title.position().top;
$("#main").height(Math.max(200, bottom));
$("#main").height(Math.max(200, bottom+75));
}
function toplevel() {
$(".sort_select").hide();
$(".toplevel li").click(function() {
var href = $(this).children("span.url").text();
var href = $(this).children("a").attr('href');
window.location = href;
});
@ -133,7 +133,7 @@ function render_error(msg) {
// Category feed {{{
function category_clicked() {
var href = $(this).find("span.href").html();
var href = $(this).find("a").attr('href');
window.location = href;
}
@ -151,11 +151,12 @@ function category() {
change: function(event, ui) {
if (ui.newContent) {
var href = ui.newContent.children("span.load_href").html();
var href = ui.newContent.prev().children("a.load_href").attr('href');
ui.newContent.children(".loading").show();
if (href) {
$.ajax({
url:href,
cache: false,
data:{'sort':cookie(sort_cookie_name)},
success: function(data) {
this.children(".loaded").html(data);
@ -212,6 +213,7 @@ function load_page(elem) {
url: href,
context: elem,
dataType: "json",
cache : false,
type: 'POST',
timeout: 600000, //milliseconds (10 minutes)
data: {'ids': ids},
@ -255,7 +257,7 @@ function booklist(hide_sort) {
function show_details(a_dom) {
var book = $(a_dom).closest('div.summary');
var bd = $('#book_details_dialog');
bd.html('<span class="loading"><img src="/static/loading.gif" alt="Loading" />Loading, please wait&hellip;</span>');
bd.html('<span class="loading"><img src="'+url_prefix+'/static/loading.gif" alt="Loading" />Loading, please wait&hellip;</span>');
bd.dialog('option', 'width', $(window).width() - 100);
bd.dialog('option', 'height', $(window).height() - 100);
bd.dialog('option', 'title', book.find('.title').text());
@ -263,6 +265,7 @@ function show_details(a_dom) {
$.ajax({
url: book.find('.details-href').attr('title'),
context: bd,
cache: false,
dataType: "json",
timeout: 600000, //milliseconds (10 minutes)
error: function(xhr, stat, err) {

2
resources/content_server/browse/details.html
View File

@ -1,6 +1,6 @@
<div id="details_{id}" class="details">
<div class="left">
<img alt="Cover of {title}" src="/get/cover/{id}" />
<img alt="Cover of {title}" src="{prefix}/get/cover/{id}" />
</div>
<div class="right">
<div class="field formats">{formats}</div>

4
resources/content_server/browse/summary.html
View File

@ -1,6 +1,6 @@
<div id="summary_{id}" class="summary">
<div class="left">
<img alt="Cover of {title}" src="/get/thumb_90_120/{id}" />
<img alt="Cover of {title}" src="{prefix}/get/thumb_90_120/{id}" />
{get_button}
</div>
<div class="right">
@ -8,7 +8,7 @@
<span class="rating_container">{stars}</span>
<span class="series">{series}</span>
<a href="#" onclick="show_details(this); return false;" title="{details_tt}">{details}</a>
<a href="/browse/book/{id}" title="{permalink_tt}">{permalink}</a>
<a href="{prefix}/browse/book/{id}" title="{permalink_tt}">{permalink}</a>
</div>
<div class="title"><strong>{title}</strong></div>
<div class="authors">{authors}</div>

BIN
resources/content_server/button-donate.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 1.6 KiB

4
resources/content_server/gui.js
View File

@ -40,7 +40,7 @@ function create_table_headers() {
function format_url(format, id, title) {
return 'get/'+format.toLowerCase() + '/'+encodeURIComponent(title) + '_' + id+'.'+format.toLowerCase();
return url_prefix + '/get/'+format.toLowerCase() + '/'+encodeURIComponent(title) + '_' + id+'.'+format.toLowerCase();
}
function render_book(book) {
@ -101,7 +101,7 @@ function render_book(book) {
}
}
title += '</span>'
title += '<img style="display:none" alt="" src="get/cover/{0}" /></span>'.format(id);
title += '<img style="display:none" alt="" src="{1}/get/cover/{0}" /></span>'.format(id, url_prefix);
title += '<div class="comments">{0}</div>'.format(comments)
// Render authors cell
var _authors = new Array();

19
resources/content_server/index.html
View File

@ -3,26 +3,27 @@
<html xmlns="http://www.w3.org/1999/xhtml" version="XHTML 1.1" xml:lang="en">
<head>
<title>calibre library</title>
<link rel="stylesheet" type="text/css" href="/static/gui.css" charset="utf-8" />
<script type="text/javascript" src="/static/date.js" charset="utf-8"></script>
<script type="text/javascript" src="/static/jquery.js" charset="utf-8"></script>
<script type="text/javascript" src="/static/gui.js" charset="utf-8"></script>
<script type="text/javascript">var url_prefix='{prefix}';</script>
<link rel="stylesheet" type="text/css" href="{prefix}/static/gui.css" charset="utf-8" />
<script type="text/javascript" src="{prefix}/static/date.js" charset="utf-8"></script>
<script type="text/javascript" src="{prefix}/static/jquery.js" charset="utf-8"></script>
<script type="text/javascript" src="{prefix}/static/gui.js" charset="utf-8"></script>
<link rel="icon" href="http://calibre-ebook.com/favicon.ico" type="image/x-icon" />
</head>
<body>
<div id="banner">
<a style="border: 0pt" href="http://calibre-ebook.com" alt="calibre" title="calibre"><img style="border:0pt" src="/static/calibre_banner.png" alt="calibre" /></a>
<a style="border: 0pt" href="http://calibre-ebook.com" alt="calibre" title="calibre"><img style="border:0pt" src="{prefix}/static/calibre_banner.png" alt="calibre" /></a>
</div>
<div id="search_box">
<form name="search_form" onsubmit="search();return false;" action="./" method="get" accept-charset="UTF-8">
<form name="search_form" onsubmit="search();return false;" action="{prefix}/old" method="get" accept-charset="UTF-8">
<input value="" id="s" type="text" />
<input type="image" src="/static/btn_search_box.png" width="27" height="24" id="go" alt="Search" title="Search" />
<input type="image" src="{prefix}/static/btn_search_box.png" width="27" height="24" id="go" alt="Search" title="Search" />
</form>
</div>
<div id="count_bar">
<span id="left"><img src="/static/first.png" alt="Show first set of books" title="Show first set of books"/>&nbsp;<img src="/static/previous.png" alt="Show previous set of books" title="Show previous set of books"/>&nbsp;</span><span id="count">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</span>&nbsp;<span id="right"><img src="/static/next.png" alt="Show next set of books" title="Show next set of books"/>&nbsp;<img src="/static/last.png" alt="Show last set of books" title="Show last set of books" /></span>
<span id="left"><img src="{prefix}/static/first.png" alt="Show first set of books" title="Show first set of books"/>&nbsp;<img src="{prefix}/static/previous.png" alt="Show previous set of books" title="Show previous set of books"/>&nbsp;</span><span id="count">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</span>&nbsp;<span id="right"><img src="{prefix}/static/next.png" alt="Show next set of books" title="Show next set of books"/>&nbsp;<img src="{prefix}/static/last.png" alt="Show last set of books" title="Show last set of books" /></span>
</div>
<div id="main">
@ -38,7 +39,7 @@
<div id="loading">
<div>
<img align="top" src="/static/loading.gif" alt="Loading..." title="Loading..."/>&nbsp;<span id="loading_msg">Loading&hellip;</span>
<img align="top" src="{prefix}/static/loading.gif" alt="Loading..." title="Loading..."/>&nbsp;<span id="loading_msg">Loading&hellip;</span>
</div>
</div>

19
resources/content_server/mobile.css
View File

@ -1,5 +1,9 @@
/* CSS for the mobile version of the content server webpage */
.body {
font-family: sans-serif;
}
.navigation table.buttons {
width: 100%;
}
@ -53,6 +57,7 @@ div.navigation {
}
#listing td {
padding: 0.25em;
vertical-align: middle;
}
#listing td.thumbnail {
@ -73,6 +78,7 @@ div.navigation {
overflow: hidden;
text-align: center;
text-decoration: none;
vertical-align: middle;
}
#logo {
@ -83,4 +89,17 @@ div.navigation {
clear: both;
}
.data-container {
display: inline-block;
vertical-align: middle;
}
.first-line {
font-size: larger;
font-weight: bold;
}
.second-line {
margin-top: 0.75ex;
display: block;
}

3385
resources/content_server/read/monocle.js Normal file
View File

File diff suppressed because it is too large Load Diff

35
resources/default_tweaks.py
View File

@ -106,7 +106,8 @@ title_sort_articles=r'^(A|The|An)\s+'
auto_connect_to_folder = ''
# Specify renaming rules for sony collections. Collections on Sonys are named
# Specify renaming rules for sony collections. This tweak is only applicable if
# metadata management is set to automatic. Collections on Sonys are named
# depending upon whether the field is standard or custom. A collection derived
# from a standard field is named for the value in that field. For example, if
# the standard 'series' column contains the name 'Darkover', then the series
@ -137,6 +138,24 @@ auto_connect_to_folder = ''
sony_collection_renaming_rules={}
# Specify how sony collections are sorted. This tweak is only applicable if
# metadata management is set to automatic. You can indicate which metadata is to
# be used to sort on a collection-by-collection basis. The format of the tweak
# is a list of metadata fields from which collections are made, followed by the
# name of the metadata field containing the sort value.
# Example: The following indicates that collections built from pubdate and tags
# are to be sorted by the value in the custom column '#mydate', that collections
# built from 'series' are to be sorted by 'series_index', and that all other
# collections are to be sorted by title. If a collection metadata field is not
# named, then if it is a series- based collection it is sorted by series order,
# otherwise it is sorted by title order.
# [(['pubdate', 'tags'],'#mydate'), (['series'],'series_index'), (['*'], 'title')]
# Note that the bracketing and parentheses are required. The syntax is
# [ ( [list of fields], sort field ) , ( [ list of fields ] , sort field ) ]
# Default: empty (no rules), so no collection attributes are named.
sony_collection_sorting_rules = []
# Create search terms to apply a query across several built-in search terms.
# Syntax: {'new term':['existing term 1', 'term 2', ...], 'new':['old'...] ...}
# Example: create the term 'myseries' that when used as myseries:foo would
@ -184,3 +203,17 @@ content_server_wont_display = ['']
# level sorts, and if you are seeing a slowdown, reduce the value of this tweak.
maximum_resort_levels = 5
# Absolute path to a TTF font file to use as the font for the title and author
# when generating a default cover. Useful if the default font (Liberation
# Serif) does not contain glyphs for the language of the books in your library.
generate_cover_title_font = None
# Absolute path to a TTF font file to use as the font for the footer in the
# default cover
generate_cover_foot_font = None
# Behavior of doubleclick on the books list. Choices:
# open_viewer, do_nothing, edit_cell. Default: open_viewer.
# Example: doubleclick_on_library_view = 'do_nothing'
doubleclick_on_library_view = 'open_viewer'

BIN
resources/images/format-text-bold.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 5.0 KiB

BIN
resources/images/format-text-italic.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 4.1 KiB

BIN
resources/images/format-text-strikethrough.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 5.9 KiB

BIN
resources/images/format-text-underline.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 4.4 KiB

BIN
resources/images/hotmail.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 2.6 KiB

BIN
resources/images/news/avto-magazin.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 1.4 KiB

BIN
resources/images/news/dnevnik.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 861 B

BIN
resources/images/news/perfil.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 781 B

BIN
resources/images/news/rollingstone.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 1.3 KiB

BIN
resources/images/news/siol.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 423 B

BIN
resources/images/news/theecocolapse.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 1.2 KiB

11
resources/jacket/stylesheet.css
View File

@ -39,7 +39,16 @@
.cbj_title {
font-size: x-large;
text-align: center;
}
}
/*
** Author
*/
.cbj_author {
font-size: medium;
text-align: center;
margin-bottom: 1ex;
}
/*
** Table containing Series, Publication Year, Rating and Tags

1
resources/jacket/template.xhtml
View File

@ -7,6 +7,7 @@
<body>
<div class="cbj_banner">
<div class="cbj_title">{title}</div>
<div class="cbj_author">{author}</div>
<table class="cbj_header">
<tr class="cbj_series">
<td class="cbj_label">{series_label}:</td>

8
resources/recipes/atlantic.recipe
View File

@ -71,7 +71,9 @@ class TheAtlantic(BasicNewsRecipe):
for poem in soup.findAll('div', attrs={'class':'poem'}):
title = self.tag_to_string(poem.find('h4'))
desc = self.tag_to_string(poem.find(attrs={'class':'author'}))
url = 'http://www.theatlantic.com'+poem.find('a')['href']
url = poem.find('a')['href']
if url.startswith('/'):
url = 'http://www.theatlantic.com' + url
self.log('\tFound article:', title, 'at', url)
self.log('\t\t', desc)
poems.append({'title':title, 'url':url, 'description':desc,
@ -83,7 +85,9 @@ class TheAtlantic(BasicNewsRecipe):
if div is not None:
self.log('Found section: Advice')
title = self.tag_to_string(div.find('h4'))
url = 'http://www.theatlantic.com'+div.find('a')['href']
url = div.find('a')['href']
if url.startswith('/'):
url = 'http://www.theatlantic.com' + url
desc = self.tag_to_string(div.find('p'))
self.log('\tFound article:', title, 'at', url)
self.log('\t\t', desc)

46
resources/recipes/avto-magazin.recipe Normal file
View File

@ -0,0 +1,46 @@
__license__ = 'GPL v3'
__copyright__ = '2010, BlonG'
'''
avto-magazin.si
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Dnevnik(BasicNewsRecipe):
title = u'Avto Magazin'
__author__ = u'BlonG'
description = u'Za avtomobilisti\xc4\x8dne frike, poznavalce in nedeljske \xc5\xa1oferje.'
oldest_article = 7
max_articles_per_feed = 20
labguage = 'sl'
no_stylesheets = True
use_embedded_content = False
conversion_options = {'linearize_tables' : True}
cover_url = 'https://sites.google.com/site/javno2010/home/avto_magazin_cover.jpg'
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
h2{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''
keep_only_tags = [
dict(name='div', attrs={'id':'_iprom_inStream'}),
# dict(name='div', attrs={'class':'entry-content'}),
]
remove_tags = [
dict(name='div', attrs={'id':'voteConfirmation'}),
dict(name='div', attrs={'id':'InsideVote'}),
dict(name='div', attrs={'class':'Zone234'}),
dict(name='div', attrs={'class':'Comments'}),
dict(name='div', attrs={'class':'sorodneNovice'}),
dict(name='div', attrs={'id':'footer'}),
]
feeds = [
(u'Novice', u'http://www.avto-magazin.si/rss/')
]

43
resources/recipes/calcalist.recipe Normal file
View File

@ -0,0 +1,43 @@
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import re
class AdvancedUserRecipe1283848012(BasicNewsRecipe):
description = 'This is a recipe of Calcalist.co.il. The recipe downloads the article page to not hurt the sites advertising income.'
cover_url = 'http://ftp5.bizportal.co.il/web/giflib/news/calcalist.JPG'
title = u'Calcalist'
language = 'he'
__author__ = 'marbs'
extra_css='img {max-width:100%;} body{direction: rtl;},title{direction: rtl; } ,article_description{direction: rtl; }, a.article{direction: rtl; } ,calibre_feed_description{direction: rtl; }'
simultaneous_downloads = 5
remove_javascript = True
timefmt = '[%a, %d %b, %Y]'
oldest_article = 1
max_articles_per_feed = 100
remove_attributes = ['width']
simultaneous_downloads = 5
keep_only_tags =dict(name='div', attrs={'id':'articleContainer'})
remove_tags = [dict(name='p', attrs={'text':['&nbsp;']})]
max_articles_per_feed = 100
preprocess_regexps = [
(re.compile(r'<p>&nbsp;</p>', re.DOTALL|re.IGNORECASE), lambda match: '')
]
feeds = [(u'\u05d3\u05e3 \u05d4\u05d1\u05d9\u05ea', u'http://www.calcalist.co.il/integration/StoryRss8.xml'),
(u'24/7', u'http://www.calcalist.co.il/integration/StoryRss3674.xml'),
(u'\u05d1\u05d0\u05d6\u05d6', u'http://www.calcalist.co.il/integration/StoryRss3674.xml'),
(u'\u05de\u05d1\u05d6\u05e7\u05d9\u05dd', u'http://www.calcalist.co.il/integration/StoryRss184.xml'),
(u'\u05d4\u05e9\u05d5\u05e7', u'http://www.calcalist.co.il/integration/StoryRss2.xml'),
(u'\u05d1\u05d0\u05e8\u05e5', u'http://www.calcalist.co.il/integration/StoryRss14.xml'),
(u'\u05d4\u05db\u05e1\u05e3', u'http://www.calcalist.co.il/integration/StoryRss9.xml'),
(u'\u05e0\u05d3\u05dc"\u05df', u'http://www.calcalist.co.il/integration/StoryRss7.xml'),
(u'\u05e2\u05d5\u05dc\u05dd', u'http://www.calcalist.co.il/integration/StoryRss13.xml'),
(u'\u05e4\u05e8\u05e1\u05d5\u05dd \u05d5\u05e9\u05d9\u05d5\u05d5\u05e7', u'http://www.calcalist.co.il/integration/StoryRss5.xml'),
(u'\u05e4\u05e0\u05d0\u05d9', u'http://www.calcalist.co.il/integration/StoryRss3.xml'),
(u'\u05d8\u05db\u05e0\u05d5\u05dc\u05d5\u05d2\u05d9', u'http://www.calcalist.co.il/integration/StoryRss4.xml'),
(u'\u05e2\u05e1\u05e7\u05d9 \u05e1\u05e4\u05d5\u05e8\u05d8', u'http://www.calcalist.co.il/integration/StoryRss18.xml')]
def print_version(self, url):
split1 = url.split("-")
print_url = 'http://www.calcalist.co.il/Ext/Comp/ArticleLayout/CdaArticlePrintPreview/1,2506,L-' + split1[1]
return print_url

50
resources/recipes/clic_rbs.recipe Normal file
View File

@ -0,0 +1,50 @@
from calibre.web.feeds.news import BasicNewsRecipe
class ClicRBS(BasicNewsRecipe):
title = u'ClicRBS'
language = 'pt'
__author__ = 'arvoredo'
oldest_article = 3
max_articles_per_feed = 9
cover_url = 'http://www.publicidade.clicrbs.com.br/clicrbs/imgs/logo_clic.gif'
remove_tags = [
dict(name='div', attrs={'class':['clic-barra-inner', 'botao-versao-mobile ']})
]
remove_tags_before = dict(name='div ', attrs={'class':'descricao'})
remove_tags_before = dict(name='div', attrs={'id':'glb-corpo'})
remove_tags_before = dict(name='div', attrs={'class':'descricao'})
remove_tags_before = dict(name='div', attrs={'class':'coluna'})
remove_tags_after = dict(name='div', attrs={'class':'extra'})
remove_tags_after = dict(name='div', attrs={'id':'links-patrocinados'})
remove_tags_after = dict(name='h4', attrs={'class':'tipo-c comente'})
remove_tags_after = dict(name='ul', attrs={'class':'lista'})
feeds = [
(u'zerohora.com, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?uf=1&local=1&channel=13')
, (u'diariocatarinense.com, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?uf=2&local=18&channel=67')
, (u'Concursos e Emprego', u'http://g1.globo.com/Rss2/0,,AS0-9654,00.xml')
, (u'Pioneiro.com, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?channel=87&uf=1&local=1')
, (u'Economia, zerohora.com, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?sect_id=801&uf=1&local=1&channel=13')
, (u'Esportes, zerohora.com, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?sect_id=802&uf=1&local=1&channel=13')
, (u'Economia, Pioneiro.com, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?sect_id=1180&channel=87&uf=1&local=1')
, (u'Política, Pioneiro.com, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?sect_id=1185&channel=87&uf=1&local=1')
, (u'Mundo, Pioneiro.com, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?sect_id=1184&channel=87&uf=1&local=1')
, (u'Catarinense, Esportes, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?sect_id=&theme=371&uf=2&channel=2')
, (u'Geral, Pioneiro.com, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?sect_id=1183&channel=87&uf=1&local=1')
, (u'Estilo de Vida, zerohora.com, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?sect_id=805&uf=1&local=1&channel=13')
, (u'Corrida, Corrida, Esportes, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?sect_id=1313&theme=15704&uf=1&channel=2')
, (u'Jornal de Santa Catarina, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?espid=159&uf=2&local=18')
, (u'Grêmio, Futebol, Esportes, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?sect_id=11&theme=65&uf=1&channel=2')
, (u'Velocidade, Esportes, clicRBS', u'http://www.clicrbs.com.br/jsp/rssfeed.jspx?sect_id=1314&theme=2655&uf=1&channel=2')
]
extra_css = '''
cite{color:#007BB5; font-size:xx-small; font-style:italic;}
body{font-family:Arial,Helvetica,sans-serif;font-size:x-small;}
h3{font-size:large; color:#082963; font-weight:bold;}
#ident{color:#0179B4; font-size:xx-small;}
p{color:#000000;font-weight:normal;}
.commentario p{color:#007BB5; font-style:italic;}
'''

44
resources/recipes/cm_journal.recipe Normal file
View File

@ -0,0 +1,44 @@
from calibre.web.feeds.news import BasicNewsRecipe
class CMJornal_pt(BasicNewsRecipe):
title = 'Correio da Manha - Portugal'
__author__ = 'jmst'
description = 'As noticias de Portugal e do Mundo'
publisher = 'Cofina Media'
category = ''
oldest_article = 1
no_stylesheets = True
encoding = 'utf-8'
use_embedded_content = False
language = 'pt'
extra_css = ' .publish{font-style: italic; line-height: 1.2em; border-bottom: 1px dotted; padding: 5px 0} .entity{line-height: 1.2em} .overview{line-height:1.2em} '
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags = [
dict(name=['h2','h1'])
, dict(name='div', attrs={'class': ['news']})
]
remove_tags = [
dict(name=['object','embed','iframe'])
,dict(name='a',attrs={'href':['#']})
]
feeds = [
(u'Actualidade' , u'http://www.cmjornal.xl.pt/rss/rss.aspx?channelID=00000009-0000-0000-0000-000000000009' )
,(u'Portugal' , u'http://www.cmjornal.xl.pt/rss/rss.aspx?channelID=00000010-0000-0000-0000-000000000010' )
,(u'Economia' , u'http://www.cmjornal.xl.pt/rss/rss.aspx?channelID=00000011-0000-0000-0000-000000000011' )
,(u'Mundo' , u'http://www.cmjornal.xl.pt/rss/rss.aspx?channelID=00000091-0000-0000-0000-000000000091' )
,(u'Desporto' , u'http://www.cmjornal.xl.pt/rss/rss.aspx?channelID=00000012-0000-0000-0000-000000000012' )
,(u'TV & Media', u'http://www.cmjornal.xl.pt/rss/rss.aspx?channelID=00000092-0000-0000-0000-000000000092')
]
def print_version(self, url):
return url.replace('noticia.aspx', 'Imprimir.aspx')

32
resources/recipes/cubadebate.recipe
View File

@ -1,9 +1,7 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
'''
newyorker.com
cubadebate.cu
'''
from calibre.web.feeds.news import BasicNewsRecipe
@ -13,32 +11,44 @@ class CubaDebate(BasicNewsRecipe):
__author__ = 'Darko Miletic'
description = 'Contra el Terorismo Mediatico'
oldest_article = 15
language = 'es'
language = 'es'
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
publisher = 'Cubadebate'
category = 'news, politics, Cuba'
encoding = 'utf-8'
extra_css = ' #BlogTitle{font-size: x-large; font-weight: bold} '
masthead_url = 'http://www.cubadebate.cu/wp-content/themes/cubadebate/images/logo.gif'
publication_type = 'newsportal'
extra_css = """
#BlogTitle{font-size: xx-large; font-weight: bold}
body{font-family: Verdana, Arial, Tahoma, sans-serif}
"""
conversion_options = {
'comments' : description
,'tags' : category
,'language' : 'es'
,'language' : language
,'publisher' : publisher
,'pretty_print': True
}
keep_only_tags = [dict(name='div', attrs={'id':'Outline'})]
remove_tags_after = dict(name='div',attrs={'id':'BlogContent'})
remove_tags = [dict(name='link')]
remove_tags = [
dict(name=['link','base','embed','object','meta','iframe'])
,dict(attrs={'id':'addthis_container'})
]
feeds = [(u'Articulos', u'http://www.cubadebate.cu/feed/')]
remove_attributes=['width','height','lang']
def print_version(self, url):
return url + 'print/'
def preprocess_html(self, soup):
return self.adeify_images(soup)
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll('img'):
if not item.has_key('alt'):
item['alt'] = 'image'
return soup

7
resources/recipes/danas.recipe
View File

@ -25,7 +25,7 @@ class Danas(BasicNewsRecipe):
remove_empty_feeds = True
extra_css = """ @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)}
@font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)}
.article_description,body,.lokacija{font-family: Tahoma,Arial,Helvetica,sans1,sans-serif}
.article,.articledescription,body,.lokacija,.feed{font-family: Tahoma,Arial,Helvetica,sans1,sans-serif}
.nadNaslov,h1,.preamble{font-family: Georgia,"Times New Roman",Times,serif1,serif}
.antrfileText{border-left: 2px solid #999999;
margin-left: 0.8em;
@ -59,11 +59,14 @@ class Danas(BasicNewsRecipe):
,(re.compile(u'\u201d'), lambda match: '&rdquo;') # right double quotation mark
,(re.compile(u'\u201e'), lambda match: '&ldquo;') # double low-9 quotation mark
,(re.compile(u'\u201f'), lambda match: '&rdquo;') # double high-reversed-9 quotation mark
,(re.compile(u'\u00f4'), lambda match: '&ldquo;') # latin small letter o with circumflex
,(re.compile(u'\u00f6'), lambda match: '&rdquo;') # latin small letter o with dieaeresis
,(re.compile(u'\u00e1'), lambda match: '&nbsp;' ) # latin small letter a with acute
]
keep_only_tags = [dict(name='div', attrs={'id':'left'})]
remove_tags = [
dict(name='div', attrs={'class':['width_1_4','metaClanka','baner']})
dict(name='div', attrs={'class':['width_1_4','metaClanka','baner','listaVesti','article_nav']})
,dict(name='div', attrs={'id':'comments'})
,dict(name=['object','link','iframe','meta'])
]

61
resources/recipes/deredactie.recipe Normal file
View File

@ -0,0 +1,61 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
class deredactie(BasicNewsRecipe):
title = u'Deredactie.be'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
cover_url = 'http://www.deredactie.be/polopoly_fs/1.510827!image/2710428628.gif'
language = 'de'
keep_only_tags = []
__author__ = 'malfi'
keep_only_tags.append(dict(name = 'div', attrs = {'id': 'articlehead'}))
keep_only_tags.append(dict(name = 'div', attrs = {'id': 'articlebody'}))
remove_tags = []
remove_tags.append(dict(name = 'div', attrs = {'id': 'story'}))
remove_tags.append(dict(name = 'div', attrs = {'id': 'useractions'}))
remove_tags.append(dict(name = 'hr'))
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''
def parse_index(self):
categories = []
catnames = {}
soup = self.index_to_soup('http://www.deredactie.be/cm/vrtnieuws.deutsch')
for elem in soup.findAll('li', attrs={'id' : re.compile("^navItem[2-9]") }):
a = elem.find('a', href=True)
m = re.search('(?<=/)[^/]*$', a['href'])
cat = str(m.group(0))
categories.append(cat)
catnames[cat] = a['title']
self.log("found cat %s\n" % catnames[cat])
feeds = []
for cat in categories:
articles = []
soup = self.index_to_soup('http://www.deredactie.be/cm/vrtnieuws.deutsch/'+cat)
for a in soup.findAll('a',attrs={'href' : re.compile("deutsch.*/[0-9][0-9][0-9][0-9][0-9][0-9]_")}):
skip_this_article = False
url = a['href'].strip()
if url.startswith('/'):
url = 'http://www.deredactie.be' + url
myarticle=({'title':self.tag_to_string(a), 'url':url, 'description':'', 'date':''})
for article in articles :
if article['url'] == url :
skip_this_article = True
self.log("SKIPPING DUP %s" % url)
break
if skip_this_article :
continue;
articles.append(myarticle)
self.log("Adding URL %s\n" %url)
if articles:
feeds.append((catnames[cat], articles))
return feeds

42
resources/recipes/diario_sport.recipe Normal file
View File

@ -0,0 +1,42 @@
from calibre.web.feeds.news import BasicNewsRecipe
class DiarioSport(BasicNewsRecipe):
title = u'Diario Sport'
oldest_article = 2
max_articles_per_feed = 75
__author__ = 'Jefferson Frantz'
description = 'Todas las noticias del Barça y del mundo del deporte en general'
timefmt = ' [%d %b, %Y]'
language = 'es'
no_stylesheets = True
feeds = [(u'Sport', u'http://feeds.feedburner.com/sport/ultimahora')]
extra_css = '''
h2{font-family: serif; font-size: small; font-weight: bold; color: #000000; text-align: justify}
'''
keep_only_tags = [dict(name='div', attrs={'id':['noticiasMedio']})]
remove_tags = [
dict(name=['object','link','script','ul'])
,dict(name='div', attrs={'id':['scrAdSense','herramientas2','participacion','participacion2','bloque1resultados','bloque2resultados','cont_vinyetesAnt','tinta','noticiasSuperior','cintillopublicidad2']})
,dict(name='p', attrs={'class':['masinformacion','hora']})
,dict(name='a', attrs={'class':["'link'"]})
,dict(name='div', attrs={'class':['addthis_toolbox addthis_default_style','firma','pretitularnoticia']})
,dict(name='form', attrs={'id':['formularioDeBusquedaAvanzada']})
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup
def postprocess_html(self, soup, first_fetch):
img = soup.find('img',src='/img/videos/mascaravideo.png')
if not img is None:
img.extract()
return soup

63
resources/recipes/dnevnik.recipe Normal file
View File

@ -0,0 +1,63 @@
__license__ = 'GPL v3'
__copyright__ = '2010, BlonG'
'''
dnevnik.si
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Dnevnik(BasicNewsRecipe):
title = u'Dnevnik.si'
__author__ = u'BlonG'
description = u'''Dnevnik je \u010dasnik z ve\u010d kot polstoletno zgodovino.
Pod sloganom \xbb\u017divljenje ima besedo\xab na svojih straneh prina\u0161a
bralcem bogastvo informacij, komentarjev in kolumen in raznovrstnost
pogledov, zaznamovanih z odgovornostjo do posameznika in \u0161ir\u0161e
dru\u017ebe.'''
oldest_article = 3
max_articles_per_feed = 20
language = 'sl'
no_stylesheets = True
use_embedded_content = False
cover_url = 'https://sites.google.com/site/javno2010/home/dnevnik_cover.jpg'
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''
keep_only_tags = [
dict(name='div', attrs={'id':'_iprom_inStream'}),
dict(name='div', attrs={'class':'entry-content'}),
]
remove_tags = [
dict(name='div', attrs={'class':'fb_article_top'}),
dict(name='div', attrs={'class':'related'}),
dict(name='div', attrs={'class':'fb_article_foot'}),
dict(name='div', attrs={'class':'spreading'}),
dict(name='dl', attrs={'class':'ad'}),
dict(name='p', attrs={'class':'report'}),
dict(name='div', attrs={'class':'hfeed comments'}),
dict(name='dl', attrs={'id':'entryPanel'}),
dict(name='dl', attrs={'class':'infopush ip_wide'}),
dict(name='div', attrs={'class':'sidebar'}),
dict(name='dl', attrs={'class':'bottom'}),
dict(name='div', attrs={'id':'footer'}),
]
feeds = [
(u'Slovenija', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=13')
,(u'Svet', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=14')
,(u'EU', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=116')
,(u'Poslovni dnevnik', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=5')
,(u'Kronika', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=15')
,(u'Kultura', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=17')
,(u'Zdravje', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=18')
,(u'Znanost in IT', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=19')
,(u'(Ne)verjetno', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=20')
,(u'E-strada', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=21')
,(u'Svet vozil', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=22')
]

77
resources/recipes/el_faro.recipe Normal file
View File

@ -0,0 +1,77 @@
from calibre.web.feeds.news import BasicNewsRecipe
class ElFaroDeVigo(BasicNewsRecipe):
title = u'El Faro de Vigo'
oldest_article = 1
max_articles_per_feed = 100
__author__ = 'Jefferson Frantz'
description = 'Noticias de Vigo'
timefmt = ' [%d %b, %Y]'
language = 'es'
encoding = 'cp1252'
no_stylesheets = True
remove_javascript = True
feeds = [
## (u'Vigo', u'http://www.farodevigo.es/elementosInt/rss/1'),
## (u'Gran Vigo', u'http://www.farodevigo.es/elementosInt/rss/2'),
(u'Galicia', u'http://www.farodevigo.es/elementosInt/rss/4'),
(u'España', u'http://www.farodevigo.es/elementosInt/rss/6'),
(u'Mundo', u'http://www.farodevigo.es/elementosInt/rss/7'),
## (u'Opinión', u'http://www.farodevigo.es/elementosInt/rss/5'),
(u'Economía', u'http://www.farodevigo.es/elementosInt/rss/10'),
(u'Sociedad y Cultura', u'http://www.farodevigo.es/elementosInt/rss/8'),
(u'Sucesos', u'http://www.farodevigo.es/elementosInt/rss/9'),
(u'Deportes', u'http://www.farodevigo.es/elementosInt/rss/11'),
(u'Agenda', u'http://www.farodevigo.es/elementosInt/rss/21'),
(u'Gente', u'http://www.farodevigo.es/elementosInt/rss/24'),
(u'Televisión', u'http://www.farodevigo.es/elementosInt/rss/25'),
(u'Ciencia y Tecnología', u'http://www.farodevigo.es/elementosInt/rss/26')]
extra_css = '''.noticia_texto{ font-family: sans-serif; font-size: medium; text-align: justify }
h1{font-family: serif; font-size: x-large; font-weight: bold; color: #000000; text-align: center}
h2{font-family: serif; font-size: medium; font-weight: bold; color: #000000; text-align: left}
.enlacenegrita10{font-family: serif; font-size: small; font-weight: bold; color: #000000; text-align: left}
.noticia_titular{font-family: serif; font-size: x-large; font-weight: bold; color: #000000; text-align: center}'''
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
url = 'http://estaticos00.farodevigo.es//elementosWeb/mediaweb/images/compartir/barrapunto.gif'
fitem = soup.find('img',src=url)
if fitem:
par = fitem.parent
par.extract()
url = 'http://estaticos01.farodevigo.es//elementosWeb/mediaweb/images/compartir/barrapunto.gif'
fitem = soup.find('img',src=url)
if fitem:
par = fitem.parent
par.extract()
url = 'http://estaticos02.farodevigo.es//elementosWeb/mediaweb/images/compartir/barrapunto.gif'
fitem = soup.find('img',src=url)
if fitem:
par = fitem.parent
par.extract()
return self.adeify_images(soup)
def postprocess_html(self, soup, first_fetch):
divs = soup.findAll(True, {'class':'enlacenegrita10'})
for div in divs:
div['align'] = 'left'
return soup
keep_only_tags = [dict(name='div', attrs={'class':['noticias']})]
remove_tags = [
dict(name=['object','link','script','ul','iframe','ol'])
,dict(name='div', attrs={'class':['noticiadd2', 'cintillo2', 'noticiadd', 'noticiadd2']})
,dict(name='div', attrs={'class':['imagen_derecha', 'noticiadd3', 'extraHTML']})
]

13
resources/recipes/el_pais.recipe
View File

@ -2,7 +2,7 @@
__license__ = 'GPL v3'
__author__ = 'Jordi Balcells, based on an earlier version by Lorenzo Vigentini & Kovid Goyal'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
description = 'Main daily newspaper from Spain - v1.03 (03, September 2010)'
description = 'Main daily newspaper from Spain - v1.04 (19, October 2010)'
__docformat__ = 'restructuredtext en'
'''
@ -32,19 +32,16 @@ class ElPais(BasicNewsRecipe):
remove_javascript = True
no_stylesheets = True
keep_only_tags = [ dict(name='div', attrs={'class':['cabecera_noticia','cabecera_noticia_reportaje','cabecera_noticia_opinion','contenido_noticia','caja_despiece','presentacion']})]
keep_only_tags = [ dict(name='div', attrs={'class':['cabecera_noticia_reportaje estirar','cabecera_noticia_opinion estirar','cabecera_noticia estirar','contenido_noticia','caja_despiece']})]
extra_css = '''
p{style:normal size:12 serif}
'''
extra_css = ' p{text-align: justify; font-size: 100%} body{ text-align: left; font-family: serif; font-size: 100% } h1{ font-family: sans-serif; font-size:200%; font-weight: bolder; text-align: justify; } h2{ font-family: sans-serif; font-size:150%; font-weight: 500; text-align: justify } h3{ font-family: sans-serif; font-size:125%; font-weight: 500; text-align: justify } img{margin-bottom: 0.4em} '
remove_tags = [
dict(name='div', attrs={'class':['zona_superior','pie_enlaces_inferiores','contorno_f','ampliar']}),
dict(name='div', attrs={'class':['limpiar','mod_apoyo','borde_sup','votos','info_complementa','info_relacionada','buscador_m','nav_ant_sig']}),
dict(name='div', attrs={'class':['limpiar','mod_apoyo','borde_sup','votos estirar','info_complementa','info_relacionada','buscador_m','nav_ant_sig']}),
dict(name='div', attrs={'id':['suscribirse suscrito','google_noticia','utilidades','coment','foros_not','pie','lomas','calendar']}),
dict(name='p', attrs={'class':'nav_meses'}),
dict(attrs={'class':['enlaces_m','miniaturas_m']})
dict(attrs={'class':['enlaces_m','miniaturas_m','nav_miniaturas_m']})
]
feeds = [

38
resources/recipes/elektrolese.recipe
View File

@ -1,38 +0,0 @@
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
'''
Fetch elektrolese.
'''
from calibre.web.feeds.news import BasicNewsRecipe
class elektrolese(BasicNewsRecipe):
title = u'elektrolese'
description = 'News about electronic publishing'
__author__ = 'Oliver Niesner'
use_embedded_content = False
timefmt = ' [%a %d %b %Y]'
language = 'de'
oldest_article = 14
max_articles_per_feed = 50
no_stylesheets = True
conversion_options = {'linearize_tables':True}
encoding = 'utf-8'
remove_tags_after = [dict(id='comments')]
filter_regexps = [r'ad\.doubleclick\.net']
remove_tags = [dict(name='div', attrs={'class':'bannerSuperBanner'}),
dict(id='comments'),
dict(id='Navbar1')]
feeds = [ (u'elektrolese', u'http://elektrolese.blogspot.com/feeds/posts/default?alt=rss') ]

28
resources/recipes/elperiodico_catalan.recipe
View File

@ -2,7 +2,7 @@
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '30 October 2010, Jordi Balcells based on an earlier recipe by Darko Miletic <darko.miletic at gmail.com>'
'''
elperiodico.cat
'''
@ -12,8 +12,8 @@ from calibre.ebooks.BeautifulSoup import Tag
class ElPeriodico_cat(BasicNewsRecipe):
title = 'El Periodico de Catalunya'
__author__ = 'Darko Miletic'
description = 'Noticias desde Catalunya'
__author__ = 'Jordi Balcells/Darko Miletic'
description = 'Noticies des de Catalunya'
publisher = 'elperiodico.cat'
category = 'news, politics, Spain, Catalunya'
oldest_article = 2
@ -33,15 +33,25 @@ class ElPeriodico_cat(BasicNewsRecipe):
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
feeds = [(u"Tota l'edició", u'http://www.elperiodico.cat/rss.asp?id=46')]
feeds = [(u'Portada', u'http://www.elperiodico.cat/ca/rss/rss_portada.xml'),
(u'Internacional', u'http://www.elperiodico.cat/ca/rss/internacional/rss.xml'),
(u'Societat', u'http://www.elperiodico.cat/ca/rss/societat/rss.xml'),
(u'Ci\xe8ncia i tecnologia', u'http://www.elperiodico.cat/ca/rss/ciencia-i-tecnologia/rss.xml'),
(u'Esports', u'http://www.elperiodico.cat/ca/rss/esports/rss.xml'),
(u'Gent', u'http://www.elperiodico.cat/ca/rss/gent/rss.xml'),
(u'Opini\xf3', u'http://www.elperiodico.cat/ca/rss/opinio/rss.xml'),
(u'Pol\xedtica', u'http://www.elperiodico.cat/ca/rss/politica/rss.xml'),
(u'Barcelona', u'http://www.elperiodico.cat/ca/rss/barcelona/rss.xml'),
(u'Economia', u'http://www.elperiodico.cat/ca/rss/economia/rss.xml'),
(u'Cultura i espectacles', u'http://www.elperiodico.cat/ca/rss/cultura-i-espectacles/rss.xml'),
(u'Tele', u'http://www.elperiodico.cat/ca/rss/tele/rss.xml')]
keep_only_tags = [dict(name='div', attrs={'id':'noticia'})]
keep_only_tags = [dict(name='div', attrs={'class':'titularnoticia'}),
dict(name='div', attrs={'class':'noticia_completa'})]
remove_tags = [
dict(name=['object','link','script'])
,dict(name='ul',attrs={'class':'herramientasDeNoticia'})
,dict(name='div', attrs={'id':'inferiores'})
remove_tags = [dict(name='div', attrs={'class':['opcionb','opcionb last','columna_noticia']}),
dict(name='span', attrs={'class':'opcionesnoticia'})
]
def print_version(self, url):

30
resources/recipes/elperiodico_spanish.recipe
View File

@ -2,17 +2,17 @@
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '30 October 2010, Jordi Balcells based on an earlier recipe by Darko Miletic <darko.miletic at gmail.com>'
'''
elperiodico.com
elperiodico.cat
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class ElPeriodico_esp(BasicNewsRecipe):
class ElPeriodico_cat(BasicNewsRecipe):
title = 'El Periodico de Catalunya'
__author__ = 'Darko Miletic'
__author__ = 'Jordi Balcells/Darko Miletic'
description = 'Noticias desde Catalunya'
publisher = 'elperiodico.com'
category = 'news, politics, Spain, Catalunya'
@ -33,15 +33,25 @@ class ElPeriodico_esp(BasicNewsRecipe):
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
feeds = [(u"Toda la edición", u'http://www.elperiodico.com/rss.asp?id=46')]
feeds = [(u'Portada', u'http://www.elperiodico.com/es/rss/rss_portada.xml'),
(u'Internacional', u'http://elperiodico.com/es/rss/internacional/rss.xml'),
(u'Sociedad', u'http://elperiodico.com/es/rss/sociedad/rss.xml'),
(u'Ciencia y Tecnolog\xeda', u'http://elperiodico.com/es/rss/ciencia-y-tecnologia/rss.xml'),
(u'Deportes', u'http://elperiodico.com/es/rss/deportes/rss.xml'),
(u'Gente', u'http://elperiodico.com/es/rss/gente/rss.xml'),
(u'Opini\xf3n', u'http://elperiodico.com/es/rss/opinion/rss.xml'),
(u'Pol\xedtica', u'http://elperiodico.com/es/rss/politica/rss.xml'),
(u'Barcelona', u'http://elperiodico.com/es/rss/barcelona/rss.xml'),
(u'Econom\xeda', u'http://elperiodico.com/es/rss/economia/rss.xml'),
(u'Cultura y espect\xe1culos', u'http://elperiodico.com/es/rss/cultura-y-espectaculos/rss.xml'),
(u'Tele', u'http://elperiodico.com/es/rss/cultura-y-espectaculos/rss.xml')]
keep_only_tags = [dict(name='div', attrs={'id':'noticia'})]
keep_only_tags = [dict(name='div', attrs={'class':'titularnoticia'}),
dict(name='div', attrs={'class':'noticia_completa'})]
remove_tags = [
dict(name=['object','link','script'])
,dict(name='ul',attrs={'class':'herramientasDeNoticia'})
,dict(name='div', attrs={'id':'inferiores'})
remove_tags = [dict(name='div', attrs={'class':['opcionb','opcionb last','columna_noticia']}),
dict(name='span', attrs={'class':'opcionesnoticia'})
]
def print_version(self, url):

58
resources/recipes/eu_commission.recipe Normal file
View File

@ -0,0 +1,58 @@
from calibre.web.feeds.news import BasicNewsRecipe
LANGUAGE = 'de'
def feedlink(num):
return u'http://europa.eu/rapid/syndication/QuickRSSAction.do?id='+\
str(num)+'&lang='+ LANGUAGE
class EUCommissionPress(BasicNewsRecipe):
title = u'Pressemitteilungen der EU Kommission pro Politikbereich'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
cover_url = 'http://ec.europa.eu/wel/template_2007/images/banners/banner-background.jpg'
__author__ = 'malfi'
language = LANGUAGE
keep_only_tags = []
keep_only_tags.append(dict(name = 'div', attrs = {'class': 'pressReleaseContentMain'}))
remove_tags = []
feeds = [
(u'Pressemitteilung des Tages',feedlink(64)),
(u'Presidency',feedlink(137)),
(u'Foreign affairs and security policy',feedlink(138)),
(u'Agriculture and rural development',feedlink(139)),
(u'Budget and financial programming ',feedlink(140)),
(u'Climate action',feedlink(141)),
(u'Competition',feedlink(142)),
(u'Development',feedlink(143)),
(u'Digital agenda',feedlink(144)),
(u'Economic and monetary affairs',feedlink(145)),
(u'Education, culture, multilingualism and youth ',feedlink(146)),
(u'Employment, social Affairs and inclusion ',feedlink(147)),
(u'Energy',feedlink(148)),
(u'Enlargment and European neighbourhood policy ',feedlink(149)),
(u'Environment',feedlink(150)),
(u'Health and consumer policy',feedlink(151)),
(u'Home affairs',feedlink(152)),
(u'Industry and entrepreneurship',feedlink(153)),
(u'Inter-Institutional relations and administration',feedlink(154)),
(u'Internal market and services',feedlink(155)),
(u'International cooperation, humanitarian aid and crisis response',feedlink(156)),
(u'Justice, fundamental rights and citizenship',feedlink(157)),
(u'Maritime affairs and fisheries',feedlink(158)),
(u'Regional policy',feedlink(159)),
(u'Research and innovation',feedlink(160)),
(u'Taxation and customs union, audit and anti-fraud',feedlink(161)),
(u'Trade',feedlink(162)),
(u'Transport',feedlink(163))
]
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''

51
resources/recipes/european_voice.recipe Normal file
View File

@ -0,0 +1,51 @@
from calibre.web.feeds.news import BasicNewsRecipe
class EuropeanVoice(BasicNewsRecipe):
title = u'European Voice'
__author__ = 'malfi'
oldest_article = 14
max_articles_per_feed = 100
no_stylesheets = True
cover_url = 'http://www.europeanvoice.com/Css/images/logo.gif'
language = 'en'
keep_only_tags = [dict(name='div', attrs={'id':'articleLeftColumn'})]
remove_tags = [dict(name='div', attrs={'id':'BreadCrump'})]
feeds = [
(u'Whole site ',u'http://www.europeanvoice.com/Rss/2.xml'),
(u'News and analysis',u'http://www.europeanvoice.com/Rss/6.xml'),
(u'Comment',u'http://www.europeanvoice.com/Rss/7.xml'),
(u'Special reports',u'http://www.europeanvoice.com/Rss/5.xml'),
(u'People',u'http://www.europeanvoice.com/Rss/8.xml'),
(u'Career',u'http://www.europeanvoice.com/Rss/11.xml'),
(u'Policies',u'http://www.europeanvoice.com/Rss/4.xml'),
(u'EVents',u'http://www.europeanvoice.com/Rss/10.xml'),
(u'Policies - Economics',u'http://www.europeanvoice.com/Rss/31.xml'),
(u'Policies - Business',u'http://www.europeanvoice.com/Rss/19.xml'),
(u'Policies - Trade',u'http://www.europeanvoice.com/Rss/25.xml'),
(u'Policies - Information society',u'http://www.europeanvoice.com/Rss/20.xml'),
(u'Policies - Energy',u'http://www.europeanvoice.com/Rss/15.xml'),
(u'Policies - Transport',u'http://www.europeanvoice.com/Rss/18.xml'),
(u'Policies - Climate change',u'http://www.europeanvoice.com/Rss/16.xml'),
(u'Policies - Environment',u'http://www.europeanvoice.com/Rss/17.xml'),
(u'Policies - Farming & food',u'http://www.europeanvoice.com/Rss/23.xml'),
(u'Policies - Health & society',u'http://www.europeanvoice.com/Rss/24.xml'),
(u'Policies - Justice',u'http://www.europeanvoice.com/Rss/29.xml'),
(u'Policies - Foreign affairs',u'http://www.europeanvoice.com/Rss/27.xml')
]
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''
def print_version(self, url):
return url + '?bPrint=1'
def preprocess_html(self, soup):
denied = soup.findAll(True,text='Subscribers')
if denied:
raise Exception('Article skipped, because content can only be seen with subscription')
return soup

39
resources/recipes/foxnews.recipe
View File

@ -4,7 +4,6 @@ __copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
foxnews.com
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class FoxNews(BasicNewsRecipe):
@ -21,11 +20,10 @@ class FoxNews(BasicNewsRecipe):
language = 'en'
publication_type = 'newsportal'
remove_empty_feeds = True
extra_css = ' body{font-family: Arial,sans-serif } img{margin-bottom: 0.4em} .caption{font-size: x-small} '
preprocess_regexps = [
(re.compile(r'</title>.*?</head>', re.DOTALL|re.IGNORECASE),lambda match: '</title></head>')
]
extra_css = """
body{font-family: Arial,sans-serif }
.caption{font-size: x-small}
"""
conversion_options = {
'comment' : description
@ -34,27 +32,15 @@ class FoxNews(BasicNewsRecipe):
, 'language' : language
}
remove_attributes = ['xmlns']
keep_only_tags = [
dict(name='div', attrs={'id' :['story','browse-story-content']})
,dict(name='div', attrs={'class':['posts articles','slideshow']})
,dict(name='h4' , attrs={'class':'storyDate'})
,dict(name='h1' , attrs={'xmlns:functx':'http://www.functx.com'})
,dict(name='div', attrs={'class':'authInfo'})
,dict(name='div', attrs={'id':'articleCont'})
]
remove_attributes = ['xmlns','lang']
remove_tags = [
dict(name='div', attrs={'class':['share-links','quigo quigo2','share-text','storyControls','socShare','btm-links']})
,dict(name='div', attrs={'id' :['otherMedia','loomia_display','img-all-path','story-vcmId','story-url','pane-browse-story-comments','story_related']})
,dict(name='ul' , attrs={'class':['tools','tools alt','tools alt2','tabs']})
,dict(name='a' , attrs={'class':'join-discussion'})
,dict(name='ul' , attrs={'class':['tools','tools alt','tools alt2']})
,dict(name='p' , attrs={'class':'see_fullarchive'})
,dict(name=['object','embed','link','script'])
dict(name=['object','embed','link','script','iframe','meta','base'])
,dict(attrs={'class':['user-control','url-description','ad-context']})
]
remove_tags_before=dict(name='h1')
remove_tags_after =dict(attrs={'class':'url-description'})
feeds = [
(u'Latest Headlines', u'http://feeds.foxnews.com/foxnews/latest' )
@ -67,8 +53,5 @@ class FoxNews(BasicNewsRecipe):
,(u'Entertainment' , u'http://feeds.foxnews.com/foxnews/entertainment' )
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return self.adeify_images(soup)
def print_version(self, url):
return url + 'print'

2
resources/recipes/fudzilla.recipe
View File

@ -33,7 +33,7 @@ class Fudzilla(BasicNewsRecipe):
]
feeds = [
(u'Posts', u'http://www.fudzilla.com/index.php?option=com_rss&feed=RSS2.0&no_html=1')
(u'Posts', u'http://www.fudzilla.com/?format=feed')
]
preprocess_regexps = [

40
resources/recipes/gamespot.recipe Normal file
View File

@ -0,0 +1,40 @@
__license__ = 'GPL v3'
__author__ = u'Marc Toensing'
from calibre.web.feeds.news import BasicNewsRecipe
class GamespotCom(BasicNewsRecipe):
title = u'Gamespot.com Reviews'
description = 'review articles from gamespot.com'
language = 'en'
__author__ = u'Marc T\xf6nsing'
oldest_article = 7
max_articles_per_feed = 40
remove_empty_feeds = True
no_stylesheets = True
no_javascript = True
feeds = [
('All Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5'),
('PC Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5&platform=5'),
('XBOX 360 Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5&platform=1029'),
('Wii Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5&platform=1031'),
('PlayStation 3 Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5&platform=1028'),
('PlayStation 2 Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5&platform=7'),
('PlayStation Portable Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5&platform=1024'),
('Nintendo DS Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5&platform=1026'),
('iPhone Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5&platform=1049'),
]
remove_tags = [
dict(name='div', attrs={'class':'top_bar'}),
dict(name='div', attrs={'class':'video_embed'})
]
def get_cover_url(self):
return 'http://image.gamespotcdn.net/gamespot/shared/gs5/gslogo_bw.gif'
def get_article_url(self, article):
return article.get('link') + '?print=1'

28
resources/recipes/german_gov.recipe Normal file
View File

@ -0,0 +1,28 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
class GermanGovermentPress(BasicNewsRecipe):
title = u'Pressemitteilungen der Bundesregierung'
oldest_article = 14
__author__ = 'malfi'
max_articles_per_feed = 100
no_stylesheets = True
cover_url = 'http://www.bundesregierung.de/static/images/logoBR.gif'
language = 'de'
keep_only_tags = []
keep_only_tags.append(dict(name = 'h2'))
keep_only_tags.append(dict(name = 'div', attrs = {'class': 'textblack'}))
keep_only_tags.append(dict(name = 'div', attrs = {'class': 'subtitle'}))
keep_only_tags.append(dict(name = 'div', attrs = {'class': 'text'}))
remove_tags = []
feeds = [ (u'Pressemitteilungen',u'http://www.bundesregierung.de/Webs/Breg/DE/Service/RSS/Functions/bundesregierungPressemitteilungenRSS20,templateId=renderNewsfeed.rdf') ]
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''
def print_version(self, url):
m = re.search(r'^(.*).html$', url)
return str(m.group(1)) + ',layoutVariant=Druckansicht.html'

89
resources/recipes/globe_and_mail.recipe
View File

@ -1,7 +1,7 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__copyright__ = '2010, Szing'
__docformat__ = 'restructuredtext en'
'''
@ -10,49 +10,52 @@ globeandmail.com
from calibre.web.feeds.news import BasicNewsRecipe
class GlobeAndMail(BasicNewsRecipe):
title = u'Globe and Mail'
language = 'en_CA'
__author__ = 'Kovid Goyal'
class AdvancedUserRecipe1287083651(BasicNewsRecipe):
title = u'Globe & Mail'
__license__ = 'GPL v3'
__author__ = 'Szing'
oldest_article = 2
max_articles_per_feed = 10
no_stylesheets = True
extra_css = '''
h3 {font-size: 22pt; font-weight:bold; margin:0px; padding:0px 0px 8pt 0px;}
h4 {margin-top: 0px;}
#byline { font-family: monospace; font-weight:bold; }
#placeline {font-weight:bold;}
#credit {margin-top:0px;}
.tag {font-size: 22pt;}'''
description = 'Canada\'s national newspaper'
keep_only_tags = [dict(name='article')]
remove_tags = [dict(name='aside'),
dict(name='footer'),
dict(name='div', attrs={'class':(lambda x: isinstance(x, (str,unicode)) and 'articlecommentcountholder' in x.split(' '))}),
dict(name='ul', attrs={'class':(lambda x: isinstance(x, (str,unicode)) and 'articletoolbar' in x.split(' '))}),
]
feeds = [
(u'Latest headlines', u'http://www.theglobeandmail.com/?service=rss'),
(u'Top stories', u'http://www.theglobeandmail.com/?service=rss&feed=topstories'),
(u'National', u'http://www.theglobeandmail.com/news/national/?service=rss'),
(u'Politics', u'http://www.theglobeandmail.com/news/politics/?service=rss'),
(u'World', u'http://www.theglobeandmail.com/news/world/?service=rss'),
(u'Business', u'http://www.theglobeandmail.com/report-on-business/?service=rss'),
(u'Opinions', u'http://www.theglobeandmail.com/news/opinions/?service=rss'),
(u'Columnists', u'http://www.theglobeandmail.com/news/opinions/columnists/?service=rss'),
(u'Globe Investor', u'http://www.theglobeandmail.com/globe-investor/?service=rss'),
(u'Sports', u'http://www.theglobeandmail.com/sports/?service=rss'),
(u'Technology', u'http://www.theglobeandmail.com/news/technology/?service=rss'),
(u'Arts', u'http://www.theglobeandmail.com/news/arts/?service=rss'),
(u'Life', u'http://www.theglobeandmail.com/life/?service=rss'),
(u'Blogs', u'http://www.theglobeandmail.com/blogs/?service=rss'),
(u'Real Estate', u'http://www.theglobeandmail.com/real-estate/?service=rss'),
(u'Auto', u'http://www.theglobeandmail.com/auto/?service=rss')
]
max_articles_per_feed = 100
encoding = 'utf8'
publisher = 'Globe & Mail'
language = 'en_CA'
extra_css = 'p.meta {font-size:75%}\n .redtext {color: red;}\n .byline {font-size: 70%}'
def get_article_url(self, article):
url = BasicNewsRecipe.get_article_url(self, article)
if '/video/' not in url:
return url
feeds = [
(u'Top National Stories', u'http://www.theglobeandmail.com/news/national/?service=rss'),
(u'Business', u'http://www.theglobeandmail.com/report-on-business/?service=rss'),
(u'Commentary', u'http://www.theglobeandmail.com/report-on-business/commentary/?service=rss'),
(u'Blogs', u'http://www.theglobeandmail.com/blogs/?service=rss'),
(u'Facts & Arguments', u'http://www.theglobeandmail.com/life/facts-and-arguments/?service=rss'),
(u'Technology', u'http://www.theglobeandmail.com/news/technology/?service=rss'),
(u'Investing', u'http://www.theglobeandmail.com/globe-investor/?service=rss'),
(u'Top Polical Stories', u'http://www.theglobeandmail.com/news/politics/?service=rss'),
(u'Arts', u'http://www.theglobeandmail.com/news/arts/?service=rss'),
(u'Life', u'http://www.theglobeandmail.com/life/?service=rss'),
(u'Real Estate', u'http://www.theglobeandmail.com/real-estate/?service=rss'),
(u'Auto', u'http://www.theglobeandmail.com/sports/?service=rss'),
(u'Sports', u'http://www.theglobeandmail.com/auto/?service=rss')
]
keep_only_tags = [
dict(name='h1'),
dict(name='h2', attrs={'id':'articletitle'}),
dict(name='p', attrs={'class':['leadText', 'meta', 'leadImage', 'redtext byline', 'bodyText']}),
dict(name='div', attrs={'class':['news','articlemeta','articlecopy']}),
dict(name='id', attrs={'class':'article'}),
dict(name='table', attrs={'class':'todays-market'}),
dict(name='header', attrs={'id':'leadheader'})
]
remove_tags = [
dict(name='div', attrs={'id':['tabInside', 'ShareArticles', 'topStories']})
]
#this has to be here or the text in the article appears twice.
remove_tags_after = [dict(id='article')]
#Use the mobile version rather than the web version
def print_version(self, url):
return url + '&service=mobile'

41
resources/recipes/handelsblatt.recipe Normal file
View File

@ -0,0 +1,41 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Handelsblatt(BasicNewsRecipe):
title = u'Handelsblatt'
__author__ = 'malfi'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
cover_url = 'http://www.handelsblatt.com/images/logo/logo_handelsblatt.com.png'
language = 'de'
keep_only_tags = []
keep_only_tags.append(dict(name = 'div', attrs = {'class': 'structOneCol'}))
keep_only_tags.append(dict(name = 'div', attrs = {'id': 'fullText'}))
remove_tags = [dict(name='img', attrs = {'src': 'http://www.handelsblatt.com/images/icon/loading.gif'})]
feeds = [
(u'Handelsblatt Exklusiv',u'http://www.handelsblatt.com/rss/exklusiv'),
(u'Handelsblatt Top-Themen',u'http://www.handelsblatt.com/rss/top-themen'),
(u'Handelsblatt Schlagzeilen',u'http://www.handelsblatt.com/rss/ticker/'),
(u'Handelsblatt Finanzen',u'http://www.handelsblatt.com/rss/finanzen/'),
(u'Handelsblatt Unternehmen',u'http://www.handelsblatt.com/rss/unternehmen/'),
(u'Handelsblatt Politik',u'http://www.handelsblatt.com/rss/politik/'),
(u'Handelsblatt Technologie',u'http://www.handelsblatt.com/rss/technologie/'),
(u'Handelsblatt Meinung',u'http://www.handelsblatt.com/rss/meinung'),
(u'Handelsblatt Magazin',u'http://www.handelsblatt.com/rss/magazin/'),
(u'Handelsblatt Weblogs',u'http://www.handelsblatt.com/rss/blogs')
]
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''
def print_version(self, url):
m = re.search('(?<=;)[0-9]*', url)
return u'http://www.handelsblatt.com/_b=' + str(m.group(0)) + ',_p=21,_t=ftprint,doc_page=0;printpage'

38
resources/recipes/hola.recipe Normal file
View File

@ -0,0 +1,38 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2010, Brendan Sleight <bms.calibre at barwap.com>'
'''
hola.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Hackaday(BasicNewsRecipe):
title = u'Hola'
__author__ = 'bmsleight'
description = 'diario de actualidad, moda y belleza.'
oldest_article = 10
max_articles_per_feed = 100
no_stylesheets = True
language = 'es'
use_embedded_content = False
keep_only_tags = [
dict(name='div', attrs={'id':'cuerpo'})
]
feeds = [
(u'Famosos' , u'http://www.hola.com/famosos/rss.xml' ),
(u'Realeza' , u'http://www.hola.com/realeza/rss.xml' ),
(u'Cine' , u'http://www.hola.com/cine/rss.xml' ),
(u'Música' , u'http://www.hola.com/musica/rss.xml' ),
(u'Moda y modelos' , u'http://www.hola.com/moda/portada/rss.xml' ),
(u'Belleza y salud', u'http://www.hola.com/belleza/portada/rss.xml' ),
(u'Niños' , u'http://www.hola.com/ninos/rss.xml' ),
(u'Todas las noticias', u'http://int2.hola.com/app/feeds/rss_hola.php'),
]
def get_article_url(self, article):
url = article.get('guid', None)
return url

13
resources/recipes/irish_times.recipe
View File

@ -33,13 +33,14 @@ class IrishTimes(BasicNewsRecipe):
('Letters', 'http://www.irishtimes.com/feeds/rss/newspaper/letters.rss'),
]
def print_version(self, url):
if url.count('rss.feedsportal.com'):
u = url.replace('0Bhtml/story01.htm','_pf0Bhtml/story01.htm')
else:
u = url.replace('.html','_pf.html')
return u
if url.count('rss.feedsportal.com'):
u = 'http://www.irishtimes.com' + \
(((url[69:].replace('0C','/')).replace('0A','0'))).replace('0Bhtml/story01..htm','_pf.html')
else:
u = url.replace('.html','_pf.html')
return u
def get_article_url(self, article):
return article.link

1
resources/recipes/la_jornada.recipe
View File

@ -38,6 +38,7 @@ class LaJornada_mx(BasicNewsRecipe):
.loc{font-weight: bold}
.carton{text-align: center}
.credit{font-weight: bold}
.sumario{font-weight: bold; text-align: center}
.text{margin-top: 1.4em}
p.inicial{display: inline; font-size: xx-large; font-weight: bold}
p.s-s{display: inline; text-indent: 0}

177
resources/recipes/lenta_ru.recipe Normal file
View File

@ -0,0 +1,177 @@
#!/usr/bin/env python
'''
Lenta.ru
'''
from calibre.web.feeds.feedparser import parse
from calibre.ebooks.BeautifulSoup import Tag
from calibre.web.feeds.news import BasicNewsRecipe
import re
class LentaRURecipe(BasicNewsRecipe):
title = u'Lenta.ru: \u041d\u043e\u0432\u043e\u0441\u0442\u0438'
__author__ = 'Nikolai Kotchetkov'
publisher = 'lenta.ru'
category = 'news, Russia'
description = u'''\u0415\u0436\u0435\u0434\u043d\u0435\u0432\u043d\u0430\u044f
\u0438\u043d\u0442\u0435\u0440\u043d\u0435\u0442-\u0433\u0430\u0437\u0435\u0442\u0430.
\u041d\u043e\u0432\u043e\u0441\u0442\u0438 \u0441\u043e
\u0432\u0441\u0435\u0433\u043e \u043c\u0438\u0440\u0430 \u043d\u0430
\u0440\u0443\u0441\u0441\u043a\u043e\u043c
\u044f\u0437\u044b\u043a\u0435'''
description = u'Ежедневная интернет-газета. Новости со всего мира на русском языке'
oldest_article = 3
max_articles_per_feed = 100
masthead_url = u'http://img.lenta.ru/i/logowrambler.gif'
cover_url = u'http://img.lenta.ru/i/logowrambler.gif'
#Add feed names if you want them to be sorted (feeds of this list appear first)
sortOrder = [u'_default', u'В России', u'б.СССР', u'В мире']
encoding = 'cp1251'
language = 'ru'
no_stylesheets = True
remove_javascript = True
recursions = 0
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags = [dict(name='td', attrs={'class':['statya','content']})]
remove_tags_after = [dict(name='p', attrs={'class':'links'}), dict(name='div', attrs={'id':'readers-block'})]
remove_tags = [dict(name='table', attrs={'class':['vrezka','content']}), dict(name='div', attrs={'class':'b240'}), dict(name='div', attrs={'id':'readers-block'}), dict(name='p', attrs={'class':'links'})]
feeds = [u'http://lenta.ru/rss/']
extra_css = 'h1 {font-size: 1.2em; margin: 0em 0em 0em 0em;} h2 {font-size: 1.0em; margin: 0em 0em 0em 0em;} h3 {font-size: 0.8em; margin: 0em 0em 0em 0em;}'
def parse_index(self):
try:
feedData = parse(self.feeds[0])
if not feedData:
raise NotImplementedError
self.log("parse_index: Feed loaded successfully.")
if feedData.feed.has_key('title'):
self.title = feedData.feed.title
self.log("parse_index: Title updated to: ", self.title)
if feedData.feed.has_key('image'):
self.log("HAS IMAGE!!!!")
def get_virtual_feed_articles(feed):
if feeds.has_key(feed):
return feeds[feed][1]
self.log("Adding new feed: ", feed)
articles = []
feeds[feed] = (feed, articles)
return articles
feeds = {}
#Iterate feed items and distribute articles using tags
for item in feedData.entries:
link = item.get('link', '');
title = item.get('title', '');
if '' == link or '' == title:
continue
article = {'title':title, 'url':link, 'description':item.get('description', ''), 'date':item.get('date', ''), 'content':''};
if not item.has_key('tags'):
get_virtual_feed_articles('_default').append(article)
continue
for tag in item.tags:
addedToDefault = False
term = tag.get('term', '')
if '' == term:
if (not addedToDefault):
get_virtual_feed_articles('_default').append(article)
continue
get_virtual_feed_articles(term).append(article)
#Get feed list
#Select sorted feeds first of all
result = []
for feedName in self.sortOrder:
if (not feeds.has_key(feedName)): continue
result.append(feeds[feedName])
del feeds[feedName]
result = result + feeds.values()
return result
except Exception, err:
self.log(err)
raise NotImplementedError
def preprocess_html(self, soup):
return self.adeify_images(soup)
def postprocess_html(self, soup, first_fetch):
#self.log('Original: ', soup.prettify())
contents = Tag(soup, 'div')
#Extract tags with given attributes
extractElements = {'div' : [{'id' : 'readers-block'}]}
#Remove all elements that were not extracted before
for tag, attrs in extractElements.iteritems():
for attr in attrs:
garbage = soup.findAll(tag, attr)
if garbage:
for pieceOfGarbage in garbage:
pieceOfGarbage.extract()
#Find article text using header
#and add all elements to contents
element = soup.find({'h1' : True, 'h2' : True})
if (element):
element.name = 'h1'
while element:
nextElement = element.nextSibling
element.extract()
contents.insert(len(contents.contents), element)
element = nextElement
#Place article date after header
dates = soup.findAll(text=re.compile('\d{2}\.\d{2}\.\d{4}, \d{2}:\d{2}:\d{2}'))
if dates:
for date in dates:
for string in date:
parent = date.parent
if (parent and isinstance(parent, Tag) and 'div' == parent.name and 'dt' == parent['class']):
#Date div found
parent.extract()
parent['style'] = 'font-size: 0.5em; color: gray; font-family: monospace;'
contents.insert(1, parent)
break
#Place article picture after date
pic = soup.find('img')
if pic:
picDiv = Tag(soup, 'div')
picDiv['style'] = 'width: 100%; text-align: center;'
pic.extract()
picDiv.insert(0, pic)
title = pic.get('title', None)
if title:
titleDiv = Tag(soup, 'div')
titleDiv['style'] = 'font-size: 0.5em;'
titleDiv.insert(0, title)
picDiv.insert(1, titleDiv)
contents.insert(2, picDiv)
body = soup.find('td', {'class':['statya','content']})
if body:
body.replaceWith(contents)
#self.log('Result: ', soup.prettify())
return soup

35
resources/recipes/marctv.recipe Normal file
View File

@ -0,0 +1,35 @@
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
'''
Fetch MarcTV.
'''
from calibre.web.feeds.news import BasicNewsRecipe
class MarcTVde(BasicNewsRecipe):
title = 'Marc Toensings Visionen'
description = 'Marc Toensings Visionen'
language = 'de'
__author__ = 'Marc Toensing'
max_articles_per_feed = 40
oldest_article = 665
use_embedded_content = False
remove_tags = []
keep_only_tags = dict(name='div', attrs={'class':["content"]})
feeds = [(u'Spiele', u'http://feeds.feedburner.com/marctv/spiele'), (u'Leben', u'http://feeds.feedburner.com/marctv/leben'), (u'Medien', u'http://feeds.feedburner.com/marctv/medien')]
extra_css = '.#wrapper .entry p img{width:620px; height: 270px;}'
def get_cover_url(self):
return 'http://marctv.de/marctv.png'

82
resources/recipes/mediapart.recipe
View File

@ -1,53 +1,79 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Mathieu Godlewski <mathieu at godlewski.fr>'
__copyright__ = '2009, Mathieu Godlewski <mathieu at godlewski.fr>; 2010, Louis Gesbert <meta at antislash dot info>'
'''
Mediapart
'''
import re, string
from calibre.ebooks.BeautifulSoup import BeautifulSoup
from calibre.ebooks.BeautifulSoup import Tag
from calibre.web.feeds.news import BasicNewsRecipe
class Mediapart(BasicNewsRecipe):
title = 'Mediapart'
__author__ = 'Mathieu Godlewski <mathieu at godlewski.fr>'
__author__ = 'Mathieu Godlewski'
description = 'Global news in french from online newspapers'
oldest_article = 7
language = 'fr'
needs_subscription = True
max_articles_per_feed = 50
no_stylesheets = True
html2lrf_options = ['--base-font-size', '10']
cover_url = 'http://www.mediapart.fr/sites/all/themes/mediapart/mediapart/images/annonce.jpg'
feeds = [
('Les articles', 'http://www.mediapart.fr/articles/feed'),
]
preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE|re.DOTALL), i[1]) for i in
[
(r'<div class="print-title">([^>]+)</div>', lambda match : '<h2>'+match.group(1)+'</h2>'),
(r'<p>Mediapart\.fr</p>', lambda match : ''),
(r'<p[^>]*>[\s]*</p>', lambda match : ''),
(r'<p><a href="[^\.]+\.pdf">[^>]*</a></p>', lambda match : ''),
# -- print-version has poor quality on this website, better do the conversion ourselves
#
# preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE|re.DOTALL), i[1]) for i in
# [
# (r'<div class="print-title">([^>]+)</div>', lambda match : '<h2>'+match.group(1)+'</h2>'),
# (r'<span class=\'auteur_staff\'>[^>]+<a title=\'[^\']*\'[^>]*>([^<]*)</a>[^<]*</span>',
# lambda match : '<i>'+match.group(1)+'</i>'),
# (r'\'', lambda match: '&rsquo;'),
# ]
# ]
#
# remove_tags = [ dict(name='div', attrs={'class':'print-source_url'}),
# dict(name='div', attrs={'class':'print-links'}),
# dict(name='img', attrs={'src':'entete_article.png'}),
# dict(name='br') ]
#
# def print_version(self, url):
# raw = self.browser.open(url).read()
# soup = BeautifulSoup(raw.decode('utf8', 'replace'))
# div = soup.find('div', {'id':re.compile('node-\d+')})
# if div is None:
# return None
# article_id = string.replace(div['id'], 'node-', '')
# if article_id is None:
# return None
# return 'http://www.mediapart.fr/print/'+article_id
# -- Non-print version [dict(name='div', attrs={'class':'advert'})]
keep_only_tags = [
dict(name='h1', attrs={'class':'title'}),
dict(name='div', attrs={'class':'page_papier_detail'}),
]
]
remove_tags = [ dict(name='div', attrs={'class':'print-source_url'}),
dict(name='div', attrs={'class':'print-links'}),
dict(name='img', attrs={'src':'entete_article.png'}),
]
def preprocess_html(self,soup):
for title in soup.findAll('div', {'class':'titre'}):
tag = Tag(soup, 'h3')
title.replaceWith(tag)
tag.insert(0,title)
return soup
# -- Handle login
def get_browser(self):
br = BasicNewsRecipe.get_browser()
if self.username is not None and self.password is not None:
br.open('http://www.mediapart.fr/')
br.select_form(nr=1)
br['name'] = self.username
br['pass'] = self.password
br.submit()
return br
def print_version(self, url):
raw = self.browser.open(url).read()
soup = BeautifulSoup(raw.decode('utf8', 'replace'))
div = soup.find('div', {'class':'node node-type-article'})
if div is None:
return None
article_id = string.replace(div['id'], 'node-', '')
if article_id is None:
return None
return 'http://www.mediapart.fr/print/'+article_id

61
resources/recipes/ming_pao.recipe Normal file
View File

@ -0,0 +1,61 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Eddie Lau'
'''
modified from Singtao Toronto calibre recipe by rty
Change Log:
2010/10/31: skip repeated articles in section pages
'''
import datetime
from calibre.web.feeds.recipes import BasicNewsRecipe
class AdvancedUserRecipe1278063072(BasicNewsRecipe):
title = 'Ming Pao - Hong Kong'
oldest_article = 1
max_articles_per_feed = 100
__author__ = 'Eddie Lau'
description = 'Hong Kong Chinese Newspaper'
publisher = 'news.mingpao.com'
category = 'Chinese, News, Hong Kong'
remove_javascript = True
use_embedded_content = False
no_stylesheets = True
language = 'zh'
encoding = 'Big5-HKSCS'
recursions = 0
conversion_options = {'linearize_tables':True}
masthead_url = 'http://news.mingpao.com/image/portals_top_logo_news.gif'
keep_only_tags = [dict(name='h1'),
dict(attrs={'id':['newscontent01','newscontent02']})]
def get_fetchdate(self):
dt_utc = datetime.datetime.utcnow()
# convert UTC to local hk time - at around HKT 5.30am, all news are available
dt_local = dt_utc - datetime.timedelta(-2.5/24)
return dt_local.strftime("%Y%m%d")
def parse_index(self):
feeds = []
dateStr = self.get_fetchdate()
for title, url in [(u'\u8981\u805e Headline', 'http://news.mingpao.com/' + dateStr + '/gaindex.htm'), (u'\u6559\u80b2 Education', 'http://news.mingpao.com/' + dateStr + '/gfindex.htm'), (u'\u6e2f\u805e Local', 'http://news.mingpao.com/' + dateStr + '/gbindex.htm'), (u'\u793e\u8a55\u2027\u7b46\u9663 Editorial', 'http://news.mingpao.com/' + dateStr + '/mrindex.htm'), (u'\u8ad6\u58c7 Forum', 'http://news.mingpao.com/' + dateStr + '/faindex.htm'), (u'\u4e2d\u570b China', 'http://news.mingpao.com/' + dateStr + '/caindex.htm'), (u'\u570b\u969b World', 'http://news.mingpao.com/' + dateStr + '/taindex.htm'), ('Tech News', 'http://news.mingpao.com/' + dateStr + '/naindex.htm'), (u'\u9ad4\u80b2 Sport', 'http://news.mingpao.com/' + dateStr + '/spindex.htm'), (u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'),]:
articles = self.parse_section(url)
if articles:
feeds.append((title, articles))
return feeds
def parse_section(self, url):
dateStr = self.get_fetchdate()
soup = self.index_to_soup(url)
divs = soup.findAll(attrs={'class': ['bullet']})
current_articles = []
included_urls = []
for i in divs:
a = i.find('a', href = True)
title = self.tag_to_string(a)
url = a.get('href', False)
url = 'http://news.mingpao.com/' + dateStr + '/' +url
if url not in included_urls:
current_articles.append({'title': title, 'url': url, 'description':''})
included_urls.append(url)
return current_articles

57
resources/recipes/mmc_rtv.recipe Normal file
View File

@ -0,0 +1,57 @@
__license__ = 'GPL v3'
__copyright__ = '2010, BlonG'
'''
www.rtvslo.si
'''
from calibre.web.feeds.news import BasicNewsRecipe
class MMCRTV(BasicNewsRecipe):
title = u'MMC RTV Slovenija'
__author__ = u'BlonG'
description = u"Prvi interaktivni multimedijski portal, MMC RTV Slovenija"
oldest_article = 3
max_articles_per_feed = 20
language = 'sl'
no_stylesheets = True
use_embedded_content = False
cover_url = 'https://sites.google.com/site/javno2010/home/rtv_slo_cover.jpg'
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''
def print_version(self, url):
split_url = url.split("/")
print_url = 'http://www.rtvslo.si/index.php?c_mod=news&op=print&id=' + split_url[-1]
return print_url
keep_only_tags = [
dict(name='div', attrs={'class':'title'}),
dict(name='div', attrs={'id':'newsbody'}),
dict(name='div', attrs={'id':'newsblocks'}),
]
# remove_tags=[
# 40 dict(name='div', attrs={'id':'newsblocks'}),
# ]
feeds = [
(u'Slovenija', u'http://www.rtvslo.si/feeds/01.xml'),
(u'Svet', u'http://www.rtvslo.si/feeds/02.xml'),
(u'Evropska unija', u'http://www.rtvslo.si/feeds/16.xml'),
(u'Gospodarstvo', u'http://www.rtvslo.si/feeds/04.xml'),
(u'\u010crna kronika', u'http://www.rtvslo.si/feeds/08.xml'),
(u'Okolje', u'http://www.rtvslo.si/feeds/12.xml'),
(u'Znanost in tehnologija', u'http://www.rtvslo.si/feeds/09.xml'),
(u'Zabava', u'http://www.rtvslo.si/feeds/06.xml'),
(u'Ture avanture', u'http://www.rtvslo.si/feeds/28.xml'),
]
# def preprocess_html(self, soup):
# newsblocks = soup.find('div',attrs = ['id':'newsblocks'])
# soup.find('div', attrs = {'id':'newsbody'}).insert(-1, newsblocks)
# return soup

29
resources/recipes/new_scientist.recipe
View File

@ -8,11 +8,11 @@ import re
from calibre.web.feeds.news import BasicNewsRecipe
class NewScientist(BasicNewsRecipe):
title = 'New Scientist - Online News'
title = 'New Scientist - Online News w. subscription'
__author__ = 'Darko Miletic'
description = 'Science news and science articles from New Scientist.'
language = 'en'
publisher = 'New Scientist'
publisher = 'Reed Business Information Ltd.'
category = 'science news, science articles, science jobs, drugs, cancer, depression, computer software'
oldest_article = 7
max_articles_per_feed = 100
@ -21,7 +21,12 @@ class NewScientist(BasicNewsRecipe):
cover_url = 'http://www.newscientist.com/currentcover.jpg'
masthead_url = 'http://www.newscientist.com/img/misc/ns_logo.jpg'
encoding = 'utf-8'
extra_css = ' body{font-family: Arial,sans-serif} img{margin-bottom: 0.8em} '
needs_subscription = 'optional'
extra_css = """
body{font-family: Arial,sans-serif}
img{margin-bottom: 0.8em}
.quotebx{font-size: x-large; font-weight: bold; margin-right: 2em; margin-left: 2em}
"""
conversion_options = {
'comment' : description
@ -33,15 +38,27 @@ class NewScientist(BasicNewsRecipe):
keep_only_tags = [dict(name='div', attrs={'id':['pgtop','maincol','blgmaincol','nsblgposts','hldgalcols']})]
def get_browser(self):
br = BasicNewsRecipe.get_browser()
br.open('http://www.newscientist.com/')
if self.username is not None and self.password is not None:
br.open('https://www.newscientist.com/user/login?redirectURL=')
br.select_form(nr=2)
br['loginId' ] = self.username
br['password'] = self.password
br.submit()
return br
remove_tags = [
dict(name='div' , attrs={'class':['hldBd','adline','pnl','infotext' ]})
,dict(name='div' , attrs={'id' :['compnl','artIssueInfo','artTools','comments','blgsocial','sharebtns']})
,dict(name='p' , attrs={'class':['marker','infotext' ]})
,dict(name='meta' , attrs={'name' :'description' })
,dict(name='a' , attrs={'rel' :'tag' })
,dict(name='a' , attrs={'rel' :'tag' })
,dict(name=['link','base','meta','iframe','object','embed'])
]
remove_tags_after = dict(attrs={'class':['nbpcopy','comments']})
remove_attributes = ['height','width']
remove_attributes = ['height','width','lang']
feeds = [
(u'Latest Headlines' , u'http://feeds.newscientist.com/science-news' )
@ -62,6 +79,8 @@ class NewScientist(BasicNewsRecipe):
return url + '?full=true&print=true'
def preprocess_html(self, soup):
for item in soup.findAll(['quote','quotetext']):
item.name='p'
for tg in soup.findAll('a'):
if tg.string == 'Home':
tg.parent.extract()

68
resources/recipes/newsweek_polska.recipe Normal file
View File

@ -0,0 +1,68 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2010, Mateusz Kielar, matek09@gmail.com'
from calibre.web.feeds.news import BasicNewsRecipe
class Newsweek(BasicNewsRecipe):
EDITION = 0
title = u'Newsweek Polska'
__author__ = 'Mateusz Kielar'
description = 'Weekly magazine'
encoding = 'utf-8'
no_stylesheets = True
language = 'en'
remove_javascript = True
keep_only_tags =[]
keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'article'}))
remove_tags =[]
remove_tags.append(dict(name = 'div', attrs = {'class' : 'copy'}))
remove_tags.append(dict(name = 'div', attrs = {'class' : 'url'}))
extra_css = '''
.body {font-size: small}
.author {font-size: x-small}
.lead {font-size: x-small}
.title{font-size: x-large; font-weight: bold}
'''
def print_version(self, url):
return url.replace("http://www.newsweek.pl/artykuly/wydanie/" + str(self.EDITION), "http://www.newsweek.pl/artykuly") + '/print'
def find_last_full_issue(self):
page = self.index_to_soup('http://www.newsweek.pl/Frames/IssueCover.aspx')
issue = 'http://www.newsweek.pl/Frames/' + page.find(lambda tag: tag.name == 'span' and not tag.attrs).a['href']
page = self.index_to_soup(issue)
issue = 'http://www.newsweek.pl/Frames/' + page.find(lambda tag: tag.name == 'span' and not tag.attrs).a['href']
page = self.index_to_soup(issue)
self.EDITION = page.find('a', attrs={'target' : '_parent'})['href'].replace('/wydania/','')
def parse_index(self):
self.find_last_full_issue()
soup = self.index_to_soup('http://www.newsweek.pl/wydania/' + str(self.EDITION))
img = soup.find('img', id="ctl00_C1_PaperIsssueView_IssueImage", src=True)
self.cover_url = img['src']
feeds = []
parent = soup.find(id='content-left-big')
for txt in parent.findAll(attrs={'class':'txt_normal_red strong'}):
section = self.tag_to_string(txt).capitalize()
articles = list(self.find_articles(txt))
feeds.append((section, articles))
return feeds
def find_articles(self, txt):
for a in txt.findAllNext( attrs={'class':['strong','hr']}):
if a.name in "div":
break
yield {
'title' : self.tag_to_string(a),
'url' : 'http://www.newsweek.pl'+a['href'],
'date' : '',
'description' : ''
}

35
resources/recipes/now_toronto.recipe Normal file
View File

@ -0,0 +1,35 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
#Based on Lars Jacob's Taz Digiabo recipe
__license__ = 'GPL v3'
__copyright__ = '2010, Starson17'
import os, urllib2, zipfile
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ptempfile import PersistentTemporaryFile
class NowToronto(BasicNewsRecipe):
title = u'Now Toronto'
description = u'Now Toronto'
__author__ = 'Starson17'
conversion_options = {
'no_default_epub_cover' : True
}
def build_index(self):
epub_feed = "http://feeds.feedburner.com/NowEpubEditions"
soup = self.index_to_soup(epub_feed)
url = soup.find(name = 'feedburner:origlink').string
f = urllib2.urlopen(url)
tmp = PersistentTemporaryFile(suffix='.epub')
self.report_progress(0,_('downloading epub'))
tmp.write(f.read())
tmp.close()
zfile = zipfile.ZipFile(tmp.name, 'r')
self.report_progress(0,_('extracting epub'))
zfile.extractall(self.output_dir)
tmp.close()
index = os.path.join(self.output_dir, 'content.opf')
self.report_progress(1,_('epub downloaded and extracted'))
return index

513
resources/recipes/nytimes.recipe
View File

@ -5,65 +5,61 @@ __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
'''
nytimes.com
'''
import re
import time
from calibre import entity_to_unicode
import re, string, time
from calibre import entity_to_unicode, strftime
from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag, NavigableString, \
Comment, BeautifulStoneSoup
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag, BeautifulStoneSoup
class NYTimes(BasicNewsRecipe):
title = 'New York Times Top Stories'
__author__ = 'GRiker'
language = 'en'
requires_version = (0, 7, 5)
description = 'Top Stories from the New York Times'
# set headlinesOnly to True for the headlines-only version
headlinesOnly = True
# List of sections typically included in Top Stories. Use a keyword from the
# right column in the excludeSectionKeywords[] list to skip downloading that section
sections = {
'arts' : 'Arts',
'business' : 'Business',
'diningwine' : 'Dining & Wine',
'editorials' : 'Editorials',
'health' : 'Health',
'magazine' : 'Magazine',
'mediaadvertising' : 'Media & Advertising',
'newyorkregion' : 'New York/Region',
'oped' : 'Op-Ed',
'politics' : 'Politics',
'science' : 'Science',
'sports' : 'Sports',
'technology' : 'Technology',
'topstories' : 'Top Stories',
'travel' : 'Travel',
'us' : 'U.S.',
'world' : 'World'
}
# includeSections: List of sections to include. If empty, all sections found will be included.
# Otherwise, only the sections named will be included. For example,
#
# includeSections = ['Politics','Sports']
#
# would cause only the Politics and Sports sections to be included.
# Add section keywords from the right column above to skip that section
# For example, to skip sections containing the word 'Sports' or 'Dining', use:
# excludeSectionKeywords = ['Sports', 'Dining']
# Fetch only Business and Technology
# excludeSectionKeywords = ['Arts','Dining','Editorials','Health','Magazine','Media','Region','Op-Ed','Politics','Science','Sports','Top Stories','Travel','U.S.','World']
# Fetch only Top Stories
# excludeSectionKeywords = ['Arts','Business','Dining','Editorials','Health','Magazine','Media','Region','Op-Ed','Politics','Science','Sports','Technology','Travel','U.S.','World']
# By default, no sections are skipped.
excludeSectionKeywords = []
includeSections = [] # by default, all sections included
# excludeSections: List of sections to exclude. If empty, all sections found will be included.
# Otherwise, the sections named will be excluded. For example,
#
# excludeSections = ['Politics','Sports']
#
# would cause the Politics and Sports sections to be excluded. This parameter can be used
# in conjuction with includeSections although in most cases using one or the other, but
# not both, is sufficient.
excludeSections = []
# one_picture_per_article specifies that calibre should only use the first image
# from an article (if one exists). If one_picture_per_article = True, the image
# will be moved to a location between the headline and the byline.
# If one_picture_per_article = False, all images from the article will be included
# and shown in their original location.
one_picture_per_article = True
# The maximum number of articles that will be downloaded
max_articles_per_feed = 40
max_articles_per_feed = 100
if headlinesOnly:
title='New York Times Headlines'
description = 'Headlines from the New York Times'
else:
title='New York Times'
description = 'Today\'s New York Times'
__author__ = 'GRiker/Kovid Goyal/Nick Redding'
language = 'en'
requires_version = (0, 7, 5)
timefmt = ''
needs_subscription = True
masthead_url = 'http://graphics8.nytimes.com/images/misc/nytlogo379x64.gif'
cover_margins = (18,18,'grey99')
@ -82,6 +78,7 @@ class NYTimes(BasicNewsRecipe):
'entry-response module',
'icon enlargeThis',
'leftNavTabs',
'metaFootnote',
'module box nav',
'nextArticleLink',
'nextArticleLink clearfix',
@ -89,12 +86,13 @@ class NYTimes(BasicNewsRecipe):
'relatedSearchesModule',
'side_tool',
'singleAd',
'subNavigation clearfix',
'subNavigation tabContent active',
'subNavigation tabContent active clearfix',
re.compile('^subNavigation'),
re.compile('^leaderboard'),
re.compile('^module'),
]}),
dict(id=[
'adxLeaderboard',
'adxSponLink',
'archive',
'articleExtras',
'articleInline',
@ -105,87 +103,98 @@ class NYTimes(BasicNewsRecipe):
'footer',
'header',
'header_search',
'inlineBox',
'login',
'masthead',
'masthead-nav',
'memberTools',
'navigation',
'portfolioInline',
'readerReviews',
'readerReviewsCount',
'relatedArticles',
'relatedTopics',
'respond',
'side_search',
'side_index',
'side_tool',
'toolsRight',
]),
dict(name=['script', 'noscript', 'style'])]
dict(name=['script', 'noscript', 'style','form','hr'])]
no_stylesheets = True
extra_css = '.headline {text-align: left;}\n \
.byline {font-family: monospace; \
text-align: left; \
margin-top: 0px; \
margin-bottom: 0px;}\n \
.dateline {font-size: small; \
margin-top: 0px; \
margin-bottom: 0px;}\n \
.timestamp {font-size: small; \
margin-top: 0px; \
margin-bottom: 0px;}\n \
.source {text-align: left;}\n \
.image {text-align: center;}\n \
.credit {text-align: right; \
font-size: small; \
margin-top: 0px; \
margin-bottom: 0px;}\n \
.articleBody {text-align: left;}\n \
.authorId {text-align: left; \
font-style: italic;}\n '
extra_css = '''
.articleHeadline { text-align: left; margin-top:0.5em; margin-bottom:0.25em; }
.credit { text-align: right; font-size: small; line-height:1em; margin-top:5px; margin-left:0; margin-right:0; margin-bottom: 0; }
.byline { text-align: left; font-size: small; line-height:1em; margin-top:10px; margin-left:0; margin-right:0; margin-bottom: 0; }
.dateline { text-align: left; font-size: small; line-height:1em;margin-top:5px; margin-left:0; margin-right:0; margin-bottom: 0; }
.kicker { font-size: small; line-height:1em;margin-top:5px; margin-left:0; margin-right:0; margin-bottom: 0; }
.timestamp { text-align: left; font-size: small; }
.caption { font-size: small; font-style:italic; line-height:1em; margin-top:5px; margin-left:0; margin-right:0; margin-bottom: 0; }
a:link {text-decoration: none; }
.articleBody { }
.authorId {text-align: left; }
.image {text-align: center;}
.source {text-align: left; }'''
def dump_ans(self, ans) :
def filter_ans(self, ans) :
total_article_count = 0
for section in ans :
idx = 0
idx_max = len(ans)-1
while idx <= idx_max:
if self.includeSections != []:
if ans[idx][0] not in self.includeSections:
print "SECTION NOT INCLUDED: ",ans[idx][0]
del ans[idx]
idx_max = idx_max-1
continue
if ans[idx][0] in self.excludeSections:
print "SECTION EXCLUDED: ",ans[idx][0]
del ans[idx]
idx_max = idx_max-1
continue
if self.verbose:
self.log("section %s: %d articles" % (section[0], len(section[1])) )
for article in section[1]:
self.log("Section %s: %d articles" % (ans[idx][0], len(ans[idx][1])) )
for article in ans[idx][1]:
total_article_count += 1
if self.verbose:
self.log("\t%-40.40s... \t%-60.60s..." % (article['title'].encode('cp1252','replace'),
article['url'].encode('cp1252','replace')))
idx = idx+1
self.log( "Queued %d articles" % total_article_count )
return ans
def fixChars(self,string):
# Replace lsquo (\x91)
fixed = re.sub("\x91","&#8216;",string)
fixed = re.sub("\x91","‘",string)
# Replace rsquo (\x92)
fixed = re.sub("\x92","&#8217;",fixed)
fixed = re.sub("\x92","’",fixed)
# Replace ldquo (\x93)
fixed = re.sub("\x93","&#8220;",fixed)
fixed = re.sub("\x93","“",fixed)
# Replace rdquo (\x94)
fixed = re.sub("\x94","&#8221;",fixed)
fixed = re.sub("\x94","”",fixed)
# Replace ndash (\x96)
fixed = re.sub("\x96","&#8211;",fixed)
fixed = re.sub("\x96","–",fixed)
# Replace mdash (\x97)
fixed = re.sub("\x97","&#8212;",fixed)
fixed = re.sub("\x97","—",fixed)
return fixed
def get_browser(self):
br = BasicNewsRecipe.get_browser()
if self.username is not None and self.password is not None:
try:
br.open('http://www.nytimes.com/auth/login')
br.select_form(name='login')
br['USERID'] = self.username
br['PASSWORD'] = self.password
br.submit()
except:
self.log("\nFailed to login")
br.open('http://www.nytimes.com/auth/login')
br.select_form(name='login')
br['USERID'] = self.username
br['PASSWORD'] = self.password
raw = br.submit().read()
if 'Please try again' in raw:
raise Exception('Your username and password are incorrect')
return br
def skip_ad_pages(self, soup):
@ -213,6 +222,9 @@ class NYTimes(BasicNewsRecipe):
cover = None
return cover
def short_title(self):
return self.title
def index_to_soup(self, url_or_raw, raw=False):
'''
OVERRIDE of class method
@ -255,157 +267,184 @@ class NYTimes(BasicNewsRecipe):
# Kindle TOC descriptions won't render certain characters
if description:
massaged = unicode(BeautifulStoneSoup(description, convertEntities=BeautifulStoneSoup.HTML_ENTITIES))
# Replace '&' with '&#38;'
massaged = re.sub("&","&#38;", massaged)
# Replace '&' with '&'
massaged = re.sub("&","&", massaged)
return self.fixChars(massaged)
else:
return description
def parse_index(self):
def parse_todays_index(self):
def feed_title(div):
return ''.join(div.findAll(text=True, recursive=True)).strip()
articles = {}
key = None
ans = []
url_list = []
def handle_article(div):
a = div.find('a', href=True)
if not a:
return
url = re.sub(r'\?.*', '', a['href'])
if not url.startswith("http"):
return
if not url.endswith(".html"):
return
if 'podcast' in url:
return
if '/video/' in url:
return
url += '?pagewanted=all'
if url in url_list:
return
url_list.append(url)
title = self.tag_to_string(a, use_alt=True).strip()
description = ''
pubdate = strftime('%a, %d %b')
summary = div.find(True, attrs={'class':'summary'})
if summary:
description = self.tag_to_string(summary, use_alt=False)
author = ''
authorAttribution = div.find(True, attrs={'class':'byline'})
if authorAttribution:
author = self.tag_to_string(authorAttribution, use_alt=False)
else:
authorAttribution = div.find(True, attrs={'class':'byline'})
if authorAttribution:
author = self.tag_to_string(authorAttribution, use_alt=False)
feed = key if key is not None else 'Uncategorized'
if not articles.has_key(feed):
ans.append(feed)
articles[feed] = []
articles[feed].append(
dict(title=title, url=url, date=pubdate,
description=description, author=author,
content=''))
soup = self.index_to_soup('http://www.nytimes.com/pages/todayspaper/index.html')
# Find each article
for div in soup.findAll(True,
attrs={'class':['section-headline', 'story', 'story headline','sectionHeader','headlinesOnly multiline flush']}):
if div['class'] in ['section-headline','sectionHeader']:
key = string.capwords(feed_title(div))
key = key.replace('Op-ed','Op-Ed')
key = key.replace('U.s.','U.S.')
elif div['class'] in ['story', 'story headline'] :
handle_article(div)
elif div['class'] == 'headlinesOnly multiline flush':
for lidiv in div.findAll('li'):
handle_article(lidiv)
ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
return self.filter_ans(ans)
def parse_headline_index(self):
articles = {}
ans = []
feed = key = 'All Top Stories'
articles[key] = []
ans.append(key)
self.log("Scanning 1 section ...")
url_list = []
soup = self.index_to_soup('http://www.nytimes.com/pages/todaysheadlines/')
# Fetch the outer table
table = soup.find('table')
previousTable = table
# Fetch the content table
content_table = soup.find('table',{'id':'content'})
if content_table is None:
self.log("FATAL ERROR: CANNOT FIND CONTENT TABLE")
return None
# Find the deepest table containing the stories
while True :
table = table.find('table')
if table.find(text=re.compile('top stories start')) :
previousTable = table
continue
else :
table = previousTable
break
# Within this table are <td id=".*Column.*"> entries, each containing one or more h6 tags which represent sections
# There are multiple subtables, find the one containing the stories
for block in table.findAll('table') :
if block.find(text=re.compile('top stories start')) :
table = block
break
else :
continue
for td_col in content_table.findAll('td', {'id' : re.compile('Column')}):
for div_sec in td_col.findAll('div',recursive=False):
for h6_sec_name in div_sec.findAll('h6',{'style' : re.compile('text-transform: *uppercase')}):
section_name = self.tag_to_string(h6_sec_name,use_alt=False)
section_name = re.sub(r'^ *$','',section_name)
if section_name == '':
continue
section_name=string.capwords(section_name)
if section_name == 'U.s.':
section_name = 'U.S.'
elif section_name == 'Op-ed':
section_name = 'Op-Ed'
pubdate = strftime('%a, %d %b')
# Again there are multiple subtables, find the one containing the stories
for storyblock in table.findAll('table') :
if storyblock.find(text=re.compile('top stories start')) :
break
else :
continue
skipThisSection = False
todays_article_count = 0
# Within this table are <font face="times new roman, times, san serif"> entries
self.log("Fetching feed Top Stories")
for tr in storyblock.findAllNext('tr'):
if tr.find('span') is not None :
sectionblock = tr.find(True, attrs={'face':['times new roman, times,sans serif',
'times new roman,times, sans serif',
'times new roman, times, sans serif']})
section = None
bylines = []
descriptions = []
pubdate = None
# Get the Section title
for (x,i) in enumerate(sectionblock.contents) :
skipThisSection = False
# Extract the section title
if ('Comment' in str(i.__class__)) :
if 'start(name=' in i :
section = i[i.find('=')+1:-2]
if not self.sections.has_key(section) :
skipThisSection = True
search_div = div_sec
for next_tag in h6_sec_name.findNextSiblings(True):
if next_tag.__class__.__name__ == 'Tag':
if next_tag.name == 'div':
search_div = next_tag
break
# Check for excluded section
if len(self.excludeSectionKeywords):
key = self.sections[section]
excluded = re.compile('|'.join(self.excludeSectionKeywords))
if excluded.search(key) or articles.has_key(key):
skipThisSection = True
break
# Get the bylines and descriptions
if not skipThisSection :
lines = sectionblock.contents
contentStrings = []
for line in lines:
if not isinstance(line, Comment) and line.strip and line.strip() > "":
contentStrings.append(line.strip())
# Gather the byline/description pairs
bylines = []
descriptions = []
for contentString in contentStrings:
if contentString[0:3] == 'By ' and contentString[3].isupper() :
bylines.append(contentString)
# Get the articles
for h3_item in search_div.findAll('h3'):
byline = h3_item.h6
if byline is not None:
author = self.tag_to_string(byline,usa_alt=False)
else:
descriptions.append(contentString)
# Fetch the article titles and URLs
articleCount = len(sectionblock.findAll('span'))
todays_article_count += articleCount
for (i,span) in enumerate(sectionblock.findAll(attrs={'class':'headlineWrapper'})) :
a = span.find('a', href=True)
author = ''
a = h3_item.find('a', href=True)
if not a:
continue
url = re.sub(r'\?.*', '', a['href'])
if not url.startswith("http"):
continue
if not url.endswith(".html"):
continue
if 'podcast' in url:
continue
if 'video' in url:
continue
url += '?pagewanted=all'
if url in url_list:
continue
url_list.append(url)
self.log("URL %s" % url)
title = self.tag_to_string(a, use_alt=True).strip()
desc = h3_item.find('p')
if desc is not None:
description = self.tag_to_string(desc,use_alt=False)
else:
description = ''
if not articles.has_key(section_name):
ans.append(section_name)
articles[section_name] = []
articles[section_name].append(dict(title=title, url=url, date=pubdate, description=description, author=author, content=''))
title = self.tag_to_string(a, use_alt=True)
# prepend the section name
title = self.sections[section] + " &middot; " + title
if not isinstance(title, unicode):
title = title.decode('utf-8', 'replace')
# Allow for unattributed, undescribed entries "Editor's Note"
if i >= len(descriptions) :
description = None
else :
description = descriptions[i]
if len(bylines) == articleCount :
author = bylines[i]
else :
author = None
# Check for duplicates
duplicateFound = False
if len(articles[feed]) > 1:
for article in articles[feed] :
if url == article['url'] :
duplicateFound = True
break
if duplicateFound:
# Continue fetching, don't add this article
todays_article_count -= 1
continue
if not articles.has_key(feed):
articles[feed] = []
articles[feed].append(
dict(title=title, url=url, date=pubdate,
description=description, author=author, content=''))
# self.log("Queuing %d articles from %s" % (todays_article_count, "Top Stories"))
ans = self.sort_index_by(ans, {'Top Stories':-1})
ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
self.dump_ans(ans)
return ans
return self.filter_ans(ans)
def parse_index(self):
if self.headlinesOnly:
return self.parse_headline_index()
else:
return self.parse_todays_index()
def strip_anchors(self,soup):
paras = soup.findAll(True)
for para in paras:
aTags = para.findAll('a')
for a in aTags:
if a.img is None:
a.replaceWith(a.renderContents().decode('cp1252','replace'))
return soup
def preprocess_html(self, soup):
kicker_tag = soup.find(attrs={'class':'kicker'})
if kicker_tag: # remove Op_Ed author head shots
tagline = self.tag_to_string(kicker_tag)
if tagline=='Op-Ed Columnist':
img_div = soup.find('div','inlineImage module')
if img_div:
img_div.extract()
return self.strip_anchors(soup)
def postprocess_html(self,soup, True):
@ -422,8 +461,9 @@ class NYTimes(BasicNewsRecipe):
firstImg = inlineImgs[0]
for inlineImg in inlineImgs[1:]:
inlineImg.extract()
# Move firstImg after headline
cgFirst = soup.find(True, {'class':'columnGroup first'})
# Move firstImg before article body
#article_body = soup.find(True, {'id':'articleBody'})
cgFirst = soup.find(True, {'class':re.compile('columnGroup *first')})
if cgFirst:
# Strip all sibling NavigableStrings: noise
navstrings = cgFirst.findAll(text=True, recursive=False)
@ -443,30 +483,18 @@ class NYTimes(BasicNewsRecipe):
if headline_found:
cgFirst.insert(insertLoc,firstImg)
else:
self.log(">>> No class:'columnGroup first' found <<<")
# Change class="kicker" to <h3>
kicker = soup.find(True, {'class':'kicker'})
if kicker and kicker.contents[0]:
h3Tag = Tag(soup, "h3")
h3Tag.insert(0, self.fixChars(self.tag_to_string(kicker,
use_alt=False)))
kicker.replaceWith(h3Tag)
self.log(">>> No class:'columnGroup first' found <<<")
# Change captions to italic -1
# Change captions to italic
for caption in soup.findAll(True, {'class':'caption'}) :
if caption and caption.contents[0]:
emTag = Tag(soup, "em")
cTag = Tag(soup, "p", [("class", "caption")])
c = self.fixChars(self.tag_to_string(caption,use_alt=False)).strip()
mp_off = c.find("More Photos")
if mp_off >= 0:
c = c[:mp_off]
emTag.insert(0, c)
#hrTag = Tag(soup, 'hr')
#hrTag['class'] = 'caption_divider'
hrTag = Tag(soup, 'div')
hrTag['class'] = 'divider'
emTag.insert(1, hrTag)
caption.replaceWith(emTag)
cTag.insert(0, c)
caption.replaceWith(cTag)
# Change <nyt_headline> to <h2>
h1 = soup.find('h1')
@ -506,17 +534,6 @@ class NYTimes(BasicNewsRecipe):
bTag.insert(0, subhead.contents[0])
subhead.replaceWith(bTag)
# Synthesize a section header
dsk = soup.find('meta', attrs={'name':'dsk'})
if dsk and dsk.has_key('content'):
hTag = Tag(soup,'h3')
hTag['class'] = 'section'
hTag.insert(0,NavigableString(dsk['content']))
articleTag = soup.find(True, attrs={'id':'article'})
if articleTag:
articleTag.insert(0,hTag)
# Add class="articleBody" to <div> so we can format with CSS
divTag = soup.find('div',attrs={'id':'articleBody'})
if divTag:
divTag['class'] = divTag['id']
@ -532,11 +549,3 @@ class NYTimes(BasicNewsRecipe):
return soup
def strip_anchors(self,soup):
paras = soup.findAll(True)
for para in paras:
aTags = para.findAll('a')
for a in aTags:
if a.img is None:
a.replaceWith(a.renderContents().decode('cp1252','replace'))
return soup

589
resources/recipes/nytimes_sub.recipe
View File

@ -4,56 +4,66 @@ __license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
'''
nytimes.com
V5 - One picture per article, moved to top:
Headline
Image
Byline
Story
'''
import re, string, time
from calibre import strftime
from calibre import entity_to_unicode, strftime
from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulStoneSoup, NavigableString, Tag
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag, BeautifulStoneSoup
class NYTimes(BasicNewsRecipe):
title = 'The New York Times'
__author__ = 'GRiker'
language = 'en'
requires_version = (0, 7, 5)
# set headlinesOnly to True for the headlines-only version
headlinesOnly = False
description = 'Daily news from the New York Times (subscription version)'
allSectionKeywords = ['The Front Page', 'International','National','Obituaries','Editorials',
'New York','Business Day','Science Times','Sports','Dining','Arts',
'Home','Styles','Sunday Business','Week In Review','Travel','Magazine',
'Book Review','Weddings','Real Estate','Automobiles',"T Men's Fashion",
"T Women's Fashion"]
# includeSections: List of sections to include. If empty, all sections found will be included.
# Otherwise, only the sections named will be included. For example,
#
# includeSections = ['Politics','Sports']
#
# would cause only the Politics and Sports sections to be included.
# List of sections to exclude
# To add a section, copy the section name from the allSectionKeywords list above
# For example, to exclude 'Dining' and 'Weddings':
#excludeSectionKeywords = ['Dining','Weddings']
excludeSectionKeywords = []
includeSections = [] # by default, all sections included
# List of sections to include (test and debug only)
# By default, any sections in today's paper that are not listed in excludeSectionKeywords
# are downloaded. fetch_only specifies that only certain sections are to be downloaded.
# This should only be used for testing and debugging.
# For example, to download only 'The Front Page' section:
# fetch_only = set(['The Front Page'])
fetch_only = set([])
if fetch_only:
excludeSectionKeywords = list(set(allSectionKeywords) ^ fetch_only)
# excludeSections: List of sections to exclude. If empty, all sections found will be included.
# Otherwise, the sections named will be excluded. For example,
#
# excludeSections = ['Politics','Sports']
#
# would cause the Politics and Sports sections to be excluded. This parameter can be used
# in conjuction with includeSections although in most cases using one or the other, but
# not both, is sufficient.
excludeSections = []
# one_picture_per_article specifies that calibre should only use the first image
# from an article (if one exists). If one_picture_per_article = True, the image
# will be moved to a location between the headline and the byline.
# If one_picture_per_article = False, all images from the article will be included
# and shown in their original location.
one_picture_per_article = True
# The maximum number of articles that will be downloaded
max_articles_per_feed = 100
if headlinesOnly:
title='New York Times Headlines'
description = 'Headlines from the New York Times'
else:
title='New York Times'
description = 'Today\'s New York Times'
__author__ = 'GRiker/Kovid Goyal/Nick Redding'
language = 'en'
requires_version = (0, 7, 5)
timefmt = ''
needs_subscription = True
masthead_url = 'http://graphics8.nytimes.com/images/misc/nytlogo379x64.gif'
cover_margins = (18,18,'grey99')
remove_tags_before = dict(id='article')
remove_tags_after = dict(id='article')
remove_tags = [dict(attrs={'class':[
@ -69,6 +79,7 @@ class NYTimes(BasicNewsRecipe):
'entry-response module',
'icon enlargeThis',
'leftNavTabs',
'metaFootnote',
'module box nav',
'nextArticleLink',
'nextArticleLink clearfix',
@ -76,12 +87,13 @@ class NYTimes(BasicNewsRecipe):
'relatedSearchesModule',
'side_tool',
'singleAd',
'subNavigation clearfix',
'subNavigation tabContent active',
'subNavigation tabContent active clearfix',
re.compile('^subNavigation'),
re.compile('^leaderboard'),
re.compile('^module'),
]}),
dict(id=[
'adxLeaderboard',
'adxSponLink',
'archive',
'articleExtras',
'articleInline',
@ -92,61 +104,110 @@ class NYTimes(BasicNewsRecipe):
'footer',
'header',
'header_search',
'inlineBox',
'login',
'masthead',
'masthead-nav',
'memberTools',
'navigation',
'portfolioInline',
'readerReviews',
'readerReviewsCount',
'relatedArticles',
'relatedTopics',
'respond',
'side_search',
'side_index',
'side_tool',
'toolsRight',
]),
dict(name=['script', 'noscript', 'style'])]
masthead_url = 'http://graphics8.nytimes.com/images/misc/nytlogo379x64.gif'
cover_margins = (18,18,'grey99')
dict(name=['script', 'noscript', 'style','form','hr'])]
no_stylesheets = True
extra_css = '.headline {text-align: left;}\n \
.byline {font-family: monospace; \
text-align: left; \
margin-top: 0px; \
margin-bottom: 0px;}\n \
.dateline {font-size: small; \
margin-top: 0px; \
margin-bottom: 0px;}\n \
.timestamp {font-size: small; \
margin-top: 0px; \
margin-bottom: 0px;}\n \
.source {text-align: left;}\n \
.image {text-align: center;}\n \
.credit {text-align: right; \
font-size: small; \
margin-top: 0px; \
margin-bottom: 0px;}\n \
.articleBody {text-align: left;}\n \
.authorId {text-align: left; \
font-style: italic;}\n '
extra_css = '''
.articleHeadline { text-align: left; margin-top:0.5em; margin-bottom:0.25em; }
.credit { text-align: right; font-size: small; line-height:1em; margin-top:5px; margin-left:0; margin-right:0; margin-bottom: 0; }
.byline { text-align: left; font-size: small; line-height:1em; margin-top:10px; margin-left:0; margin-right:0; margin-bottom: 0; }
.dateline { text-align: left; font-size: small; line-height:1em;margin-top:5px; margin-left:0; margin-right:0; margin-bottom: 0; }
.kicker { font-size: small; line-height:1em;margin-top:5px; margin-left:0; margin-right:0; margin-bottom: 0; }
.timestamp { text-align: left; font-size: small; }
.caption { font-size: small; font-style:italic; line-height:1em; margin-top:5px; margin-left:0; margin-right:0; margin-bottom: 0; }
a:link {text-decoration: none; }
.articleBody { }
.authorId {text-align: left; }
.image {text-align: center;}
.source {text-align: left; }'''
def filter_ans(self, ans) :
total_article_count = 0
idx = 0
idx_max = len(ans)-1
while idx <= idx_max:
if self.includeSections != []:
if ans[idx][0] not in self.includeSections:
print "SECTION NOT INCLUDED: ",ans[idx][0]
del ans[idx]
idx_max = idx_max-1
continue
if ans[idx][0] in self.excludeSections:
print "SECTION EXCLUDED: ",ans[idx][0]
del ans[idx]
idx_max = idx_max-1
continue
if self.verbose:
self.log("Section %s: %d articles" % (ans[idx][0], len(ans[idx][1])) )
for article in ans[idx][1]:
total_article_count += 1
if self.verbose:
self.log("\t%-40.40s... \t%-60.60s..." % (article['title'].encode('cp1252','replace'),
article['url'].encode('cp1252','replace')))
idx = idx+1
self.log( "Queued %d articles" % total_article_count )
return ans
def fixChars(self,string):
# Replace lsquo (\x91)
fixed = re.sub("\x91","‘",string)
# Replace rsquo (\x92)
fixed = re.sub("\x92","’",fixed)
# Replace ldquo (\x93)
fixed = re.sub("\x93","“",fixed)
# Replace rdquo (\x94)
fixed = re.sub("\x94","”",fixed)
# Replace ndash (\x96)
fixed = re.sub("\x96","–",fixed)
# Replace mdash (\x97)
fixed = re.sub("\x97","—",fixed)
return fixed
def get_browser(self):
br = BasicNewsRecipe.get_browser()
if self.username is not None and self.password is not None:
try:
br.open('http://www.nytimes.com/auth/login')
br.select_form(name='login')
br['USERID'] = self.username
br['PASSWORD'] = self.password
raw = br.submit().read()
if 'Sorry, we could not find the combination you entered. Please try again.' in raw:
raise Exception('Your username and password are incorrect')
#open('/t/log.html', 'wb').write(raw)
except:
self.log("\nFailed to login")
br.open('http://www.nytimes.com/auth/login')
br.select_form(name='login')
br['USERID'] = self.username
br['PASSWORD'] = self.password
raw = br.submit().read()
if 'Please try again' in raw:
raise Exception('Your username and password are incorrect')
return br
def skip_ad_pages(self, soup):
# Skip ad pages served before actual article
skip_tag = soup.find(True, {'name':'skip'})
if skip_tag is not None:
self.log.warn("Found forwarding link: %s" % skip_tag.parent['href'])
url = 'http://www.nytimes.com' + re.sub(r'\?.*', '', skip_tag.parent['href'])
url += '?pagewanted=all'
self.log.warn("Skipping ad to article at '%s'" % url)
return self.index_to_soup(url, raw=True)
def get_cover_url(self):
cover = None
st = time.localtime()
@ -162,143 +223,232 @@ class NYTimes(BasicNewsRecipe):
cover = None
return cover
def get_masthead_title(self):
def short_title(self):
return self.title
def dump_ans(self, ans):
total_article_count = 0
for section in ans :
if self.verbose:
self.log("section %s: %d articles" % (section[0], len(section[1])) )
for article in section[1]:
total_article_count += 1
if self.verbose:
self.log("\t%-40.40s... \t%-60.60s..." % (article['title'].encode('mac-roman','replace'),
article['url'].encode('mac-roman','replace')))
self.log( "Queued %d articles" % total_article_count )
def index_to_soup(self, url_or_raw, raw=False):
'''
OVERRIDE of class method
deals with various page encodings between index and articles
'''
def get_the_soup(docEncoding, url_or_raw, raw=False) :
if re.match(r'\w+://', url_or_raw):
f = self.browser.open(url_or_raw)
_raw = f.read()
f.close()
if not _raw:
raise RuntimeError('Could not fetch index from %s'%url_or_raw)
else:
_raw = url_or_raw
if raw:
return _raw
def dump_hex(self, src, length=16):
''' Diagnostic '''
FILTER=''.join([(len(repr(chr(x)))==3) and chr(x) or '.' for x in range(256)])
N=0; result=''
while src:
s,src = src[:length],src[length:]
hexa = ' '.join(["%02X"%ord(x) for x in s])
s = s.translate(FILTER)
result += "%04X %-*s %s\n" % (N, length*3, hexa, s)
N+=length
print result
if not isinstance(_raw, unicode) and self.encoding:
_raw = _raw.decode(docEncoding, 'replace')
massage = list(BeautifulSoup.MARKUP_MASSAGE)
massage.append((re.compile(r'&(\S+?);'), lambda match: entity_to_unicode(match, encoding=self.encoding)))
return BeautifulSoup(_raw, markupMassage=massage)
def fixChars(self,string):
# Replace lsquo (\x91)
fixed = re.sub("\x91","&#8216;",string)
# Entry point
print "index_to_soup()"
soup = get_the_soup( self.encoding, url_or_raw )
contentType = soup.find(True,attrs={'http-equiv':'Content-Type'})
docEncoding = str(contentType)[str(contentType).find('charset=') + len('charset='):str(contentType).rfind('"')]
if docEncoding == '' :
docEncoding = self.encoding
# Replace rsquo (\x92)
fixed = re.sub("\x92","&#8217;",fixed)
if self.verbose > 2:
self.log( " document encoding: '%s'" % docEncoding)
if docEncoding != self.encoding :
soup = get_the_soup(docEncoding, url_or_raw)
# Replace ldquo (\x93)
fixed = re.sub("\x93","&#8220;",fixed)
# Replace rdquo (\x94)
fixed = re.sub("\x94","&#8221;",fixed)
# Replace ndash (\x96)
fixed = re.sub("\x96","&#8211;",fixed)
# Replace mdash (\x97)
fixed = re.sub("\x97","&#8212;",fixed)
return fixed
return soup
def massageNCXText(self, description):
# Kindle TOC descriptions won't render certain characters
if description:
massaged = unicode(BeautifulStoneSoup(description, convertEntities=BeautifulStoneSoup.HTML_ENTITIES))
# Replace '&' with '&#38;'
massaged = re.sub("&","&#38;", massaged)
# Replace '&' with '&'
massaged = re.sub("&","&", massaged)
return self.fixChars(massaged)
else:
return description
def parse_index(self):
soup = self.index_to_soup('http://www.nytimes.com/pages/todayspaper/index.html')
def parse_todays_index(self):
def feed_title(div):
return ''.join(div.findAll(text=True, recursive=False)).strip()
return ''.join(div.findAll(text=True, recursive=True)).strip()
articles = {}
key = None
ans = []
# Find each instance of class="section-headline", class="story", class="story headline"
for div in soup.findAll(True,
attrs={'class':['section-headline', 'story', 'story headline']}):
url_list = []
if div['class'] == 'section-headline':
key = string.capwords(feed_title(div))
if self.excludeSectionKeywords:
excluded = re.compile('|'.join(self.excludeSectionKeywords))
if excluded.search(key):
self.log("Skipping section %s" % key)
continue
articles[key] = []
ans.append(key)
elif div['class'] in ['story', 'story headline'] :
a = div.find('a', href=True)
if not a:
continue
url = re.sub(r'\?.*', '', a['href'])
url += '?pagewanted=all'
title = self.massageNCXText(self.tag_to_string(a, use_alt=True).strip())
description = ''
pubdate = strftime('%a, %d %b')
summary = div.find(True, attrs={'class':'summary'})
if summary:
description = self.massageNCXText(self.tag_to_string(summary, use_alt=False))
author = ''
authorAttribution = div.find(True, attrs={'class':'storyheadline-author'})
def handle_article(div):
a = div.find('a', href=True)
if not a:
return
url = re.sub(r'\?.*', '', a['href'])
if not url.startswith("http"):
return
if not url.endswith(".html"):
return
if 'podcast' in url:
return
if '/video/' in url:
return
url += '?pagewanted=all'
if url in url_list:
return
url_list.append(url)
title = self.tag_to_string(a, use_alt=True).strip()
description = ''
pubdate = strftime('%a, %d %b')
summary = div.find(True, attrs={'class':'summary'})
if summary:
description = self.tag_to_string(summary, use_alt=False)
author = ''
authorAttribution = div.find(True, attrs={'class':'byline'})
if authorAttribution:
author = self.tag_to_string(authorAttribution, use_alt=False)
else:
authorAttribution = div.find(True, attrs={'class':'byline'})
if authorAttribution:
author = self.tag_to_string(authorAttribution, use_alt=False)
else:
authorAttribution = div.find(True, attrs={'class':'byline'})
if authorAttribution:
author = self.tag_to_string(authorAttribution, use_alt=False)
# Kill commas - Kindle switches to '&'
author = re.sub(',','',author)
feed = key if key is not None else 'Uncategorized'
if not articles.has_key(feed):
ans.append(feed)
articles[feed] = []
articles[feed].append(
dict(title=title, url=url, date=pubdate,
description=description, author=author,
content=''))
soup = self.index_to_soup('http://www.nytimes.com/pages/todayspaper/index.html')
# Find each article
for div in soup.findAll(True,
attrs={'class':['section-headline', 'story', 'story headline','sectionHeader','headlinesOnly multiline flush']}):
if div['class'] in ['section-headline','sectionHeader']:
key = string.capwords(feed_title(div))
key = key.replace('Op-ed','Op-Ed')
key = key.replace('U.s.','U.S.')
elif div['class'] in ['story', 'story headline'] :
handle_article(div)
elif div['class'] == 'headlinesOnly multiline flush':
for lidiv in div.findAll('li'):
handle_article(lidiv)
feed = key if key is not None else 'Uncategorized'
if not articles.has_key(feed):
articles[feed] = []
if not 'podcasts' in url:
articles[feed].append(
dict(title=title, url=url, date=pubdate,
description=description, author=author,
content=''))
ans = self.sort_index_by(ans, {'The Front Page':-1,
'Dining In, Dining Out':1,
'Obituaries':2})
ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
self.dump_ans(ans)
return ans
return self.filter_ans(ans)
def parse_headline_index(self):
articles = {}
ans = []
url_list = []
soup = self.index_to_soup('http://www.nytimes.com/pages/todaysheadlines/')
# Fetch the content table
content_table = soup.find('table',{'id':'content'})
if content_table is None:
self.log("FATAL ERROR: CANNOT FIND CONTENT TABLE")
return None
# Within this table are <td id=".*Column.*"> entries, each containing one or more h6 tags which represent sections
for td_col in content_table.findAll('td', {'id' : re.compile('Column')}):
for div_sec in td_col.findAll('div',recursive=False):
for h6_sec_name in div_sec.findAll('h6',{'style' : re.compile('text-transform: *uppercase')}):
section_name = self.tag_to_string(h6_sec_name,use_alt=False)
section_name = re.sub(r'^ *$','',section_name)
if section_name == '':
continue
section_name=string.capwords(section_name)
if section_name == 'U.s.':
section_name = 'U.S.'
elif section_name == 'Op-ed':
section_name = 'Op-Ed'
pubdate = strftime('%a, %d %b')
search_div = div_sec
for next_tag in h6_sec_name.findNextSiblings(True):
if next_tag.__class__.__name__ == 'Tag':
if next_tag.name == 'div':
search_div = next_tag
break
# Get the articles
for h3_item in search_div.findAll('h3'):
byline = h3_item.h6
if byline is not None:
author = self.tag_to_string(byline,usa_alt=False)
else:
author = ''
a = h3_item.find('a', href=True)
if not a:
continue
url = re.sub(r'\?.*', '', a['href'])
if not url.startswith("http"):
continue
if not url.endswith(".html"):
continue
if 'podcast' in url:
continue
if 'video' in url:
continue
url += '?pagewanted=all'
if url in url_list:
continue
url_list.append(url)
self.log("URL %s" % url)
title = self.tag_to_string(a, use_alt=True).strip()
desc = h3_item.find('p')
if desc is not None:
description = self.tag_to_string(desc,use_alt=False)
else:
description = ''
if not articles.has_key(section_name):
ans.append(section_name)
articles[section_name] = []
articles[section_name].append(dict(title=title, url=url, date=pubdate, description=description, author=author, content=''))
ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
return self.filter_ans(ans)
def parse_index(self):
if self.headlinesOnly:
return self.parse_headline_index()
else:
return self.parse_todays_index()
def strip_anchors(self,soup):
paras = soup.findAll(True)
for para in paras:
aTags = para.findAll('a')
for a in aTags:
if a.img is None:
a.replaceWith(a.renderContents().decode('cp1252','replace'))
return soup
def skip_ad_pages(self, soup):
# Skip ad pages served before actual article
skip_tag = soup.find(True, {'name':'skip'})
if skip_tag is not None:
self.log.warn("Found forwarding link: %s" % skip_tag.parent['href'])
url = 'http://www.nytimes.com' + re.sub(r'\?.*', '', skip_tag.parent['href'])
url += '?pagewanted=all'
self.log.warn("Skipping ad to article at '%s'" % url)
return self.index_to_soup(url, raw=True)
def preprocess_html(self, soup):
kicker_tag = soup.find(attrs={'class':'kicker'})
if kicker_tag: # remove Op_Ed author head shots
tagline = self.tag_to_string(kicker_tag)
if tagline=='Op-Ed Columnist':
img_div = soup.find('div','inlineImage module')
if img_div:
img_div.extract()
return self.strip_anchors(soup)
def postprocess_html(self,soup, True):
print "\npostprocess_html()\n"
if self.one_picture_per_article:
# Remove all images after first
@ -312,8 +462,9 @@ class NYTimes(BasicNewsRecipe):
firstImg = inlineImgs[0]
for inlineImg in inlineImgs[1:]:
inlineImg.extract()
# Move firstImg after headline
cgFirst = soup.find(True, {'class':'columnGroup first'})
# Move firstImg before article body
#article_body = soup.find(True, {'id':'articleBody'})
cgFirst = soup.find(True, {'class':re.compile('columnGroup *first')})
if cgFirst:
# Strip all sibling NavigableStrings: noise
navstrings = cgFirst.findAll(text=True, recursive=False)
@ -333,30 +484,18 @@ class NYTimes(BasicNewsRecipe):
if headline_found:
cgFirst.insert(insertLoc,firstImg)
else:
self.log(">>> No class:'columnGroup first' found <<<")
# Change class="kicker" to <h3>
kicker = soup.find(True, {'class':'kicker'})
if kicker and kicker.contents and kicker.contents[0]:
h3Tag = Tag(soup, "h3")
h3Tag.insert(0, self.fixChars(self.tag_to_string(kicker,
use_alt=False)))
kicker.replaceWith(h3Tag)
self.log(">>> No class:'columnGroup first' found <<<")
# Change captions to italic -1
# Change captions to italic
for caption in soup.findAll(True, {'class':'caption'}) :
if caption and caption.contents[0]:
emTag = Tag(soup, "em")
cTag = Tag(soup, "p", [("class", "caption")])
c = self.fixChars(self.tag_to_string(caption,use_alt=False)).strip()
mp_off = c.find("More Photos")
if mp_off >= 0:
c = c[:mp_off]
emTag.insert(0, c)
#hrTag = Tag(soup, 'hr')
#hrTag['class'] = 'caption_divider'
hrTag = Tag(soup, 'div')
hrTag['class'] = 'divider'
emTag.insert(1, hrTag)
caption.replaceWith(emTag)
cTag.insert(0, c)
caption.replaceWith(cTag)
# Change <nyt_headline> to <h2>
h1 = soup.find('h1')
@ -396,17 +535,6 @@ class NYTimes(BasicNewsRecipe):
bTag.insert(0, subhead.contents[0])
subhead.replaceWith(bTag)
# Synthesize a section header
dsk = soup.find('meta', attrs={'name':'dsk'})
if dsk and dsk.has_key('content'):
hTag = Tag(soup,'h3')
hTag['class'] = 'section'
hTag.insert(0,NavigableString(dsk['content']))
articleTag = soup.find(True, attrs={'id':'article'})
if articleTag:
articleTag.insert(0,hTag)
# Add class="articleBody" to <div> so we can format with CSS
divTag = soup.find('div',attrs={'id':'articleBody'})
if divTag:
divTag['class'] = divTag['id']
@ -422,56 +550,3 @@ class NYTimes(BasicNewsRecipe):
return soup
def populate_article_metadata(self,article,soup,first):
'''
Extract author and description from article, add to article metadata
'''
def extract_author(soup):
byline = soup.find('meta',attrs={'name':['byl','CLMST']})
if byline :
author = byline['content']
else :
# Try for <div class="byline">
byline = soup.find('div', attrs={'class':'byline'})
if byline:
author = byline.renderContents()
else:
print soup.prettify()
return None
return author
def extract_description(soup):
description = soup.find('meta',attrs={'name':['description','description ']})
if description :
return self.massageNCXText(description['content'])
else:
# Take first paragraph of article
articlebody = soup.find('div',attrs={'id':'articlebody'})
if not articlebody:
# Try again with class instead of id
articlebody = soup.find('div',attrs={'class':'articlebody'})
if not articlebody:
print 'postprocess_book.extract_description(): Did not find <div id="articlebody">:'
print soup.prettify()
return None
paras = articlebody.findAll('p')
for p in paras:
if p.renderContents() > '' :
return self.massageNCXText(self.tag_to_string(p,use_alt=False))
return None
if not article.author:
article.author = extract_author(soup)
if not article.summary:
article.summary = article.text_summary = extract_description(soup)
def strip_anchors(self,soup):
paras = soup.findAll(True)
for para in paras:
aTags = para.findAll('a')
for a in aTags:
if a.img is None:
a.replaceWith(a.renderContents().decode('utf-8','replace'))
#a.replaceWith(a.renderContents().decode('cp1252','replace'))
return soup

93
resources/recipes/nzherald.recipe
View File

@ -1,74 +1,43 @@
from calibre.web.feeds.recipes import BasicNewsRecipe
import re
class NewZealandHerald(BasicNewsRecipe):
title = 'New Zealand Herald'
__author__ = 'Krittika Goyal'
__author__ = 'Kovid Goyal'
description = 'Daily news'
timefmt = ' [%d %b, %Y]'
language = 'en_NZ'
oldest_article = 2.5
no_stylesheets = True
remove_tags_before = dict(name='div', attrs={'class':'contentContainer left eight'})
remove_tags_after = dict(name='div', attrs={'class':'callToAction'})
remove_tags = [
dict(name='iframe'),
dict(name='div', attrs={'class':['sectionHeader', 'tools','callToAction', 'contentContainer right two nopad relatedColumn']}),
#dict(name='div', attrs={'id':['shareContainer']}),
#dict(name='form', attrs={'onsubmit':"return verifySearch(this.w,'Keyword, citation, or #author')"}),
#dict(name='table', attrs={'cellspacing':'0'}),
feeds = [
('Business',
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000003.xml'),
('World',
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000002.xml'),
('National',
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000001.xml'),
('Entertainment',
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_001501119.xml'),
('Travel',
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000007.xml'),
('Opinion',
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000466.xml'),
('Life & Style',
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000006.xml'),
('Technology'
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000005.xml'),
('Sport',
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000004.xml'),
('Motoring',
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000009.xml'),
('Property',
'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000008.xml'),
]
def preprocess_html(self, soup):
table = soup.find('table')
if table is not None:
table.extract()
return soup
#TO GET ARTICLES IN SECTION
def nz_parse_section(self, url):
soup = self.index_to_soup(url)
div = soup.find(attrs={'class':'col-300 categoryList'})
date = div.find(attrs={'class':'link-list-heading'})
current_articles = []
for x in date.findAllNext(attrs={'class':['linkList', 'link-list-heading']}):
if x.get('class') == 'link-list-heading': break
for li in x.findAll('li'):
a = li.find('a', href=True)
if a is None:
continue
title = self.tag_to_string(a)
url = a.get('href', False)
if not url or not title:
continue
if url.startswith('/'):
url = 'http://www.nzherald.co.nz'+url
self.log('\t\tFound article:', title)
self.log('\t\t\t', url)
current_articles.append({'title': title, 'url':url,
'description':'', 'date':''})
return current_articles
# To GET SECTIONS
def parse_index(self):
feeds = []
for title, url in [
('National',
'http://www.nzherald.co.nz/nz/news/headlines.cfm?c_id=1'),
('World',
'http://www.nzherald.co.nz/world/news/headlines.cfm?c_id=2'),
('Politics',
'http://www.nzherald.co.nz/politics/news/headlines.cfm?c_id=280'),
('Crime',
'http://www.nzherald.co.nz/crime/news/headlines.cfm?c_id=30'),
('Environment',
'http://www.nzherald.co.nz/environment/news/headlines.cfm?c_id=39'),
]:
articles = self.nz_parse_section(url)
if articles:
feeds.append((title, articles))
return feeds
def print_version(self, url):
m = re.search(r'objectid=(\d+)', url)
if m is None:
return url
return 'http://www.nzherald.co.nz/news/print.cfm?pnum=1&objectid=' + m.group(1)

25
resources/recipes/pagina12.recipe
View File

@ -21,8 +21,16 @@ class Pagina12(BasicNewsRecipe):
use_embedded_content = False
language = 'es'
remove_empty_feeds = True
publication_type = 'newspaper'
masthead_url = 'http://www.pagina12.com.ar/commons/imgs/logo-home.gif'
extra_css = ' body{font-family: Arial,Helvetica,sans-serif } img{margin-bottom: 0.4em} #autor{font-weight: bold} #fecha,#epigrafe{font-size: 0.9em; margin: 5px} #imagen{border: 1px solid black; margin: 0 0 1.25em 1.25em; width: 232px } '
extra_css = """
body{font-family: Arial,Helvetica,sans-serif }
img{margin-bottom: 0.4em; display:block}
#autor{font-weight: bold}
#fecha,#epigrafe{font-size: 0.9em; margin: 5px}
#imagen{border: 1px solid black; margin: 0 0 1.25em 1.25em; width: 232px }
.fgprincipal{font-size: large; font-weight: bold}
"""
conversion_options = {
'comment' : description
@ -31,7 +39,11 @@ class Pagina12(BasicNewsRecipe):
, 'language' : language
}
remove_tags = [dict(name='div', attrs={'id':['volver','logo','logo_suple','fin','permalink']})]
remove_tags = [
dict(name=['meta','link'])
,dict(name='div', attrs={'id':['volver','logo','logo_suple','fin','permalink']})
]
remove_attributes=['lang']
feeds = [
@ -65,4 +77,13 @@ class Pagina12(BasicNewsRecipe):
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll('span', attrs={'id':'seccion'}):
it = item.a
it.name='span'
del it['href']
del it['title']
for item in soup.findAll('p'):
it = item.find('h3')
if it:
it.name='span'
return soup

70
resources/recipes/pc_lab.recipe Normal file
View File

@ -0,0 +1,70 @@
#!/usr/bin/env python
from calibre.web.feeds.recipes import BasicNewsRecipe
class PCLab(BasicNewsRecipe):
cover_url = 'http://pclab.pl/img/logo.png'
title = u"PC Lab"
__author__ = 'ravcio - rlelusz[at]gmail.com'
description = u"Articles from PC Lab website"
language = 'pl'
oldest_article = 30.0
max_articles_per_feed = 100
recursions = 0
encoding = 'iso-8859-2'
no_stylesheets = True
remove_javascript = True
use_embedded_content = False
keep_only_tags = [
dict(name='div', attrs={'class':['substance']})
]
remove_tags = [
dict(name='div', attrs={'class':['chapters']})
,dict(name='div', attrs={'id':['script_bxad_slot_display_list_bxad_slot']})
]
remove_tags_after = [
dict(name='div', attrs={'class':['navigation']})
]
#links to RSS feeds
feeds = [ ('PCLab', u'http://pclab.pl/xml/artykuly.xml') ]
#load second and subsequent page content
# in: soup - full page with 'next' button
# out: appendtag - tag to which new page is to be added
def append_page(self, soup, appendtag):
# find the 'Next' button
pager = soup.find('div', attrs={'class':'next'})
if pager:
#search for 'a' element with link to next page (exit if not found)
a = pager.find('a')
if a:
nexturl = a['href']
soup2 = self.index_to_soup('http://pclab.pl/' + nexturl)
pagetext_substance = soup2.find('div', attrs={'class':'substance'})
pagetext = pagetext_substance.find('div', attrs={'class':'data'})
pagetext.extract()
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
pos = len(appendtag.contents)
self.append_page(soup2, appendtag)
def preprocess_html(self, soup):
# soup.body contains no title and no navigator, they are in soup
self.append_page(soup, soup.body)
# finally remove some tags
tags = soup.findAll('div',attrs={'class':['tags', 'index', 'script_bxad_slot_display_list_bxad_slot', 'index first', 'zumi', 'navigation']})
[tag.extract() for tag in tags]
return soup

66
resources/recipes/perfil.recipe Normal file
View File

@ -0,0 +1,66 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
perfil.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Perfil(BasicNewsRecipe):
title = 'Perfil'
__author__ = 'Darko Miletic'
description = 'Noticias de Argentina y el resto del mundo'
publisher = 'perfil.com'
category = 'news, politics, Argentina'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'cp1252'
use_embedded_content = False
language = 'es'
remove_empty_feeds = True
masthead_url = 'http://www.perfil.com/export/sites/diarioperfil/arte/10/logo_perfilcom_mm.gif'
extra_css = """
body{font-family: Arial,Helvetica,sans-serif }
.seccion{border-bottom: 1px dotted #666666; text-transform: uppercase; font-size: x-large}
.foto1 h1{font-size: x-small}
h1{font-family: Georgia,"Times New Roman",serif}
img{margin-bottom: 0.4em}
"""
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
remove_tags = [
dict(name=['iframe','embed','object','base','meta','link'])
,dict(name='a', attrs={'href':'#comentarios'})
,dict(name='div', attrs={'class':'foto3'})
,dict(name='img', attrs={'alt':'ampliar'})
]
keep_only_tags=[dict(attrs={'class':['bd468a','cuerpoSuperior']})]
remove_attributes=['onload','lang','width','height','border']
feeds = [
(u'Ultimo momento' , u'http://www.perfil.com/rss/ultimomomento.xml')
,(u'Politica' , u'http://www.perfil.com/rss/politica.xml' )
,(u'Policia' , u'http://www.perfil.com/rss/policia.xml' )
,(u'Internacionales', u'http://www.perfil.com/rss/internacional.xml')
,(u'Economia' , u'http://www.perfil.com/rss/economia.xml' )
,(u'Deportes' , u'http://www.perfil.com/rss/deportes.xml' )
,(u'Opinion' , u'http://www.perfil.com/rss/columnistas.xml' )
,(u'Sociedad' , u'http://www.perfil.com/rss/sociedad.xml' )
,(u'Cultura' , u'http://www.perfil.com/rss/cultura.xml' )
,(u'Espectaculos' , u'http://www.perfil.com/rss/espectaculos.xml' )
,(u'Ciencia' , u'http://www.perfil.com/rss/ciencia.xml' )
,(u'Salud' , u'http://www.perfil.com/rss/salud.xml' )
,(u'Tecnologia' , u'http://www.perfil.com/rss/tecnologia.xml' )
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup

73
resources/recipes/politika.recipe
View File

@ -1,13 +1,10 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
'''
politika.rs
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class Politika(BasicNewsRecipe):
title = 'Politika Online'
@ -19,53 +16,51 @@ class Politika(BasicNewsRecipe):
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
remove_javascript = True
encoding = 'utf8'
language = 'sr'
lang = 'sr-Latn-RS'
direction = 'ltr'
extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: sans1, sans-serif}'
delay = 1
language = 'sr'
publication_type = 'newspaper'
masthead_url = 'http://static.politika.co.rs/images_new/politika.gif'
extra_css = """
@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)}
@font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)}
body{font-family: Arial,Helvetica,sans1,sans-serif}
h1{font-family: "Times New Roman",Times,serif1,serif}
.articledescription{font-family: sans1, sans-serif}
"""
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : lang
, 'pretty_print' : True
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
keep_only_tags = [dict(name='div', attrs={'class':'content_center_border'})]
remove_tags = [
dict(name='div', attrs={'class':['send_print','txt-komentar']})
,dict(name=['object','link','a'])
,dict(name='h1', attrs={'class':'box_header-tags'})
]
keep_only_tags = [dict(name='div', attrs={'class':'big_article_home item_details'})]
remove_tags_after = dict(attrs={'class':'online_date'})
remove_tags = [dict(name=['link','meta','iframe','embed','object'])]
feeds = [
(u'Politika' , u'http://www.politika.rs/rubrike/Politika/index.1.lt.xml' )
,(u'Svet' , u'http://www.politika.rs/rubrike/Svet/index.1.lt.xml' )
,(u'Redakcijski komentari', u'http://www.politika.rs/rubrike/redakcijski-komentari/index.1.lt.xml')
,(u'Pogledi' , u'http://www.politika.rs/pogledi/index.lt.xml' )
,(u'Pogledi sa strane' , u'http://www.politika.rs/rubrike/Pogledi-sa-strane/index.1.lt.xml' )
,(u'Tema dana' , u'http://www.politika.rs/rubrike/tema-dana/index.1.lt.xml' )
,(u'Kultura' , u'http://www.politika.rs/rubrike/Kultura/index.1.lt.xml' )
,(u'Zivot i stil' , u'http://www.politika.rs/rubrike/zivot-i-stil/index.1.lt.xml' )
(u'Politika' , u'http://www.politika.rs/rubrike/Politika/index.1.lt.xml' )
,(u'Svet' , u'http://www.politika.rs/rubrike/Svet/index.1.lt.xml' )
,(u'Ostali komentari' , u'http://www.politika.rs/rubrike/ostali-komentari/index.1.lt.xml' )
,(u'Pogledi' , u'http://www.politika.rs/pogledi/index.lt.xml' )
,(u'Pogledi sa strane', u'http://www.politika.rs/rubrike/Pogledi-sa-strane/index.1.lt.xml')
,(u'Tema dana' , u'http://www.politika.rs/rubrike/tema-dana/index.1.lt.xml' )
,(u'Kultura' , u'http://www.politika.rs/rubrike/Kultura/index.1.lt.xml' )
,(u'Spektar' , u'http://www.politika.rs/rubrike/zivot-i-stil/index.1.lt.xml' )
]
def preprocess_html(self, soup):
soup.html['lang'] = self.lang
soup.html['dir' ] = self.direction
mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
soup.head.insert(0,mlang)
for item in soup.findAll(style=True):
del item['style']
ftag = soup.find('div',attrs={'class':'content_center_border'})
if ftag.has_key('align'):
del ftag['align']
return self.adeify_images(soup)
for item in soup.findAll('a', attrs={'class':'category'}):
item.name='span'
if item.has_key('href'):
del item['href']
if item.has_key('title'):
del item['title']
return soup

68
resources/recipes/polityka.recipe Normal file
View File

@ -0,0 +1,68 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2010, Mateusz Kielar, matek09@gmail.com'
from calibre.web.feeds.news import BasicNewsRecipe
class Polityka(BasicNewsRecipe):
title = u'Polityka'
__author__ = 'Mateusz Kielar'
description = 'Weekly magazine. Last archive issue'
encoding = 'utf-8'
no_stylesheets = True
language = 'en'
remove_javascript = True
remove_tags_before = dict(dict(name = 'h2', attrs = {'class' : 'box_nag'}))
remove_tags_after = dict(dict(name = 'div', attrs = {'class' : 'box_footer'}))
remove_tags =[]
remove_tags.append(dict(name = 'h2', attrs = {'class' : 'box_nag'}))
remove_tags.append(dict(name = 'div', attrs = {'class' : 'box_footer'}))
extra_css = '''
h1 {font-size: x-large; font-weight: bold}
'''
def parse_index(self):
soup = self.index_to_soup('http://archiwum.polityka.pl/')
box_img3 = soup.findAll(attrs={'class' : 'box_img3'})
feeds = []
last = 0
self.cover_url = 'http://archiwum.polityka.pl' + box_img3[-1].find('img')['src']
last_edition = 'http://archiwum.polityka.pl' + box_img3[-1].find('a')['href']
while True:
index = self.index_to_soup(last_edition)
box_list = index.findAll('div', attrs={'class' : 'box_list'})
if len(box_list) == 0:
break
articles = {}
for box in box_list:
for div in box.findAll('div', attrs={'class': 'list_tresc'}):
article_page = self.index_to_soup('http://archiwum.polityka.pl' + div.a['href'],)
section = self.tag_to_string(article_page.find('h2', attrs = {'class' : 'box_nag'})).split('/')[0].lstrip().rstrip()
print section
if not articles.has_key(section):
articles[section] = []
articles[section].append( {
'title' : self.tag_to_string(div.a),
'url' : 'http://archiwum.polityka.pl' + div.a['href'],
'date' : '',
'description' : ''
})
for section in articles:
feeds.append((section, articles[section]))
last_edition = last_edition.replace('http://archiwum.polityka.pl/wydanie/' + str(last), 'http://archiwum.polityka.pl/wydanie/' + str(last + 1))
last = last + 1
return feeds

69
resources/recipes/rollingstone.recipe Normal file
View File

@ -0,0 +1,69 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
rollingstone.com
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class RollingStone(BasicNewsRecipe):
title = 'Rolling Stone Magazine - free content'
__author__ = 'Darko Miletic'
description = 'Rolling Stone Magazine features music, album and artist news, movie reviews, political, economic and pop culture commentary, videos, photos, and more.'
publisher = 'Werner Media inc.'
category = 'news, music, USA, world'
oldest_article = 15
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
language = 'en'
remove_empty_feeds = True
publication_type = 'magazine'
masthead_url = 'http://www.rollingstone.com/templates/rolling-stone-templates/theme/rstheme/images/rsLogo.png'
extra_css = """
body{font-family: Georgia,Times,serif }
img{margin-bottom: 0.4em; display:block}
"""
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
preprocess_regexps = [
(re.compile(r'xml:lang="en">.*?<head>', re.DOTALL|re.IGNORECASE),lambda match: 'xml:lang="en">\n<head>\n')
,(re.compile(r'</title>.*?</head>' , re.DOTALL|re.IGNORECASE),lambda match: '</title>\n</head>\n' )
]
keep_only_tags=[
dict(attrs={'class':['headerImgHolder','headerContent']})
,dict(name='div',attrs={'id':['teaser','storyTextContainer']})
,dict(name='div',attrs={'class':'blogDetailModule clearfix'})
]
remove_tags = [
dict(name=['meta','iframe','object','embed'])
,dict(attrs={'id':'mpStoryHeader'})
,dict(attrs={'class':'relatedTopics'})
]
remove_attributes=['lang','onclick','width','height','name']
remove_tags_before=dict(attrs={'class':'bloggerInfo'})
remove_tags_after=dict(attrs={'class':'relatedTopics'})
feeds = [
(u'All News' , u'http://www.rollingstone.com/siteServices/rss/allNews' )
,(u'All Blogs' , u'http://www.rollingstone.com/siteServices/rss/allBlogs' )
,(u'Movie Reviews' , u'http://www.rollingstone.com/siteServices/rss/movieReviews' )
,(u'Album Reviews' , u'http://www.rollingstone.com/siteServices/rss/albumReviews' )
,(u'Song Reviews' , u'http://www.rollingstone.com/siteServices/rss/songReviews' )
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup

53
resources/recipes/rue89.recipe Normal file
View File

@ -0,0 +1,53 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Louis Gesbert <meta at antislash dot info>'
'''
Rue89
'''
__author__ = '2010, Louis Gesbert <meta at antislash dot info>'
import re
from calibre.ebooks.BeautifulSoup import Tag
from calibre.web.feeds.news import BasicNewsRecipe
class Rue89(BasicNewsRecipe):
title = 'Rue89'
__author__ = 'Louis Gesbert'
description = 'Popular free french news website'
title = u'Rue89'
language = 'fr'
oldest_article = 7
max_articles_per_feed = 50
feeds = [(u'La Une', u'http://www.rue89.com/homepage/feed')]
no_stylesheets = True
preprocess_regexps = [
(re.compile(r'<(/?)h2>', re.IGNORECASE|re.DOTALL),
lambda match : '<'+match.group(1)+'h3>'),
(re.compile(r'<div class="print-title">([^>]+)</div>', re.IGNORECASE|re.DOTALL),
lambda match : '<h2>'+match.group(1)+'</h2>'),
(re.compile(r'<img[^>]+src="[^"]*/numeros/(\d+)[^0-9.">]*.gif"[^>]*/>', re.IGNORECASE|re.DOTALL),
lambda match : '<span style="font-family: Sans-serif; color: red; font-size:24pt; padding=2pt;">'+match.group(1)+'</span>'),
(re.compile(r'\''), lambda match: '&rsquo;'),
]
def preprocess_html(self,soup):
body = Tag(soup, 'body')
title = soup.find('h1', {'class':'title'})
content = soup.find('div', {'class':'content'})
soup.body.replaceWith(body)
body.insert(0, title)
body.insert(1, content)
return soup
remove_tags = [ #dict(name='div', attrs={'class':'print-source_url'}),
#dict(name='div', attrs={'class':'print-links'}),
#dict(name='img', attrs={'class':'print-logo'}),
dict(name='div', attrs={'class':'content_top'}),
dict(name='div', attrs={'id':'sidebar-left'}), ]
# -- print-version has poor quality on this website, better do the conversion ourselves
# def print_version(self, url):
# return re.sub('^.*-([0-9]+)$', 'http://www.rue89.com/print/\\1',url)

73
resources/recipes/scprint.recipe Normal file
View File

@ -0,0 +1,73 @@
from calibre.web.feeds.news import BasicNewsRecipe, LoginFailed
class SCPrintMagazine(BasicNewsRecipe):
title = u'SC Print Magazine'
__author__ = u'Tony Maro'
description = u'Last print version of the data security magazine'
INDEX = "http://www.scmagazineus.com/issuearchive/"
no_stylesheets = True
language = 'en'
keep_only_tags = [dict(id=['article','review'])]
remove_tags = [dict(id=['articlePrintTools','reviewBodyColumn'])]
LOG_IN = 'http://www.scmagazineus.com/login/'
tags = 'News,SC Magazine'
needs_subscription = True
def parse_index(self):
articles = []
issuelink = printsections = None
soup = self.index_to_soup(self.INDEX)
sectit = soup.find('div', attrs={'class':'issueArchiveItem'})
if sectit is not None:
linkt = sectit.find('a')
issuelink = linkt['href']
imgt = sectit.find('img')
self.cover_url = imgt['src']
if issuelink is not None:
issue = self.index_to_soup(issuelink)
if issue is not None:
printsections = issue.findAll('div',attrs={'class':'PrintSection'})
if printsections is not None:
for printsection in printsections:
onesection = []
sectiontitle = printsection.find('h3').contents[0]
articlesec = printsection.findAll('div',attrs={'class':'IssueArchiveFormat'})
if articlesec is not None:
''' got articles '''
for onearticle in articlesec:
''' process one article '''
arttitlet = onearticle.find('h3')
if arttitlet is not None:
mylink = arttitlet.find('a')
if mylink is not None:
if mylink.has_key('title'):
arttitle = mylink['title']
else:
arttitle = 'unknown'
if mylink.has_key('href'):
artlink = mylink['href']
artlink = artlink.replace("/article","/printarticle")
artlink = artlink.replace("/review","/printreview")
deck = onearticle.find('div',attrs={'class':'deck'})
if deck is not None:
deck = deck.contents[0]
onesection.append({'title':arttitle, 'url':artlink, 'description':deck,'date':''})
articles.append((sectiontitle, onesection))
return articles
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
br.open(self.LOG_IN)
br.select_form(name='aspnetForm')
br['ctl00$ctl00$cphAllPageContent$cphMainContent$SubscriberEasyLoginView1$txtEmail'] = self.username
br['ctl00$ctl00$cphAllPageContent$cphMainContent$SubscriberEasyLoginView1$txtPassword'] = self.password
raw = br.submit("ctl00$ctl00$cphAllPageContent$cphMainContent$SubscriberEasyLoginView1$btnLogin").read()
if 'Logout</a>' not in raw:
raise LoginFailed(
_('Failed to log in, check your username and password for'
' the calibre Periodicals service.'))
return br

55
resources/recipes/siol.recipe Normal file
View File

@ -0,0 +1,55 @@
# coding: utf-8
__license__ = 'GPL v3'
__copyright__ = '2010, BlonG'
'''
www.siol.si
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Siol(BasicNewsRecipe):
title = u'Siol.net'
__author__ = u'BlonG'
description = "Multimedijski portal z aktualnimi vsebinami, intervjuji, komentarji iz Slovenije in sveta, sportal, trendi, avtomoto, blogos"
oldest_article = 3
language = 'sl'
max_articles_per_feed = 20
no_stylesheets = True
use_embedded_content = False
cover_url = 'https://sites.google.com/site/javno2010/home/siol_cover.jpg'
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
h2{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''
html2lrf_options = ['--base-font-size', '10']
keep_only_tags = [
dict(name='div', attrs={'id':'idContent'}),
]
remove_tags = [
dict(name='span', attrs={'class':'com1'}),
dict(name='div', attrs={'class':'relation'}),
dict(name='p', attrs={'class':'path'}),
dict(name='div', attrs={'class':'clear_r'}),
dict(name='div', attrs={'id':'appendix'}),
dict(name='div', attrs={'id':'rail'}),
dict(name='div', attrs={'id':'div_comments'}),
dict(name='div', attrs={'class':'thumbs'}),
]
feeds = [
(u'Slovenija', u'http://www.siol.net/rss.aspx?path=Slovenija')
,(u'Lokalne novice', u'http://www.siol.net/rss.aspx?path=Slovenija/Lokalne_novice')
,(u'EU', u'http://www.siol.net/rss.aspx?path=EU')
,(u'Svet', u'http://www.siol.net/rss.aspx?path=Svet')
,(u'Gospodarstvo', u'http://www.siol.net/rss.aspx?path=Gospodarstvo')
,(u'Sportal', u'http://www.siol.net/rss.aspx?path=Sportal')
,(u'Trendi', u'http://www.siol.net/rss.aspx?path=Trendi')
,(u'Avtomoto', u'http://www.siol.net/rss.aspx?path=Avtomoto')
,(u'Tehnologija', u'http://www.siol.net/rss.aspx?path=Tehnologija')
,(u'TV / Film', u'http://www.siol.net/rss.aspx?path=TV')
]

60
resources/recipes/stnn.recipe Normal file
View File

@ -0,0 +1,60 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Larry Chan <larry1chan at gmail.com>'
'''
Singtao STNN
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
class SingtaoSTNN(BasicNewsRecipe):
title = 'Singtao STNN'
__author__ = 'Larry Chan, larry1chan'
description = 'Chinese News'
oldest_article = 2
max_articles_per_feed = 100
simultaneous_downloads = 5
no_stylesheets = True
#delay = 1
use_embedded_content = False
encoding = 'gb2312'
publisher = 'Singtao STNN'
category = 'news, China, world'
language = 'zh'
publication_type = 'newsportal'
extra_css = ' body{ font-family: Verdana,Helvetica,Arial,sans-serif } .introduction{font-weight: bold} .story-feature{display: block; padding: 0; border: 1px solid; width: 40%; font-size: small} .story-feature h2{text-align: center; text-transform: uppercase} '
masthead_url = 'http://www.stnn.cc/images/0806/logo_080728.gif'
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
,'linearize_tables': True
}
remove_tags_before = dict(name='div', attrs={'class':['page_box']})
remove_tags_after = dict(name='div', attrs={'class':['pagelist']})
keep_only_tags = [
dict(name='div', attrs={'class':['font_title clearfix']}),
dict(name='div', attrs={'id':['content_zoom']})
]
remove_attributes = ['width','height','href']
# for a full list of rss check out [url]http://www.stnn.cc/rss/[/url]
feeds = [ (u'Headline News', u'http://www.stnn.cc/rss/news/index.xml'),
(u'Breaking News', u'http://www.stnn.cc/rss/tufa/index.xml'),
(u'Finance', u'http://www.stnn.cc/rss/fin/index.xml'),
(u'Entertainment', u'http://www.stnn.cc/rss/ent/index.xml'),
(u'International', u'http://www.stnn.cc/rss/guoji/index.xml'),
(u'China', u'http://www.stnn.cc/rss/china/index.xml'),
(u'Opnion', u'http://www.stnn.cc/rss/fin_op/index.xml'),
(u'Blog', u'http://blog.stnn.cc/uploadfile/rssblogtypehotlog.xml'),
(u'Hong Kong', u'http://www.stnn.cc/rss/hongkong/index.xml')
]

2
resources/recipes/tagesan.recipe
View File

@ -7,7 +7,7 @@ class AdvancedUserRecipe1284927619(BasicNewsRecipe):
__author__ = 'noxxx'
max_articles_per_feed = 100
description = 'tagesanzeiger.ch: Nichts verpassen'
category = 'News, Politik, Nachrichten, Schweiz, Zürich'
category = 'News, Politik, Nachrichten, Schweiz, Zuerich'
language = 'de'
conversion_options = {

24
resources/recipes/taggeschau_de.recipe Normal file
View File

@ -0,0 +1,24 @@
from calibre.web.feeds.news import BasicNewsRecipe
class Tagesschau(BasicNewsRecipe):
title = 'Tagesschau'
description = 'Nachrichten der ARD'
publisher = 'ARD'
language = 'de'
__author__ = 'Florian Andreas Pfaff'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
feeds = [('Tagesschau', 'http://www.tagesschau.de/xml/rss2')]
remove_tags = [
dict(name='div', attrs={'class':['linksZumThema schmal','teaserBox','boxMoreLinks','directLinks','teaserBox boxtext','fPlayer','zitatBox breit flashaudio']}),
dict(name='div',
attrs={'id':['socialBookmarks','seitenanfang']}),
dict(name='ul',
attrs={'class':['directLinks','directLinks weltatlas']}),
dict(name='strong', attrs={'class':['boxTitle inv','inv']})
]
keep_only_tags = [dict(name='div', attrs={'id':'centerCol'})]

46
resources/recipes/theecocolapse.recipe Normal file
View File

@ -0,0 +1,46 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
theeconomiccollapseblog.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class TheEconomicCollapse(BasicNewsRecipe):
title = 'The Economic Collapse'
__author__ = 'Darko Miletic'
description = 'Are You Prepared For The Coming Economic Collapse And The Next Great Depression?'
publisher = 'The Economic Collapse'
category = 'news, politics, USA, economy'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
language = 'en'
remove_empty_feeds = True
extra_css = """
body{font-family: Tahoma,Arial,sans-serif }
img{margin-bottom: 0.4em}
"""
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
remove_tags = [
dict(attrs={'class':'sociable'})
,dict(name=['iframe','object','embed','meta','link','base'])
]
remove_attributes=['lang','onclick','width','height']
keep_only_tags=[dict(attrs={'class':['post-headline','post-bodycopy clearfix','']})]
feeds = [(u'Posts', u'http://theeconomiccollapseblog.com/feed')]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return self.adeify_images(soup)

8
resources/recipes/theeconomictimes_india.recipe
View File

@ -21,8 +21,9 @@ class TheEconomicTimes(BasicNewsRecipe):
language = 'en_IN'
publication_type = 'newspaper'
masthead_url = 'http://economictimes.indiatimes.com/photo/2676871.cms'
extra_css = """ body{font-family: Arial,Helvetica,sans-serif}
.heading1{font-size: xx-large; font-weight: bold} """
extra_css = """
body{font-family: Arial,Helvetica,sans-serif}
"""
conversion_options = {
'comment' : description
@ -31,8 +32,9 @@ class TheEconomicTimes(BasicNewsRecipe):
, 'language' : language
}
keep_only_tags = [dict(attrs={'class':['heading1','headingnext','Normal']})]
keep_only_tags = [dict(attrs={'class':'printdiv'})]
remove_tags = [dict(name=['object','link','embed','iframe','base','table','meta'])]
remove_attributes = ['name']
feeds = [(u'All articles', u'http://economictimes.indiatimes.com/rssfeedsdefault.cms')]

195
resources/recipes/vedomosti.recipe Normal file
View File

@ -0,0 +1,195 @@
#!/usr/bin/env python
u'''
Ведомости
'''
from calibre.web.feeds.feedparser import parse
from calibre.ebooks.BeautifulSoup import Tag
from calibre.web.feeds.news import BasicNewsRecipe
class VedomostiRecipe(BasicNewsRecipe):
title = u'Ведомости'
__author__ = 'Nikolai Kotchetkov'
publisher = 'vedomosti.ru'
category = 'press, Russia'
description = u'Ежедневная деловая газета'
oldest_article = 3
max_articles_per_feed = 100
masthead_url = u'http://motorro.com/imgdir/logos/ved_logo_black2_cropped.gif'
cover_url = u'http://motorro.com/imgdir/logos/ved_logo_black2_cropped.gif'
#Add feed names if you want them to be sorted (feeds of this list appear first)
sortOrder = [u'_default', u'Первая полоса', u'Власть и деньги']
encoding = 'cp1251'
language = 'ru'
no_stylesheets = True
remove_javascript = True
recursions = 0
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags = [dict(name='td', attrs={'class' : ['second_content']})]
remove_tags_after = [dict(name='div', attrs={'class' : 'article_text'})]
remove_tags = [dict(name='div', attrs={'class' : ['sep', 'choice', 'articleRightTbl']})]
feeds = [u'http://www.vedomosti.ru/newspaper/out/rss.xml']
#base URL for relative links
base_url = u'http://www.vedomosti.ru'
extra_css = 'h1 {font-size: 1.5em; margin: 0em 0em 0em 0em; text-align: center;}'\
'h2 {font-size: 1.0em; margin: 0em 0em 0em 0em;}'\
'h3 {font-size: 0.8em; margin: 0em 0em 0em 0em;}'\
'.article_date {font-size: 0.5em; color: gray; font-family: monospace; text-align:right;}'\
'.article_authors {font-size: 0.5em; color: gray; font-family: monospace; text-align:right;}'\
'.article_img {width:100%; text-align: center; padding: 3px 3px 3px 3px;}'\
'.article_img_desc {width:100%; text-align: center; font-size: 0.5em; color: gray; font-family: monospace;}'\
'.article_desc {font-size: 1em; font-style:italic;}'
def parse_index(self):
try:
feedData = parse(self.feeds[0])
if not feedData:
raise NotImplementedError
self.log("parse_index: Feed loaded successfully.")
if feedData.feed.has_key('title'):
self.title = feedData.feed.title
self.log("parse_index: Title updated to: ", self.title)
if feedData.feed.has_key('description'):
self.description = feedData.feed.description
self.log("parse_index: Description updated to: ", self.description)
def get_virtual_feed_articles(feed):
if feeds.has_key(feed):
return feeds[feed][1]
self.log("Adding new feed: ", feed)
articles = []
feeds[feed] = (feed, articles)
return articles
feeds = {}
#Iterate feed items and distribute articles using tags
for item in feedData.entries:
link = item.get('link', '');
title = item.get('title', '');
if '' == link or '' == title:
continue
article = {'title':title, 'url':link, 'description':item.get('description', ''), 'date':item.get('date', ''), 'content':''};
if not item.has_key('tags'):
get_virtual_feed_articles('_default').append(article)
continue
for tag in item.tags:
addedToDefault = False
term = tag.get('term', '')
if '' == term:
if (not addedToDefault):
get_virtual_feed_articles('_default').append(article)
continue
get_virtual_feed_articles(term).append(article)
#Get feed list
#Select sorted feeds first of all
result = []
for feedName in self.sortOrder:
if (not feeds.has_key(feedName)): continue
result.append(feeds[feedName])
del feeds[feedName]
result = result + feeds.values()
return result
except Exception, err:
self.log(err)
raise NotImplementedError
def preprocess_html(self, soup):
return self.adeify_images(soup)
def postprocess_html(self, soup, first_fetch):
#self.log('Original: ', soup.prettify())
#Find article
contents = soup.find('div', {'class':['article_text']})
if not contents:
self.log('postprocess_html: article div not found!')
return soup
contents.extract()
#Find title
title = soup.find('h1')
if title:
contents.insert(0, title)
#Find article image
newstop = soup.find('div', {'class':['newstop']})
if newstop:
img = newstop.find('img')
if img:
imgDiv = Tag(soup, 'div')
imgDiv['class'] = 'article_img'
if img.has_key('width'):
del(img['width'])
if img.has_key('height'):
del(img['height'])
#find description
element = img.parent.nextSibling
img.extract()
imgDiv.insert(0, img)
while element:
if not isinstance(element, Tag):
continue
nextElement = element.nextSibling
if 'p' == element.name:
element.extract()
element['class'] = 'article_img_desc'
imgDiv.insert(len(imgDiv.contents), element)
element = nextElement
contents.insert(1, imgDiv)
#find article abstract
abstract = soup.find('p', {'class':['subhead']})
if abstract:
abstract['class'] = 'article_desc'
contents.insert(2, abstract)
#Find article authors
authorsDiv = soup.find('div', {'class':['autors']})
if authorsDiv:
authorsP = authorsDiv.find('p')
if authorsP:
authorsP['class'] = 'article_authors'
contents.insert(len(contents.contents), authorsP)
#Fix urls that use relative path
urls = contents.findAll('a');
if urls:
for url in urls:
if not url.has_key('href'):
continue
if '/' == url['href'][0]:
url['href'] = self.base_url + url['href']
body = soup.find('td', {'class':['second_content']})
if body:
body.replaceWith(contents)
self.log('Result: ', soup.prettify())
return soup

5
resources/recipes/wash_post.recipe
View File

@ -31,8 +31,9 @@ class WashingtonPost(BasicNewsRecipe):
('Education', 'http://www.washingtonpost.com/wp-dyn/rss/education/index.xml'),
('Style',
'http://www.washingtonpost.com/wp-dyn/rss/print/style/index.xml'),
('Sports',
'http://feeds.washingtonpost.com/wp-dyn/rss/linkset/2010/08/19/LI2010081904067_xml'),
('NFL Sports',
'http://www.washingtonpost.com/wp-dyn/rss/sports/index/nfl/index.xml'),
('Redskins', 'http://www.washingtonpost.com/wp-dyn/rss/sports/redskins/index.xml'),
('Editorials', 'http://www.washingtonpost.com/wp-dyn/rss/linkset/2005/05/30/LI2005053000331.xml'),
]

72
resources/recipes/ynet.recipe Normal file
View File

@ -0,0 +1,72 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
import mechanize
class AdvancedUserRecipe1283848012(BasicNewsRecipe):
description = 'This is a recipe of Ynet.co.il. The recipe opens the article page and clicks on an advertisement to not hurt the sites advertising income.'
cover_url = 'http://www.bneiakiva.net/uploads/images/ynet%282%29.jpg'
title = u'Ynet'
__author__ = 'marbs'
language = 'he'
extra_css='img {max-width:100%;direction: rtl;} #article{direction: rtl;} div{direction: rtl;} title{direction: rtl; } article_description{direction: rtl; } a.article{direction: rtl; } calibre_feed_description{direction: rtl; } body{direction: ltr;}'
remove_attributes = ['width']
simultaneous_downloads = 5
keep_only_tags =dict(name='div', attrs={'id':'articleContainer'})
remove_javascript = True
timefmt = '[%a, %d %b, %Y]'
oldest_article = 1
remove_tags = [dict(name='p', attrs={'text':['&nbsp;']})]
max_articles_per_feed = 100
preprocess_regexps = [
(re.compile(r'<p>&nbsp;</p>', re.DOTALL|re.IGNORECASE), lambda match: '')
]
def preprocess_html(self, soup):
soup.html['dir'] = 'rtl'
soup.body['dir'] = 'rtl'
return soup
feeds =[(u'\u05d7\u05d3\u05e9\u05d5\u05ea',
u'http://www.ynet.co.il/Integration/StoryRss2.xml'),
(u'\u05db\u05dc\u05db\u05dc\u05d4',
u'http://www.ynet.co.il/Integration/StoryRss6.xml'),
(u'\u05e6\u05e8\u05db\u05e0\u05d5\u05ea',
u'http://www.ynet.co.il/Integration/StoryRss437.xml'),
(u'\u05e1\u05e4\u05d5\u05e8\u05d8',
u'http://www.ynet.co.il/Integration/StoryRss3.xml'),
(u'\u05ea\u05e8\u05d1\u05d5\u05ea',
u'http://www.ynet.co.il/Integration/StoryRss538.xml'),
(u'\u05de\u05e2\u05d5\u05e8\u05d1\u05d5\u05ea \u05d5\u05d7\u05d1\u05e8\u05d4',
u'http://www.ynet.co.il/Integration/StoryRss3262.xml'),
(u'\u05d1\u05e8\u05d9\u05d0\u05d5\u05ea',
u'http://www.ynet.co.il/Integration/StoryRss1208.xml'),
(u'\u05d9\u05e8\u05d5\u05e7',
u'http://www.ynet.co.il/Integration/StoryRss4872.xml'),
(u'\u05de\u05d7\u05e9\u05d1\u05d9\u05dd',
u'http://www.ynet.co.il/Integration/StoryRss544.xml'),
(u'\u05e8\u05db\u05d1', u'http://www.ynet.co.il/Integration/StoryRss550.xml'),
(u'\u05ea\u05d9\u05d9\u05e8\u05d5\u05ea',
u'http://www.ynet.co.il/Integration/StoryRss598.xml'),
(u'\u05d4\u05d5\u05e8\u05d9\u05dd',
u'http://www.ynet.co.il/Integration/StoryRss3052.xml'),
(u'\u05d0\u05d5\u05db\u05dc',
u'http://www.ynet.co.il/Integration/StoryRss975.xml'),
(u'\u05d9\u05d4\u05d3\u05d5\u05ea',
u'http://www.ynet.co.il/Integration/StoryRss4403.xml'),
(u'\u05de\u05d3\u05e2 \u05d5\u05d8\u05d1\u05e2',
u'http://www.ynet.co.il/Integration/StoryRss2142.xml'),
(u'\u05d9\u05d7\u05e1\u05d9\u05dd',
u'http://www.ynet.co.il/Integration/StoryRss3925.xml'),
(u'\u05d3\u05e2\u05d5\u05ea',
u'http://www.ynet.co.il/Integration/StoryRss194.xml')]
def print_version(self, url):
#remove from here
br = BasicNewsRecipe.get_browser()
br.open(url)
br.follow_link(mechanize.Link(base_url = '', url =url, text = '', tag = 'a', attrs = [{'id':'buzzerATop'}]))
#to here to stop supporting ynet...
split1 = url.split("-")
print_url = 'http://www.ynet.co.il/Ext/Comp/ArticleLayout/CdaArticlePrintPreview/1,2506,L-' + split1[1]
return print_url

91
resources/recipes/zeitde.recipe
View File

@ -6,22 +6,25 @@ Fetch Die Zeit.
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class ZeitDe(BasicNewsRecipe):
title = 'ZEIT Online'
description = 'ZEIT Online'
title = 'Zeit Online'
description = 'Zeit Online'
language = 'de'
lang = 'de_DE'
__author__ = 'Martin Pitt, Sujata Raman and Ingo Paschke'
use_embedded_content = False
__author__ = 'Martin Pitt, Sujata Raman, Ingo Paschke and Marc Toensing'
max_articles_per_feed = 40
remove_empty_feeds = True
no_stylesheets = True
no_javascript = True
encoding = 'utf-8'
remove_tags = [
dict(name='iframe'),
dict(name='div', attrs={'class':["response","pagination block","pagenav","inline link", "copyright"] }),
dict(name='p', attrs={'class':["ressortbacklink", "copyright"] }),
dict(name='div', attrs={'id':["place_5","place_4","comments"]})
]
keep_only_tags = [dict(id=['main'])]
feeds = [
('Seite 1', 'http://newsfeed.zeit.de/index_xml'),
@ -40,71 +43,31 @@ class ZeitDe(BasicNewsRecipe):
('Sport', 'http://newsfeed.zeit.de/sport/index'),
]
extra_css = '''
.supertitle{color:#990000; font-family:Arial,Helvetica,sans-serif;font-size:xx-small;}
.excerpt{font-family:Georgia,Palatino,Palatino Linotype,FreeSerif,serif;font-size:small;}
.title{font-family:Arial,Helvetica,sans-serif;font-size:large;clear:right;}
.caption{color:#666666; font-family:Arial,Helvetica,sans-serif;font-size:xx-small;}
.copyright{color:#666666; font-family:Arial,Helvetica,sans-serif;font-size:xx-small;}
.article{font-family:Georgia,Palatino,Palatino Linotype,FreeSerif,serif;font-size:x-small}
.quote{font-family:Georgia,Palatino,Palatino Linotype,FreeSerif,serif;font-size:x-small}
.quote .cite{font-family:Georgia,Palatino,Palatino Linotype,FreeSerif,serif;font-size:xx-small}
.headline iconportrait_inline{font-family:Arial,Helvetica,sans-serif;font-size:x-small}
.inline{float:left;margin-top:0;margin-right:15px;position:relative;width:180px; }
img.inline{float:none}
.intertitle{font-family:Georgia,Palatino,Palatino Linotype,FreeSerif,serif;font-size:x-small;font-weight:700}
.ebinfobox{font-family:Georgia,Palatino,Palatino Linotype,FreeSerif,serif;font-size:xx-small;list-style-type:none;float:right;margin-top:0;border-left-style:solid;border-left-width:1px;padding-left:10px;}
.infobox {border-style: solid; border-width: 1px;padding:8px;}
.infobox dt {font-weight:700;}
'''
extra_css = '.excerpt{font-size:1em}.reaktion,.taglist,.comments,.reponse,.responsetitle,.responsebody,.reponse,.inline,.date{display:none;}li.date{display:block}'
#filter_regexps = [r'ad.de.doubleclick.net/']
keep_only_tags = [
dict(name='div', attrs={'class':["article"]}) ,
dict(name='ul', attrs={'class':["tools"]}) ,
]
remove_tags = [
dict(name='link'), dict(name='iframe'),dict(name='style'),dict(name='meta'),
dict(name='div', attrs={'class':["pagination block","pagenav","inline link", "copyright"] }),
dict(name='p', attrs={'class':["ressortbacklink", "copyright"] }),
dict(name='div', attrs={'id':["place_5","place_4","comments"]})
]
remove_attributes = ['style', 'font']
def get_article_url(self, article):
ans = article.get('link',None)
ans += "?page=all"
ans += "?page=all&print=true"
if 'video' in ans or 'quiz' in ans :
if 'video' in ans or 'quiz' in ans or 'blog' in ans :
ans = None
return ans
def preprocess_html(self, soup):
for tag in soup.findAll(name=['ul','li']):
tag.name = 'div'
soup.html['xml:lang'] = self.lang
soup.html['lang'] = self.lang
mtag = '<meta http-equiv="Content-Type" content="text/html; charset=' + self.encoding + '">'
soup.head.insert(0,mtag)
return soup
def get_cover_url(self):
try:
inhalt = self.index_to_soup('http://www.zeit.de/inhalt')
return inhalt.find('div', attrs={'class':'singlearchive clearfix'}).img['src'].replace('icon_','')
except:
return 'http://images.zeit.de/bilder/titelseiten_zeit/1946/001_001.jpg'
def preprocess_html(self, soup):
soup.html['xml:lang'] = self.lang
soup.html['lang'] = self.lang
mtag = '<meta http-equiv="Content-Type" content="text/html; charset=' + self.encoding + '">'
soup.head.insert(0,mtag)
title = soup.find('h2', attrs={'class':'title'})
if title is None:
print "no title"
return soup
info = Tag(soup,'ul',[('class','ebinfobox')])
tools = soup.find('ul', attrs={'class':'tools'})
#author = tools.find('li','author first')
for tag in ['author first', 'date', 'date first', 'author', 'source']:
line = tools.find('li', tag)
if line:
info.insert(0,line)
title.parent.insert(0,info)
tools.extract()
return soup

79
resources/templates/fb2.xsl
View File

@ -30,23 +30,40 @@
<title>
<xsl:value-of select="fb:description/fb:title-info/fb:book-title"/>
</title>
<style type="text/x-oeb1-css">
A { color : #0002CC }
A:HOVER { color : #BF0000 }
BODY { background-color : #FEFEFE; color : #000000; font-family : Verdana, Geneva, Arial, Helvetica, sans-serif; text-align : justify }
H1{ font-size : 160%; font-style : normal; font-weight : bold; text-align : left; border : 1px solid Black; background-color : #E7E7E7; margin-left : 0px; page-break-before : always; }
H2{ font-size : 130%; font-style : normal; font-weight : bold; text-align : left; background-color : #EEEEEE; border : 1px solid Gray; page-break-before : always; }
H3{ font-size : 110%; font-style : normal; font-weight : bold; text-align : left; background-color : #F1F1F1; border : 1px solid Silver;}
H4{ font-size : 100%; font-style : normal; font-weight : bold; text-align : left; border : 1px solid Gray; background-color : #F4F4F4;}
H5{ font-size : 100%; font-style : italic; font-weight : bold; text-align : left; border : 1px solid Gray; background-color : #F4F4F4;}
H6{ font-size : 100%; font-style : italic; font-weight : normal; text-align : left; border : 1px solid Gray; background-color : #F4F4F4;}
SMALL{ font-size : 80% }
BLOCKQUOTE{ margin-left :4em; margin-top:1em; margin-right:0.2em;}
HR{ color : Black }
DIV{font-family : "Times New Roman", Times, serif; text-align : justify}
UL{margin-left: 0}
.epigraph{width:50%; margin-left : 35%;}
<style type="text/css">
a { color : #0002CC }
a:hover { color : #BF0000 }
body { background-color : #FEFEFE; color : #000000; font-family : Verdana, Geneva, Arial, Helvetica, sans-serif; text-align : justify }
h1{ font-size : 160%; font-style : normal; font-weight : bold; text-align : left; border : 1px solid Black; background-color : #E7E7E7; margin-left : 0px; page-break-before : always; }
h2{ font-size : 130%; font-style : normal; font-weight : bold; text-align : left; background-color : #EEEEEE; border : 1px solid Gray; page-break-before : always; }
h3{ font-size : 110%; font-style : normal; font-weight : bold; text-align : left; background-color : #F1F1F1; border : 1px solid Silver;}
h4{ font-size : 100%; font-style : normal; font-weight : bold; text-align : left; border : 1px solid Gray; background-color : #F4F4F4;}
h5{ font-size : 100%; font-style : italic; font-weight : bold; text-align : left; border : 1px solid Gray; background-color : #F4F4F4;}
h6{ font-size : 100%; font-style : italic; font-weight : normal; text-align : left; border : 1px solid Gray; background-color : #F4F4F4;}
small { font-size : 80% }
blockquote { margin-left :4em; margin-top:1em; margin-right:0.2em;}
hr { color : Black }
div {font-family : "Times New Roman", Times, serif; text-align : justify}
ul {margin-left: 0}
.epigraph{width:50%; margin-left : 35%;}
div.paragraph { text-align: justify; text-indent: 2em; }
</style>
<link rel="stylesheet" type="text/css" href="inline-styles.css" />
</head>
<body>
<xsl:for-each select="fb:description/fb:title-info/fb:annotation">
@ -136,12 +153,13 @@
</xsl:choose>
</xsl:variable>
<xsl:if test="$section_has_title = 'None'">
<a name="TOC_{generate-id()}" />
<xsl:if test="@id">
<xsl:element name="a">
<xsl:attribute name="name"><xsl:value-of select="@id"/></xsl:attribute>
</xsl:element>
</xsl:if>
<div id="TOC_{generate-id()}">
<xsl:if test="@id">
<xsl:element name="a">
<xsl:attribute name="id"><xsl:value-of select="@id"/></xsl:attribute>
</xsl:element>
</xsl:if>
</div>
</xsl:if>
<xsl:apply-templates>
<xsl:with-param name="section_toc_id" select="$section_has_title" />
@ -160,13 +178,13 @@
</xsl:if>
<xsl:if test="$section_toc_id != 'None'">
<xsl:element name="a">
<xsl:attribute name="name">TOC_<xsl:value-of select="$section_toc_id"/></xsl:attribute>
<xsl:attribute name="id">TOC_<xsl:value-of select="$section_toc_id"/></xsl:attribute>
</xsl:element>
</xsl:if>
<a name="TOC_{generate-id()}"></a>
<xsl:if test="@id">
<xsl:element name="a">
<xsl:attribute name="name"><xsl:value-of select="@id"/></xsl:attribute>
<xsl:attribute name="id"><xsl:value-of select="@id"/></xsl:attribute>
</xsl:element>
</xsl:if>
<xsl:apply-templates/>
@ -176,7 +194,7 @@
<xsl:element name="h6">
<xsl:if test="@id">
<xsl:element name="a">
<xsl:attribute name="name"><xsl:value-of select="@id"/></xsl:attribute>
<xsl:attribute name="id"><xsl:value-of select="@id"/></xsl:attribute>
</xsl:element>
</xsl:if>
<xsl:apply-templates/>
@ -207,11 +225,18 @@
</xsl:template>
<!-- p -->
<xsl:template match="fb:p">
<div align="justify"><xsl:if test="@id">
<xsl:element name="div">
<xsl:attribute name="class">paragraph</xsl:attribute>
<xsl:if test="@id">
<xsl:element name="a">
<xsl:attribute name="name"><xsl:value-of select="@id"/></xsl:attribute>
</xsl:element>
</xsl:if> &#160;&#160;&#160;<xsl:apply-templates/></div>
</xsl:if>
<xsl:if test="@style">
<xsl:attribute name="style"><xsl:value-of select="@style"/></xsl:attribute>
</xsl:if>
<xsl:apply-templates/>
</xsl:element>
</xsl:template>
<!-- strong -->
<xsl:template match="fb:strong">

60
resources/templates/html_export_default.css Normal file
View File

@ -0,0 +1,60 @@
body{
margin:0px;
padding: 0.5em;
background-color:#F6F3E9;
font-size:12px;
font-family:Arial, Helvetica, sans-serif;
}
.calibreMeta{
background-color:#39322B;
color:white;
padding:10px;
}
.calibreMeta a, .calibreEbNav a, .calibreEbNavTop a, .calibreToc a{
color:white;
}
.calibreMeta h1{
margin:0px;
font-size:18px;
background-color:#39322B;
}
.calibreEbookContent{
padding:20px;
}
.calibreEbNav, .calibreEbNavTop{
clear:both;
background-color:#39322B;
color:white;
padding:10px;
text-align:center;
}
.calibreEbNavTop{
margin-bottom:20px;
}
.calibreEbNav a, .calibreEbNavTop a{
padding:0px 5px;
}
.calibreTocIndex{
line-height:18px;
}
.calibreToc{
float:left;
margin:20px;
width:300px;
background-color:#39322B;
color:white;
padding:10px;
}
.calibreEbookContent{
width:600px;
float:left;
}

74
resources/templates/html_export_default.tmpl Normal file
View File

@ -0,0 +1,74 @@
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
${head_content}$
<link href="${cssLink}$" type="text/css" rel="stylesheet" />
</head>
<body>
<div class="calibreMeta">
<div class="calibreMetaTitle">
${pos1=1}$
${for title in meta.titles():}$
${if pos1:}$
<h1>
<a href="${tocUrl}$">${print title}$</a>
</h1>
${:else:}$
<div class="calibreMetaSubtitle">${print title}$</div>
${:endif}$
${pos1=0}$
${:endfor}$
</div>
<div class="calibreMetaAuthor">
${print ', '.join(meta.creators())}$
</div>
</div>
<div class="calibreMain">
<div class="calibreEbookContent">
${if prevLink or nextLink:}$
<div class="calibreEbNavTop">
${if prevLink:}$
<a href="${prevLink}$" class="calibreAPrev">${print _('previous page'),}$</a>
${:else:}$
<a href="${tocUrl}$" class="calibreAPrev">${print _('previous page'),}$</a>
${:endif}$
${if nextLink:}$
<a href="${nextLink}$" class="calibreANext">${print _('next page'),}$</a>
${:endif}$
</div>
${:endif}$
${ebookContent}$
</div>
${if has_toc:}$
<div class="calibreToc">
<h2><a href="${tocUrl}$">${print _('Table of contents'),}$</a></h2>
${print toc()}$
</div>
${:endif}$
<div class="calibreEbNav">
${if prevLink:}$
<a href="${prevLink}$" class="calibreAPrev">${print _('previous page'),}$</a>
${:else:}$
<a href="${tocUrl}$" class="calibreAPrev">${print _('previous page'),}$</a>
${:endif}$
<a href="${tocUrl}$" class="calibreAHome">${print _('start'),}$</a>
${if nextLink:}$
<a href="${nextLink}$" class="calibreANext">${print _('next page'),}$</a>
${:endif}$
</div>
</div>
</body>
</html>

61
resources/templates/html_export_default_index.tmpl Normal file
View File

@ -0,0 +1,61 @@
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
<link rel="schema.DC" href="http://purl.org/dc/elements/1.1/" />
<link rel="schema.DCTERMS" href="http://purl.org/dc/terms/" />
<title>${print ', '.join(meta.creators()),}$ - ${print meta.titles().next(); meta.titles().close()}$</title>
${for item in meta:}$
<meta ${print 'name="DC.'+item['name']+'"',}$ ${print 'content="'+item['value']+'"',}$ />
${:endfor}$
<link href="${cssLink}$" type="text/css" rel="stylesheet" />
</head>
<body>
<div class="calibreMeta">
<div class="calibreMetaTitle">
${pos1=1}$
${for title in meta.titles():}$
${if pos1:}$
<h1>
<a href="${tocUrl}$">${print title}$</a>
</h1>
${:else:}$
<div class="calibreMetaSubtitle">${print title}$</div>
${:endif}$
${pos1=0}$
${:endfor}$
</div>
<div class="calibreMetaAuthor">
${print ', '.join(meta.creators()),}$
</div>
</div>
<div class="calibreMain">
<div class="calibreEbookContent">
${if has_toc:}$
<div class="calibreTocIndex">
<h2>${print _('Table of contents'),}$</h2>
${toc}$
</div>
${:else:}$
<h2>${print _('No table of contents present'),}$</h2>
<div><strong><a href="${nextLink}$">${print _('begin to read'),}$</a></strong></div>
${:endif}$
</div>
<div class="calibreEbNav">
${if nextLink:}$
<a href="${nextLink}$" class="calibreANext">${print _('next page'),}$</a>
${:endif}$
</div>
</div>
</body>
</html>

16
resources/viewer/images.js
View File

@ -20,20 +20,4 @@ function setup_image_scaling_handlers() {
});
}
function extract_svged_images() {
$("svg").each(function() {
var children = $(this).children("img");
if (children.length == 1) {
var img = $(children[0]);
var href = img.attr('xlink:href');
if (href != undefined) {
$(this).replaceWith('<div style="text-align:center; margin: 0; padding: 0"><img style="height: 98%" alt="SVG Image" src="' + href +'"></img></div>');
}
}
});
}
$(document).ready(function() {
//extract_svged_images();
});

5
setup/commands.py
View File

@ -8,7 +8,7 @@ __docformat__ = 'restructuredtext en'
__all__ = [
'pot', 'translations', 'get_translations', 'iso639',
'build', 'build_pdf2xml',
'build', 'build_pdf2xml', 'server',
'gui',
'develop', 'install',
'resources',
@ -35,6 +35,9 @@ from setup.extensions import Build, BuildPDF2XML
build = Build()
build_pdf2xml = BuildPDF2XML()
from setup.server import Server
server = Server()
from setup.install import Develop, Install, Sdist
develop = Develop()
install = Install()

8
setup/extensions.py
View File

@ -54,7 +54,7 @@ reflow_error = poppler_error if poppler_error else magick_error
pdfreflow_libs = []
if iswindows:
pdfreflow_libs = ['advapi32', 'User32', 'Gdi32']
pdfreflow_libs = ['advapi32', 'User32', 'Gdi32', 'zlib']
extensions = [
@ -348,8 +348,12 @@ class Build(Command):
VERSION = 1.0.0
CONFIG += %s
''')%(ext.name, ' '.join(ext.headers), ' '.join(ext.sources), archs)
pro = pro.replace('\\', '\\\\')
open(ext.name+'.pro', 'wb').write(pro)
subprocess.check_call([QMAKE, '-o', 'Makefile', ext.name+'.pro'])
qmc = [QMAKE, '-o', 'Makefile']
if iswindows:
qmc += ['-spec', 'win32-msvc2008']
subprocess.check_call(qmc + [ext.name+'.pro'])
subprocess.check_call([make, '-f', 'Makefile'])
objects = glob.glob(obj_pat)
return list(map(self.a, objects))

6
setup/installer/__init__.py
View File

@ -11,7 +11,7 @@ import subprocess, tempfile, os, time
from setup import Command, installer_name
from setup.build_environment import HOST, PROJECT
BASE_RSYNC = 'rsync -avz --delete'.split()
BASE_RSYNC = ['rsync', '-avz', '--delete']
EXCLUDES = []
for x in [
'src/calibre/plugins', 'src/calibre/manual', 'src/calibre/trac',
@ -42,13 +42,13 @@ class Push(Command):
threads = []
for host in (
r'Owner@winxp:/cygdrive/c/Documents\ and\ Settings/Owner/calibre',
'kovid@ox:calibre'
'kovid@ox:calibre',
r'kovid@win7:/cygdrive/c/Users/kovid/calibre',
):
rcmd = BASE_RSYNC + EXCLUDES + ['.', host]
print '\n\nPushing to:', host, '\n'
threads.append(Thread(target=subprocess.check_call, args=(rcmd,)))
threads[-1].start()
subprocess.check_call(rcmd)
for thread in threads:
thread.join()

2
setup/installer/windows/freeze.py
View File

@ -13,7 +13,7 @@ from setup import Command, modules, functions, basenames, __version__, \
from setup.build_environment import msvc, MT, RC
from setup.installer.windows.wix import WixMixIn
QT_DIR = 'C:\\Qt\\4.6.3'
QT_DIR = 'Q:\\Qt\\4.7.1'
QT_DLLS = ['Core', 'Gui', 'Network', 'Svg', 'WebKit', 'Xml', 'XmlPatterns']
LIBUSB_DIR = 'C:\\libusb'
LIBUNRAR = 'C:\\Program Files\\UnrarDLL\\unrar.dll'

9
setup/installer/windows/notes.rst
View File

@ -28,15 +28,16 @@ If there are no windows binaries already compiled for the version of python you
Run the following command to install python dependencies::
easy_install --always-unzip -U ipython mechanize BeautifulSoup pyreadline python-dateutil dnspython
easy_install --always-unzip -U ipython mechanize pyreadline python-dateutil dnspython cssutils clientform
Install BeautifulSoup 3.0.x manually into site-packages (3.1.x parses broken HTML very poorly)
Qt
--------
Extract Qt sourcecode to C:\Qt\4.x.x. Run configure and make::
configure -opensource -qt-zlib -qt-gif -qt-libmng -qt-libpng -qt-libtiff -qt-libjpeg -release -platform win32-msvc -no-qt3support -webkit -xmlpatterns -no-phonon
nmake
configure -opensource -release -qt-zlib -qt-gif -qt-libmng -qt-libpng -qt-libtiff -qt-libjpeg -release -platform win32-msvc2008 -no-qt3support -webkit -xmlpatterns -no-phonon -no-style-plastique -no-style-cleanlooks -no-style-motif -no-style-cde -no-declarative -no-scripttools -no-audio-backend -no-multimedia -no-dbus -no-openvg -no-opengl -no-qt3support -confirm-license && nmake
SIP
-----
@ -213,7 +214,7 @@ It contains correct fonts.conf etc.
poppler
-------------
In Cmake: disable GTK, Qt, OPenjpeg, zlib, lcms, gtk_tests, qt_tests. Enable qt4, jpeg, png and zlib
In Cmake: disable GTK, Qt, OPenjpeg, cpp, lcms, gtk_tests, qt_tests. Enable qt4, jpeg, png and zlib
NOTE: poppler must be built as a static library, unless you build the qt4 bindings

128
setup/server.py Normal file
View File

@ -0,0 +1,128 @@
#!/usr/bin/env python
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
__license__ = 'GPL v3'
__copyright__ = '2010, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
import subprocess, tempfile, os, time, sys, telnetlib
from threading import RLock
from setup import Command
try:
from pyinotify import WatchManager, ThreadedNotifier, EventsCodes, ProcessEvent
except:
wm = None
else:
wm = WatchManager()
flags = EventsCodes.ALL_FLAGS
mask = flags['IN_MODIFY']
class ProcessEvents(ProcessEvent):
def __init__(self, command):
ProcessEvent.__init__(self)
self.command = command
def process_default(self, event):
name = getattr(event,
'name', None)
if not name:
return
ext = os.path.splitext(name)[1]
reload = False
if ext == '.py':
reload = True
print
print name, 'changed'
self.command.kill_server()
self.command.launch_server()
print self.command.prompt,
sys.stdout.flush()
if reload:
self.command.reload_browser(delay=1)
class Server(Command):
description = 'Run the calibre server in development mode conveniently'
MONOCLE_PATH = '../monocle'
def rebuild_monocole(self):
subprocess.check_call(['sprocketize', '-C', self.MONOCLE_PATH,
'-I', 'src', 'src/monocle.js'],
stdout=open('resources/content_server/read/monocle.js', 'wb'))
def launch_server(self):
print 'Starting server...\n'
with self.lock:
self.rebuild_monocole()
self.server_proc = p = subprocess.Popen(['calibre-server', '--develop'],
stderr=subprocess.STDOUT, stdout=self.server_log)
time.sleep(0.2)
if p.poll() is not None:
print 'Starting server failed'
raise SystemExit(1)
return p
def kill_server(self):
print 'Killing server...\n'
if self.server_proc is not None:
with self.lock:
if self.server_proc.poll() is None:
self.server_proc.terminate()
while self.server_proc.poll() is None:
time.sleep(0.1)
def watch(self):
if wm is not None:
self.notifier = ThreadedNotifier(wm, ProcessEvents(self))
self.notifier.start()
self.wdd = wm.add_watch(os.path.abspath('src'), mask, rec=True)
def reload_browser(self, delay=0.1):
time.sleep(delay)
try:
t = telnetlib.Telnet('localhost', 4242)
t.read_until("repl>")
t.write('BrowserReload();')
t.read_until("repl>")
t.close()
except:
print 'Failed to reload browser'
import traceback
traceback.print_exc()
def run(self, opts):
self.lock = RLock()
tdir = tempfile.gettempdir()
logf = os.path.join(tdir, 'calibre-server.log')
self.server_log = open(logf, 'ab')
self.prompt = 'Press Enter to kill/restart server. Ctrl+C to quit: '
print 'Server log available at:', logf
print
self.watch()
first = True
while True:
self.launch_server()
if not first:
self.reload_browser()
first = False
try:
raw_input(self.prompt)
except:
print
self.kill_server()
break
else:
self.kill_server()
print
if hasattr(self, 'notifier'):
self.notifier.stop()

8
src/calibre/__init__.py
View File

@ -21,8 +21,6 @@ from calibre.constants import iswindows, isosx, islinux, isfreebsd, isfrozen, \
filesystem_encoding, plugins, config_dir
from calibre.startup import winutil, winutilerror
import mechanize
uuid.uuid4() # Imported before PyQt4 to workaround PyQt4 util-linux conflict on gentoo
if False:
@ -269,7 +267,8 @@ def browser(honor_time=True, max_time=2, mobile_browser=False):
:param honor_time: If True honors pause time in refresh requests
:param max_time: Maximum time in seconds to wait during a refresh request
'''
opener = mechanize.Browser()
from calibre.utils.browser import Browser
opener = Browser()
opener.set_handle_refresh(True, max_time=max_time, honor_time=honor_time)
opener.set_handle_robots(False)
opener.addheaders = [('User-agent', ' Mozilla/5.0 (Windows; U; Windows CE 5.1; rv:1.8.1a3) Gecko/20060610 Minimo/0.016' if mobile_browser else \
@ -445,6 +444,9 @@ xml_entity_to_unicode = partial(entity_to_unicode, result_exceptions = {
def replace_entities(raw):
return _ent_pat.sub(entity_to_unicode, raw)
def xml_replace_entities(raw):
return _ent_pat.sub(xml_entity_to_unicode, raw)
def prepare_string_for_xml(raw, attribute=False):
raw = _ent_pat.sub(entity_to_unicode, raw)
raw = raw.replace('&', '&amp;').replace('<', '&lt;').replace('>', '&gt;')

6
src/calibre/constants.py
View File

@ -2,7 +2,7 @@ __license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'
__appname__ = 'calibre'
__version__ = '0.7.23'
__version__ = '0.7.28'
__author__ = "Kovid Goyal <kovid@kovidgoyal.net>"
import re
@ -105,7 +105,9 @@ else:
os.makedirs(config_dir, mode=CONFIG_DIR_MODE)
except:
pass
if not os.access(config_dir, os.W_OK) or not os.access(config_dir, os.X_OK):
if not os.path.exists(config_dir) or \
not os.access(config_dir, os.W_OK) or not \
os.access(config_dir, os.X_OK):
print 'No write acces to', config_dir, 'using a temporary dir instead'
import tempfile, atexit
config_dir = tempfile.mkdtemp(prefix='calibre-config-')

26
src/calibre/customize/builtins.py
View File

@ -2,9 +2,7 @@ import os.path
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
import textwrap
import os
import glob
import textwrap, os, glob, functools
from calibre.customize import FileTypePlugin, MetadataReaderPlugin, \
MetadataWriterPlugin, PreferencesPlugin, InterfaceActionBase
from calibre.constants import numeric_version
@ -95,10 +93,12 @@ class ComicMetadataReader(MetadataReaderPlugin):
def get_metadata(self, stream, ftype):
if ftype == 'cbr':
from calibre.libunrar import extract_member as extract_first
from calibre.libunrar import extract_first_alphabetically as extract_first
extract_first
else:
from calibre.libunzip import extract_member as extract_first
from calibre.libunzip import extract_member
extract_first = functools.partial(extract_member,
sort_alphabetically=True)
from calibre.ebooks.metadata import MetaInformation
ret = extract_first(stream)
mi = MetaInformation(None, None)
@ -446,6 +446,7 @@ from calibre.ebooks.rb.output import RBOutput
from calibre.ebooks.rtf.output import RTFOutput
from calibre.ebooks.tcr.output import TCROutput
from calibre.ebooks.txt.output import TXTOutput
from calibre.ebooks.html.output import HTMLOutput
from calibre.ebooks.snb.output import SNBOutput
from calibre.customize.profiles import input_profiles, output_profiles
@ -453,7 +454,7 @@ from calibre.customize.profiles import input_profiles, output_profiles
from calibre.devices.apple.driver import ITUNES
from calibre.devices.hanlin.driver import HANLINV3, HANLINV5, BOOX, SPECTRA
from calibre.devices.blackberry.driver import BLACKBERRY
from calibre.devices.cybook.driver import CYBOOK
from calibre.devices.cybook.driver import CYBOOK, ORIZON
from calibre.devices.eb600.driver import EB600, COOL_ER, SHINEBOOK, \
POCKETBOOK360, GER2, ITALICA, ECLICTO, DBOOK, INVESBOOK, \
BOOQ, ELONEX, POCKETBOOK301, MENTOR
@ -461,7 +462,7 @@ from calibre.devices.iliad.driver import ILIAD
from calibre.devices.irexdr.driver import IREXDR1000, IREXDR800
from calibre.devices.jetbook.driver import JETBOOK, MIBUK, JETBOOK_MINI
from calibre.devices.kindle.driver import KINDLE, KINDLE2, KINDLE_DX
from calibre.devices.nook.driver import NOOK
from calibre.devices.nook.driver import NOOK, NOOK_COLOR
from calibre.devices.prs505.driver import PRS505
from calibre.devices.android.driver import ANDROID, S60
from calibre.devices.nokia.driver import N770, N810, E71X, E52
@ -471,10 +472,11 @@ from calibre.devices.iriver.driver import IRIVER_STORY
from calibre.devices.binatone.driver import README
from calibre.devices.hanvon.driver import N516, EB511, ALEX, AZBOOKA, THEBOOK
from calibre.devices.edge.driver import EDGE
from calibre.devices.teclast.driver import TECLAST_K3, NEWSMY, IPAPYRUS, SOVOS
from calibre.devices.teclast.driver import TECLAST_K3, NEWSMY, IPAPYRUS, \
SOVOS, PICO
from calibre.devices.sne.driver import SNE
from calibre.devices.misc import PALMPRE, AVANT, SWEEX, PDNOVEL, KOGAN, \
GEMEI, VELOCITYMICRO, PDNOVEL_KOBO
GEMEI, VELOCITYMICRO, PDNOVEL_KOBO, Q600
from calibre.devices.folder_device.driver import FOLDER_DEVICE_FOR_CONFIG
from calibre.devices.kobo.driver import KOBO
@ -524,6 +526,7 @@ plugins += [
RTFOutput,
TCROutput,
TXTOutput,
HTMLOutput,
SNBOutput,
]
# Order here matters. The first matched device is the one used.
@ -532,6 +535,7 @@ plugins += [
HANLINV5,
BLACKBERRY,
CYBOOK,
ORIZON,
ILIAD,
IREXDR1000,
IREXDR800,
@ -545,6 +549,7 @@ plugins += [
KINDLE2,
KINDLE_DX,
NOOK,
NOOK_COLOR,
PRS505,
ANDROID,
S60,
@ -572,6 +577,7 @@ plugins += [
ELONEX,
TECLAST_K3,
NEWSMY,
PICO,
IPAPYRUS,
SOVOS,
EDGE,
@ -584,6 +590,7 @@ plugins += [
AVANT,
MENTOR,
SWEEX,
Q600,
KOGAN,
PDNOVEL,
SPECTRA,
@ -890,4 +897,3 @@ plugins += [LookAndFeel, Behavior, Columns, Toolbar, InputOptions,
Email, Server, Plugins, Tweaks, Misc]
#}}}

10
src/calibre/customize/conversion.py
View File

@ -120,6 +120,11 @@ class InputFormatPlugin(Plugin):
#: to make its output suitable for viewing
for_viewer = False
#: The encoding that this input plugin creates files in. A value of
#: None means that the encoding is undefined and must be
#: detected individually
output_encoding = 'utf-8'
#: Options shared by all Input format plugins. Do not override
#: in sub-classes. Use :attr:`options` instead. Every option must be an
#: instance of :class:`OptionRecommendation`.
@ -289,3 +294,8 @@ class OutputFormatPlugin(Plugin):
'''
raise NotImplementedError
@property
def is_periodical(self):
return self.oeb.metadata.publication_type and \
unicode(self.oeb.metadata.publication_type[0]).startswith('periodical:')

46
src/calibre/customize/profiles.py
View File

@ -4,6 +4,7 @@ __license__ = 'GPL 3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
import sys
from itertools import izip
from xml.sax.saxutils import escape
@ -249,8 +250,11 @@ class OutputProfile(Plugin):
#: If True, the date is appended to the title of downloaded news
periodical_date_in_title = True
#: The character used to represent a star in ratings
#: Characters used in jackets and catalogs
missing_char = u'x'
ratings_char = u'*'
empty_ratings_char = u' '
read_char = u'+'
#: Unsupported unicode characters to be replaced during preprocessing
unsupported_unicode_chars = []
@ -258,6 +262,9 @@ class OutputProfile(Plugin):
#: Number of ems that the left margin of a blockquote is rendered as
mobi_ems_per_blockquote = 1.0
#: Special periodical formatting needed in EPUB
epub_periodical_format = None
@classmethod
def tags_to_string(cls, tags):
return escape(', '.join(tags))
@ -283,7 +290,12 @@ class iPadOutput(OutputProfile):
'macros': {'border-width': '{length}|medium|thick|thin'}
}
]
ratings_char = u'\u2605'
missing_char = u'\u2715\u200a' # stylized 'x' plus hair space
ratings_char = u'\u2605' # filled star
empty_ratings_char = u'\u2606' # hollow star
read_char = u'\u2713' # check mark
touchscreen = True
# touchscreen_news_css {{{
touchscreen_news_css = u'''
@ -417,6 +429,13 @@ class iPadOutput(OutputProfile):
'''
# }}}
class TabletOutput(iPadOutput):
name = 'Tablet'
short_name = 'tablet'
description = _('Intended for generic tablet devices, does no resizing of images')
screen_size = (sys.maxint, sys.maxint)
comic_screen_size = (sys.maxint, sys.maxint)
class SonyReaderOutput(OutputProfile):
@ -431,6 +450,9 @@ class SonyReaderOutput(OutputProfile):
fsizes = [7.5, 9, 10, 12, 15.5, 20, 22, 24]
unsupported_unicode_chars = [u'\u201f', u'\u201b']
epub_periodical_format = 'sony'
#periodical_date_in_title = False
class KoboReaderOutput(OutputProfile):
@ -484,7 +506,6 @@ class SonyReaderLandscapeOutput(SonyReaderOutput):
screen_size = (784, 1012)
comic_screen_size = (784, 1012)
class MSReaderOutput(OutputProfile):
name = 'Microsoft Reader'
@ -553,6 +574,8 @@ class CybookOpusOutput(SonyReaderOutput):
fbase = 16
fsizes = [12, 12, 14, 16, 18, 20, 22, 24]
epub_periodical_format = None
class KindleOutput(OutputProfile):
name = 'Kindle'
@ -566,7 +589,12 @@ class KindleOutput(OutputProfile):
fsizes = [12, 12, 14, 16, 18, 20, 22, 24]
supports_mobi_indexing = True
periodical_date_in_title = False
missing_char = u'x\u2009'
empty_ratings_char = u'\u2606'
ratings_char = u'\u2605'
read_char = u'\u2713'
mobi_ems_per_blockquote = 2.0
@classmethod
@ -583,9 +611,12 @@ class KindleDXOutput(OutputProfile):
# Screen size is a best guess
screen_size = (744, 1022)
dpi = 150.0
comic_screen_size = (741, 1022)
comic_screen_size = (771, 1116)
#comic_screen_size = (741, 1022)
supports_mobi_indexing = True
periodical_date_in_title = False
ratings_char = u'\u2605'
read_char = u'\u2713'
mobi_ems_per_blockquote = 2.0
@classmethod
@ -649,13 +680,14 @@ class NookOutput(OutputProfile):
class BambookOutput(OutputProfile):
author = 'Li Fanxi'
name = 'Sanda Bambook'
short_name = 'bambook'
description = _('This profile is intended for the Sanda Bambook.')
# Screen size is a best guess
screen_size = (800, 600)
comic_screen_size = (700, 540)
screen_size = (600, 800)
comic_screen_size = (540, 700)
dpi = 168.451
fbase = 12
fsizes = [10, 12, 14, 16]
@ -663,7 +695,7 @@ class BambookOutput(OutputProfile):
output_profiles = [OutputProfile, SonyReaderOutput, SonyReader300Output,
SonyReader900Output, MSReaderOutput, MobipocketOutput, HanlinV3Output,
HanlinV5Output, CybookG3Output, CybookOpusOutput, KindleOutput,
iPadOutput, KoboReaderOutput,
iPadOutput, KoboReaderOutput, TabletOutput,
SonyReaderLandscapeOutput, KindleDXOutput, IlliadOutput,
IRexDR1000Output, IRexDR800Output, JetBook5Output, NookOutput,
BambookOutput, ]

6
src/calibre/devices/android/driver.py
View File

@ -20,7 +20,11 @@ class ANDROID(USBMS):
VENDOR_ID = {
# HTC
0x0bb4 : { 0x0c02 : [0x100, 0x0227], 0x0c01 : [0x100, 0x0227], 0x0ff9
: [0x0100, 0x0227, 0x0226], 0x0c87: [0x0100, 0x0227, 0x0226]},
: [0x0100, 0x0227, 0x0226], 0x0c87: [0x0100, 0x0227, 0x0226],
0xc92 : [0x100]},
# Eken
0x040d : { 0x8510 : [0x0001] },
# Motorola
0x22b8 : { 0x41d9 : [0x216], 0x2d67 : [0x100], 0x41db : [0x216],

19
src/calibre/devices/apple/driver.py
View File

@ -19,7 +19,7 @@ from calibre.ebooks.metadata.book.base import Metadata
from calibre.ebooks.metadata.epub import set_metadata
from calibre.library.server.utils import strftime
from calibre.utils.config import config_dir, prefs
from calibre.utils.date import isoformat, now, parse_date
from calibre.utils.date import now, parse_date
from calibre.utils.logging import Log
from calibre.utils.zipfile import ZipFile
@ -1221,12 +1221,19 @@ class ITUNES(DriverBase):
return thumb
if isosx:
# The following commands generate an error, but the artwork does in fact
# get sent to the device. Seems like a bug in Apple's automation interface?
# Could also be a problem with the integrity of the cover data?
if lb_added:
lb_added.artworks[1].data_.set(cover_data)
try:
lb_added.artworks[1].data_.set(cover_data)
except:
if DEBUG:
self.log.warning(" iTunes automation interface reported an error"
" when adding artwork to '%s' in the iTunes Library" % metadata.title)
pass
if db_added:
# The following command generates an error, but the artwork does in fact
# get sent to the device. Seems like a bug in Apple's automation interface
try:
db_added.artworks[1].data_.set(cover_data)
except:
@ -2521,11 +2528,11 @@ class ITUNES(DriverBase):
metadata.timestamp = datetime.datetime(old_ts.year, old_ts.month, old_ts.day, old_ts.hour,
old_ts.minute, old_ts.second, old_ts.microsecond+1, old_ts.tzinfo)
else:
metadata.timestamp = isoformat(now())
metadata.timestamp = now()
if DEBUG:
self.log.info(" add timestamp: %s" % metadata.timestamp)
else:
metadata.timestamp = isoformat(now())
metadata.timestamp = now()
if DEBUG:
self.log.warning(" missing <metadata> block in OPF file")
self.log.info(" add timestamp: %s" % metadata.timestamp)

2
src/calibre/devices/blackberry/driver.py
View File

@ -19,7 +19,7 @@ class BLACKBERRY(USBMS):
VENDOR_ID = [0x0fca]
PRODUCT_ID = [0x8004, 0x0004]
BCD = [0x0200, 0x0107, 0x0210, 0x0201]
BCD = [0x0200, 0x0107, 0x0210, 0x0201, 0x0211]
VENDOR_NAME = 'RIM'
WINDOWS_MAIN_MEM = 'BLACKBERRY_SD'

Some files were not shown because too many files have changed in this diff Show More