From 29d842db3ed632afc4402a9537d444e68b27d1d5 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Fri, 20 Feb 2009 09:28:47 -0800 Subject: [PATCH 01/14] IGN:Fix #1901 (Recipe update for EPUB generation) --- src/calibre/trac/plugins/templates/linux.html | 5 ++++- src/calibre/web/feeds/recipes/recipe_la_segunda.py | 13 ++++++------- upload.py | 8 +++++++- 3 files changed, 17 insertions(+), 9 deletions(-) diff --git a/src/calibre/trac/plugins/templates/linux.html b/src/calibre/trac/plugins/templates/linux.html index 5f0f287737..066f3c9b6d 100644 --- a/src/calibre/trac/plugins/templates/linux.html +++ b/src/calibre/trac/plugins/templates/linux.html @@ -114,10 +114,13 @@ sudo python -c "import urllib2; exec urllib2.urlopen('http://calibre.kovidgoyal. wget -O- http://calibre.kovidgoyal.net/downloads/${app}-${version}.tar.gz | tar xvz cd calibre* python setup.py build && sudo python setup.py install +sudo calibre_postinstall Note that if your distribution does not have a correctly compiled libunrar.so, ${app} will not - support rar files. + support rar files. The calibre_postinstall step + is required for device detection and integration + with your desktop environment.

diff --git a/src/calibre/web/feeds/recipes/recipe_la_segunda.py b/src/calibre/web/feeds/recipes/recipe_la_segunda.py index d049d9c92b..5852e6ba9a 100644 --- a/src/calibre/web/feeds/recipes/recipe_la_segunda.py +++ b/src/calibre/web/feeds/recipes/recipe_la_segunda.py @@ -6,8 +6,8 @@ __copyright__ = '2009, Darko Miletic ' lasegunda.com ''' -from calibre.web.feeds.news import BasicNewsRecipe - +from calibre.web.feeds.news import BasicNewsRecipe + class LaSegunda(BasicNewsRecipe): title = 'La Segunda' __author__ = 'Darko Miletic' @@ -21,14 +21,16 @@ class LaSegunda(BasicNewsRecipe): encoding = 'cp1252' cover_url = 'http://www.lasegunda.com/imagenes/logotipo_lasegunda_Oli.gif' remove_javascript = True + language = _('Spanish') html2lrf_options = [ - '--comment', description + '--comment', description , '--category', category , '--publisher', publisher + , '--ignore-tables' ] - html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' + html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True\noverride_css=" p {text-indent: 0em; margin-top: 0em; margin-bottom: 0.5em} "' keep_only_tags = [dict(name='table')] @@ -52,10 +54,7 @@ class LaSegunda(BasicNewsRecipe): def preprocess_html(self, soup): mtag = '' soup.head.insert(0,mtag) - for item in soup.findAll(name='table', width=True): - del item['width'] for item in soup.findAll(style=True): del item['style'] return soup - language = _('Spanish') \ No newline at end of file diff --git a/upload.py b/upload.py index 5bd473e08d..2aeb1461ee 100644 --- a/upload.py +++ b/upload.py @@ -284,7 +284,13 @@ class gui(OptionlessCommand): manifest = '\n\n%s\n\n'%'\n'.join(files) with open('images.qrc', 'wb') as f: f.write(manifest) - check_call(['pyrcc4', '-o', images, 'images.qrc']) + try: + check_call(['pyrcc4', '-o', images, 'images.qrc']) + except: + import traceback + traceback.print_exc() + raise Exception('You do not have pyrcc4 in your PATH. ' + 'Install the PyQt4 development tools.') else: print 'Images are up to date' finally: From 8e248482aa5c7a0777cda9b5117fb305e836f04c Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Fri, 20 Feb 2009 10:17:20 -0800 Subject: [PATCH 02/14] EPUB Output: Fix regression in handling of comments that would occassionally cause content in the comments to leak into the text --- src/calibre/ebooks/epub/from_html.py | 5 ++--- src/calibre/ebooks/html.py | 14 ++++++++------ 2 files changed, 10 insertions(+), 9 deletions(-) diff --git a/src/calibre/ebooks/epub/from_html.py b/src/calibre/ebooks/epub/from_html.py index afd0af73d7..ffe402538f 100644 --- a/src/calibre/ebooks/epub/from_html.py +++ b/src/calibre/ebooks/epub/from_html.py @@ -205,9 +205,8 @@ class HTMLProcessor(Processor, Rationalizer): def save(self): for meta in list(self.root.xpath('//meta')): meta.getparent().remove(meta) - #for img in self.root.xpath('//img[@src]'): - # self.convert_image(img) - Processor.save(self) + # Strip all comments since Adobe DE is petrified of them + Processor.save(self, strip_comments=True) def remove_first_image(self): images = self.root.xpath('//img') diff --git a/src/calibre/ebooks/html.py b/src/calibre/ebooks/html.py index 340f5636eb..1c15973d3b 100644 --- a/src/calibre/ebooks/html.py +++ b/src/calibre/ebooks/html.py @@ -332,8 +332,6 @@ class PreProcessor(object): (re.compile(r'&(\S+?);'), convert_entities), # Remove the ]*>'), lambda match: ''), - # Strip all comments since Adobe DE is petrified of them - (re.compile(r'', re.DOTALL).sub('', ans) with open(self.save_path(), 'wb') as f: f.write(ans) return f.name @@ -594,7 +596,7 @@ class Processor(Parser): mark = etree.Element('hr', style=page_break_before) elem.addprevious(mark) - def save(self): + def save(self, strip_comments=False): style_path = os.path.splitext(os.path.basename(self.save_path()))[0] for i, sheet in enumerate([self.stylesheet, self.font_css, self.override_css]): if sheet is not None: @@ -608,7 +610,7 @@ class Processor(Parser): if isinstance(raw, unicode): raw = raw.encode('utf-8') open(path, 'wb').write(raw) - return Parser.save(self) + return Parser.save(self, strip_comments=strip_comments) def populate_toc(self, toc): ''' From af8f3b56ce86a33ee8e0ec8f8e909ce2c0bddf55 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Fri, 20 Feb 2009 10:58:45 -0800 Subject: [PATCH 03/14] News download: Handle HTML entities in article titles --- src/calibre/web/feeds/__init__.py | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/src/calibre/web/feeds/__init__.py b/src/calibre/web/feeds/__init__.py index 3bc1110db9..82e3f40c10 100644 --- a/src/calibre/web/feeds/__init__.py +++ b/src/calibre/web/feeds/__init__.py @@ -5,10 +5,11 @@ __copyright__ = '2008, Kovid Goyal ' ''' Contains the logic for parsing feeds. ''' -import time, logging, traceback, copy +import time, logging, traceback, copy, re from datetime import datetime from calibre.web.feeds.feedparser import parse +from calibre import entity_to_unicode from lxml import html class Article(object): @@ -19,6 +20,12 @@ class Article(object): self.downloaded = False self.id = id self.title = title.strip() if title else title + try: + self.title = re.sub(r'&(\S+);', + entity_to_unicode, self.title) + print 11111, repr(self.title) + except: + pass self.url = url self.summary = summary if summary and not isinstance(summary, unicode): @@ -37,6 +44,7 @@ class Article(object): self.date = published self.utctime = datetime(*self.date[:6]) self.localtime = self.utctime + self.time_offset + def __repr__(self): return \ @@ -91,7 +99,8 @@ class Feed(object): if len(self.articles) >= max_articles_per_feed: break self.parse_article(item) - + + def populate_from_preparsed_feed(self, title, articles, oldest_article=7, max_articles_per_feed=100): self.title = title if title else _('Unknown feed') From d221e7e448f245867479671f316520597cf86115 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Fri, 20 Feb 2009 11:42:28 -0800 Subject: [PATCH 04/14] New recipe for The Chicago Tribune by Kovid Goyal --- src/calibre/web/feeds/__init__.py | 1 - src/calibre/web/feeds/recipes/__init__.py | 2 +- .../feeds/recipes/recipe_chicago_tribune.py | 82 +++++++++++++++++++ 3 files changed, 83 insertions(+), 2 deletions(-) create mode 100644 src/calibre/web/feeds/recipes/recipe_chicago_tribune.py diff --git a/src/calibre/web/feeds/__init__.py b/src/calibre/web/feeds/__init__.py index 82e3f40c10..3f0ec414a2 100644 --- a/src/calibre/web/feeds/__init__.py +++ b/src/calibre/web/feeds/__init__.py @@ -23,7 +23,6 @@ class Article(object): try: self.title = re.sub(r'&(\S+);', entity_to_unicode, self.title) - print 11111, repr(self.title) except: pass self.url = url diff --git a/src/calibre/web/feeds/recipes/__init__.py b/src/calibre/web/feeds/recipes/__init__.py index 19c4f2827a..92fbbda555 100644 --- a/src/calibre/web/feeds/recipes/__init__.py +++ b/src/calibre/web/feeds/recipes/__init__.py @@ -30,7 +30,7 @@ recipe_modules = ['recipe_' + r for r in ( 'honoluluadvertiser', 'starbulletin', 'exiled', 'indy_star', 'dna', 'pobjeda', 'chicago_breaking_news', 'glasgow_herald', 'linuxdevices', 'hindu', 'cincinnati_enquirer', 'physics_world', 'pressonline', - 'la_republica', 'physics_today', + 'la_republica', 'physics_today', 'chicago_tribune', )] import re, imp, inspect, time, os diff --git a/src/calibre/web/feeds/recipes/recipe_chicago_tribune.py b/src/calibre/web/feeds/recipes/recipe_chicago_tribune.py new file mode 100644 index 0000000000..a4754dd751 --- /dev/null +++ b/src/calibre/web/feeds/recipes/recipe_chicago_tribune.py @@ -0,0 +1,82 @@ +from __future__ import with_statement +__license__ = 'GPL 3' +__copyright__ = '2009, Kovid Goyal ' +__docformat__ = 'restructuredtext en' + +import re +from urlparse import urlparse, urlunparse +from calibre.web.feeds.news import BasicNewsRecipe +from calibre.ptempfile import PersistentTemporaryFile +from threading import RLock + +class ChicagoTribune(BasicNewsRecipe): + + title = 'Chicago Tribune' + __author__ = 'Kovid Goyal' + description = 'Politics, local and business news from Chicago' + language = _('English') + use_embedded_content = False + articles_are_obfuscated = True + remove_tags_before = dict(name='h1') + obfuctation_lock = RLock() + + feeds = [ + ('Latest news', 'http://feeds.chicagotribune.com/chicagotribune/news/'), + ('Local news', 'http://feeds.chicagotribune.com/chicagotribune/news/local/'), + ('Nation/world', 'http://feeds.chicagotribune.com/chicagotribune/news/nationworld/'), + ('Hot topics', 'http://feeds.chicagotribune.com/chicagotribune/hottopics/'), + ('Most E-mailed stories', 'http://feeds.chicagotribune.com/chicagotribune/email/'), + ('Opinion', 'http://feeds.chicagotribune.com/chicagotribune/opinion/'), + ('Off Topic', 'http://feeds.chicagotribune.com/chicagotribune/offtopic/'), + ('Politics', 'http://feeds.chicagotribune.com/chicagotribune/politics/'), + ('Special Reports', 'http://feeds.chicagotribune.com/chicagotribune/special/'), + ('Religion News', 'http://feeds.chicagotribune.com/chicagotribune/religion/'), + ('Business news', 'http://feeds.chicagotribune.com/chicagotribune/business/'), + ('Jobs and Careers', 'http://feeds.chicagotribune.com/chicagotribune/career/'), + ('Local scene', 'http://feeds.chicagotribune.com/chicagohomes/localscene/'), + ('Phil Rosenthal', 'http://feeds.chicagotribune.com/chicagotribune/rosenthal/'), + ('Tech Buzz', 'http://feeds.chicagotribune.com/chicagotribune/techbuzz/'), + ('Your Money', 'http://feeds.chicagotribune.com/chicagotribune/yourmoney/'), + ('Jon Hilkevitch - Getting around', 'http://feeds.chicagotribune.com/chicagotribune/gettingaround/'), + ('Jon Yates - What\'s your problem?', 'http://feeds.chicagotribune.com/chicagotribune/problem/'), + ('Garisson Keillor', 'http://feeds.chicagotribune.com/chicagotribune/keillor/'), + ('Marks Jarvis - On Money', 'http://feeds.chicagotribune.com/chicagotribune/marksjarvisonmoney/'), + ('Sports', 'http://feeds.chicagotribune.com/chicagotribune/sports/'), + ('Arts and Architecture', 'http://feeds.chicagotribune.com/chicagotribune/arts/'), + ('Books', 'http://feeds.chicagotribune.com/chicagotribune/books/'), + ('Magazine', 'http://feeds.chicagotribune.com/chicagotribune/magazine/'), + ('Movies', 'http://feeds.chicagotribune.com/chicagotribune/movies/'), + ('Music', 'http://feeds.chicagotribune.com/chicagotribune/movies/'), + ('TV', 'http://feeds.chicagotribune.com/chicagotribune/tv/'), + ('Hypertext', 'http://feeds.chicagotribune.com/chicagotribune/hypertext/'), + ('iPhone Blog', 'http://feeds.feedburner.com/redeye/iphoneblog'), + ('Julie\'s Health Club', 'http://feeds.chicagotribune.com/chicagotribune_julieshealthclub/'), + ] + + temp_files = [] + + def get_article_url(self, article): + return article.get('feedburner_origlink', article.get('guid', article.get('link'))) + + def get_obfuscated_article(self, url, logger): + with self.obfuctation_lock: + soup = self.index_to_soup(url) + img = soup.find('img', alt='Print') + if img is not None: + a = img.parent.find('a', href=True) + purl = urlparse(url) + xurl = urlunparse(purl[:2] + (a['href'], '', '', '')) + soup = self.index_to_soup(xurl) + for img in soup.findAll('img', src=True): + if img['src'].startswith('/'): + img['src'] = urlunparse(purl[:2]+(img['src'], '', '', '')) + html = unicode(soup) + else: + h1 = soup.find(id='page-title') + body = soup.find(attrs={'class':re.compile('asset-content')}) + html = u'%s'%(unicode(h1)+unicode(body)) + self.temp_files.append(PersistentTemporaryFile('_chicago_tribune.xhtml')) + self.temp_files[-1].write(html.encode('utf-8')) + self.temp_files[-1].close() + return self.temp_files[-1].name + From e6473047fec2fde9a31f1bdb437d4459d0031726 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Fri, 20 Feb 2009 11:47:03 -0800 Subject: [PATCH 05/14] FB2 input:Fix regression that prevented metadata from being read from input FB2 file when converting on the command line --- src/calibre/ebooks/lrf/fb2/convert_from.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/src/calibre/ebooks/lrf/fb2/convert_from.py b/src/calibre/ebooks/lrf/fb2/convert_from.py index dc4644d292..24562e708c 100644 --- a/src/calibre/ebooks/lrf/fb2/convert_from.py +++ b/src/calibre/ebooks/lrf/fb2/convert_from.py @@ -38,6 +38,7 @@ def extract_embedded_content(doc): open(fname, 'wb').write(data) def to_html(fb2file, tdir): + fb2file = os.path.abspath(fb2file) cwd = os.getcwd() try: os.chdir(tdir) @@ -52,7 +53,7 @@ def to_html(fb2file, tdir): result = transform(doc) open('index.html', 'wb').write(transform.tostring(result)) try: - mi = get_metadata(open(fb2file, 'rb')) + mi = get_metadata(open(fb2file, 'rb'), 'fb2') except: mi = MetaInformation(None, None) if not mi.title: From 70b99872c670aeb11f2cfa11ed8ff82a79f129c2 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Fri, 20 Feb 2009 13:07:32 -0800 Subject: [PATCH 06/14] EPUB Output:Be less aggressive when stripping invalid HTML constructs inserted by MS Word. Fixes regression in the Time recipe. --- src/calibre/ebooks/html.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/src/calibre/ebooks/html.py b/src/calibre/ebooks/html.py index 1c15973d3b..1f1e6b94b1 100644 --- a/src/calibre/ebooks/html.py +++ b/src/calibre/ebooks/html.py @@ -331,7 +331,8 @@ class PreProcessor(object): # Convert all entities, since lxml doesn't handle them well (re.compile(r'&(\S+?);'), convert_entities), # Remove the ]*>'), lambda match: ''), + (re.compile(r'', re.IGNORECASE), + lambda match: ''), ] # Fix pdftohtml markup From c5bae5d403a4e9518372d5889212ca2813ace9e5 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Fri, 20 Feb 2009 14:40:16 -0800 Subject: [PATCH 07/14] Fix #1888 (Bulk Convert Problem) --- src/calibre/ebooks/lrf/__init__.py | 1 + 1 file changed, 1 insertion(+) diff --git a/src/calibre/ebooks/lrf/__init__.py b/src/calibre/ebooks/lrf/__init__.py index 2f9d724ce2..ae74e429ad 100644 --- a/src/calibre/ebooks/lrf/__init__.py +++ b/src/calibre/ebooks/lrf/__init__.py @@ -30,6 +30,7 @@ preferred_source_formats = [ 'XHTML', 'PRC', 'AZW', + 'FB2', 'RTF', 'PDF', 'TXT', From 7475c520ab5fba4b1598e093672e93dee0779463 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Fri, 20 Feb 2009 16:19:34 -0800 Subject: [PATCH 08/14] version 0.4.139 --- src/calibre/constants.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/calibre/constants.py b/src/calibre/constants.py index a903e67e04..e6f9b771e9 100644 --- a/src/calibre/constants.py +++ b/src/calibre/constants.py @@ -2,7 +2,7 @@ __license__ = 'GPL v3' __copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net' __docformat__ = 'restructuredtext en' __appname__ = 'calibre' -__version__ = '0.4.138' +__version__ = '0.4.139' __author__ = "Kovid Goyal " ''' Various run time constants. From 40c50665c5a7572278f3b00594792e3f63794d4c Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Fri, 20 Feb 2009 16:32:55 -0800 Subject: [PATCH 09/14] IGN:Tag release From 544346837cfddd44c9c6f0647061864b8bd208d9 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sat, 21 Feb 2009 11:17:59 -0800 Subject: [PATCH 10/14] New recipes for E-Novine and Al Jazeera by Darko Miletic --- src/calibre/gui2/images/news/e_novine.png | Bin 0 -> 295 bytes src/calibre/web/feeds/recipes/__init__.py | 3 +- .../web/feeds/recipes/recipe_al_jazeera.py | 50 +++++++++++++++ .../web/feeds/recipes/recipe_e_novine.py | 58 ++++++++++++++++++ upload.py | 4 +- 5 files changed, 112 insertions(+), 3 deletions(-) create mode 100644 src/calibre/gui2/images/news/e_novine.png create mode 100644 src/calibre/web/feeds/recipes/recipe_al_jazeera.py create mode 100644 src/calibre/web/feeds/recipes/recipe_e_novine.py diff --git a/src/calibre/gui2/images/news/e_novine.png b/src/calibre/gui2/images/news/e_novine.png new file mode 100644 index 0000000000000000000000000000000000000000..285e1e6a4dea0e28776141fd3c836b2ae5b3b1d6 GIT binary patch literal 295 zcmeAS@N?(olHy`uVBq!ia0vp^0wB!61|;P_|4#%`Y)RhkE)4%caKYZ?lYt_f1s;*b zK-vS0-A-oPfdtD69Mgd`SU*F|v9*VRoB&T3#}JFt$tev?W#88Q=TT{xZ+}`sQbIyv zhR4Mg-VG0oB*h)dHMtGDK1lj)6#pRg;d8pAvZ8*Vy+9`?_phA|6aKdsO9(tJmuS$I z*>H!0p~qC_?}}I6AP1|KxJHyD7o{ear0S*s2?iqr14~^4BV8lI5JO8V0~0Gl18oBX wD+7bSi3>oE0c*(3PsvQH#L!@1Ze?U)Wnu!+V13Mk6R3f~)78&qol`;+04`uupa1{> literal 0 HcmV?d00001 diff --git a/src/calibre/web/feeds/recipes/__init__.py b/src/calibre/web/feeds/recipes/__init__.py index 92fbbda555..eed5670cac 100644 --- a/src/calibre/web/feeds/recipes/__init__.py +++ b/src/calibre/web/feeds/recipes/__init__.py @@ -30,7 +30,8 @@ recipe_modules = ['recipe_' + r for r in ( 'honoluluadvertiser', 'starbulletin', 'exiled', 'indy_star', 'dna', 'pobjeda', 'chicago_breaking_news', 'glasgow_herald', 'linuxdevices', 'hindu', 'cincinnati_enquirer', 'physics_world', 'pressonline', - 'la_republica', 'physics_today', 'chicago_tribune', + 'la_republica', 'physics_today', 'chicago_tribune', 'e_novine', + 'al_jazeera', )] import re, imp, inspect, time, os diff --git a/src/calibre/web/feeds/recipes/recipe_al_jazeera.py b/src/calibre/web/feeds/recipes/recipe_al_jazeera.py new file mode 100644 index 0000000000..9923f00392 --- /dev/null +++ b/src/calibre/web/feeds/recipes/recipe_al_jazeera.py @@ -0,0 +1,50 @@ +#!/usr/bin/env python + +__license__ = 'GPL v3' +__copyright__ = '2009, Darko Miletic ' + +''' +aljazeera.net +''' +from calibre.web.feeds.news import BasicNewsRecipe + +class AlJazeera(BasicNewsRecipe): + title = 'Al Jazeera in English' + __author__ = 'Darko Miletic' + description = 'News from Middle East' + publisher = 'Al Jazeera' + category = 'news, politics, middle east' + simultaneous_downloads = 1 + delay = 4 + oldest_article = 1 + max_articles_per_feed = 100 + no_stylesheets = True + encoding = 'iso-8859-1' + remove_javascript = True + use_embedded_content = False + + html2lrf_options = [ + '--comment', description + , '--category', category + , '--publisher', publisher + , '--ignore-tables' + ] + + html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_table=True' + + keep_only_tags = [dict(name='div', attrs={'id':'ctl00_divContent'})] + + remove_tags = [ + dict(name=['object','link']) + ,dict(name='td', attrs={'class':['MostActiveDescHeader','MostActiveDescBody']}) + ] + + feeds = [(u'AL JAZEERA ENGLISH (AJE)', u'http://english.aljazeera.net/Services/Rss/?PostingId=2007731105943979989' )] + + def preprocess_html(self, soup): + for item in soup.findAll(style=True): + del item['style'] + for item in soup.findAll(face=True): + del item['face'] + return soup + diff --git a/src/calibre/web/feeds/recipes/recipe_e_novine.py b/src/calibre/web/feeds/recipes/recipe_e_novine.py new file mode 100644 index 0000000000..83654fe4c8 --- /dev/null +++ b/src/calibre/web/feeds/recipes/recipe_e_novine.py @@ -0,0 +1,58 @@ +#!/usr/bin/env python + +__license__ = 'GPL v3' +__copyright__ = '2009, Darko Miletic ' + +''' +e-novine.com +''' + +import re +from calibre.web.feeds.news import BasicNewsRecipe + +class E_novine(BasicNewsRecipe): + title = 'E-Novine' + __author__ = 'Darko Miletic' + description = 'News from Serbia' + publisher = 'E-novine' + category = 'news, politics, Balcans' + oldest_article = 1 + max_articles_per_feed = 100 + no_stylesheets = True + encoding = 'cp1250' + cover_url = 'http://www.e-novine.com/slike/slike_3/r1/g2008/m03/y3165525326702598.jpg' + remove_javascript = True + use_embedded_content = False + language = _('Serbian') + 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{text-align: justify; font-family: serif1, serif} .article_description{font-family: sans1, sans-serif}' + + html2lrf_options = [ + '--comment', description + , '--category', category + , '--publisher', publisher + ] + + html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\noverride_css=" p {text-indent: 0em; margin-top: 0em; margin-bottom: 0.5em} img {margin-top: 0em; margin-bottom: 0.4em}"' + + preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] + + keep_only_tags = [dict(name='div', attrs={'id':['css_47_0_2844H']})] + + remove_tags = [dict(name=['object','link','embed','iframe'])] + + feeds = [(u'Sve vesti', u'http://www.e-novine.com/rss/e-novine.xml' )] + + def preprocess_html(self, soup): + soup.html['xml:lang'] = 'sr-Latn-ME' + soup.html['lang'] = 'sr-Latn-ME' + mtag = '' + soup.head.insert(0,mtag) + for item in soup.findAll(style=True): + del item['style'] + ftag = soup.find('div', attrs={'id':'css_47_0_2844H'}) + if ftag: + it = ftag.div + it.extract() + ftag.div.extract() + ftag.insert(0,it) + return soup diff --git a/upload.py b/upload.py index 2aeb1461ee..cab426b191 100644 --- a/upload.py +++ b/upload.py @@ -676,7 +676,7 @@ class stage3(OptionlessCommand): def run(self): OptionlessCommand.run(self) - self.misc() + self.misc() class stage2(OptionlessCommand): description = 'Stage 2 of the build process' @@ -705,4 +705,4 @@ class upload(OptionlessCommand): ('stage1', None), ('stage2', None), ('stage3', None) - ] \ No newline at end of file + ] From 2eee9da901dac31ca2259984014e61dc54b1c7b2 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sat, 21 Feb 2009 11:23:06 -0800 Subject: [PATCH 11/14] IGN:Fix #1906 (Minor fixes in spanish recipes) --- src/calibre/web/feeds/recipes/recipe_infobae.py | 5 +++-- src/calibre/web/feeds/recipes/recipe_pagina12.py | 12 +++++------- 2 files changed, 8 insertions(+), 9 deletions(-) diff --git a/src/calibre/web/feeds/recipes/recipe_infobae.py b/src/calibre/web/feeds/recipes/recipe_infobae.py index 13c52ca6b1..b5c867b914 100644 --- a/src/calibre/web/feeds/recipes/recipe_infobae.py +++ b/src/calibre/web/feeds/recipes/recipe_infobae.py @@ -19,7 +19,7 @@ class Infobae(BasicNewsRecipe): no_stylesheets = True use_embedded_content = False language = _('Spanish') - encoding = 'iso-8859-1' + encoding = 'cp1252' cover_url = 'http://www.infobae.com/imgs/header/header.gif' remove_javascript = True @@ -28,9 +28,10 @@ class Infobae(BasicNewsRecipe): , '--category' , category , '--publisher', publisher , '--ignore-tables' + , '--ignore-colors' ] - html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True' + html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True' remove_tags = [ dict(name=['embed','link','object']) diff --git a/src/calibre/web/feeds/recipes/recipe_pagina12.py b/src/calibre/web/feeds/recipes/recipe_pagina12.py index b821ed0b68..f3ed1110fa 100644 --- a/src/calibre/web/feeds/recipes/recipe_pagina12.py +++ b/src/calibre/web/feeds/recipes/recipe_pagina12.py @@ -8,10 +8,8 @@ pagina12.com.ar from calibre import strftime -from calibre.web.feeds.news import BasicNewsRecipe - class Pagina12(BasicNewsRecipe): - title = u'Pagina/12' + title = 'Pagina/12' __author__ = 'Darko Miletic' description = 'Noticias de Argentina y el resto del mundo' publisher = 'La Pagina S.A.' @@ -20,12 +18,14 @@ class Pagina12(BasicNewsRecipe): max_articles_per_feed = 100 no_stylesheets = True encoding = 'cp1252' - cover_url = strftime('http://www.pagina12.com.ar/fotos/%Y%m%d/diario/TAPAN.jpg') + cover_url = strftime('http://www.pagina12.com.ar/fotos/%Y%m%d/diario/tapagn.jpg') remove_javascript = True use_embedded_content = False + language = _('Spanish') + html2lrf_options = [ - '--comment', description + '--comment', description , '--category', category , '--publisher', publisher ] @@ -50,5 +50,3 @@ class Pagina12(BasicNewsRecipe): for item in soup.findAll(style=True): del item['style'] return soup - - language = _('Spanish') \ No newline at end of file From 0467af0c29d5571da100b92f682de4e7dfa82476 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sat, 21 Feb 2009 11:38:24 -0800 Subject: [PATCH 12/14] Cybook Gen3:Fix thumbnail generation. --- src/calibre/devices/cybookg3/driver.py | 1 + src/calibre/devices/cybookg3/t2b.py | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/src/calibre/devices/cybookg3/driver.py b/src/calibre/devices/cybookg3/driver.py index f092473675..eef32594eb 100644 --- a/src/calibre/devices/cybookg3/driver.py +++ b/src/calibre/devices/cybookg3/driver.py @@ -33,6 +33,7 @@ class CYBOOKG3(USBMS): EBOOK_DIR_MAIN = "eBooks" EBOOK_DIR_CARD = "eBooks" + THUMBNAIL_HEIGHT = 144 SUPPORTS_SUB_DIRS = True def upload_books(self, files, names, on_card=False, end_session=True, diff --git a/src/calibre/devices/cybookg3/t2b.py b/src/calibre/devices/cybookg3/t2b.py index 5bf512f22d..7aaeeb63d7 100644 --- a/src/calibre/devices/cybookg3/t2b.py +++ b/src/calibre/devices/cybookg3/t2b.py @@ -30,7 +30,7 @@ def write_t2b(t2bfile, coverdata=None): if coverdata != None: coverdata = StringIO.StringIO(coverdata) cover = Image.open(coverdata).convert("L") - cover.thumbnail((96, 144)) + cover.thumbnail((96, 144), Image.ANTIALIAS) t2bcover = Image.new('L', (96, 144), 'white') x, y = cover.size From cfcccb044340f850a45dfa76e7a099d9c78bf2a0 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sat, 21 Feb 2009 13:12:52 -0800 Subject: [PATCH 13/14] IGN:... --- src/calibre/web/feeds/recipes/recipe_pagina12.py | 1 + 1 file changed, 1 insertion(+) diff --git a/src/calibre/web/feeds/recipes/recipe_pagina12.py b/src/calibre/web/feeds/recipes/recipe_pagina12.py index f3ed1110fa..039e8a8e15 100644 --- a/src/calibre/web/feeds/recipes/recipe_pagina12.py +++ b/src/calibre/web/feeds/recipes/recipe_pagina12.py @@ -7,6 +7,7 @@ pagina12.com.ar ''' from calibre import strftime +from calibre.web.feeds.news import BasicNewsRecipe class Pagina12(BasicNewsRecipe): title = 'Pagina/12' From 6c8d6a4edb0c2b90537db744caf37f51c8badc6f Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sat, 21 Feb 2009 18:56:01 -0800 Subject: [PATCH 14/14] New recipe for Windows SuperSite by Hypernova --- src/calibre/customize/builtins.py | 4 +-- src/calibre/web/feeds/recipes/__init__.py | 2 +- .../web/feeds/recipes/recipe_winsupersite.py | 28 +++++++++++++++++++ 3 files changed, 31 insertions(+), 3 deletions(-) create mode 100644 src/calibre/web/feeds/recipes/recipe_winsupersite.py diff --git a/src/calibre/customize/builtins.py b/src/calibre/customize/builtins.py index a40878480f..14d3c79062 100644 --- a/src/calibre/customize/builtins.py +++ b/src/calibre/customize/builtins.py @@ -233,7 +233,7 @@ class RTFMetadataWriter(MetadataWriterPlugin): class MOBIMetadataWriter(MetadataWriterPlugin): name = 'Set MOBI metadata' - file_types = set(['mobi', 'prc']) + file_types = set(['mobi', 'prc', 'azw']) description = _('Set metadata in %s files')%'MOBI' author = 'Marshall T. Vandegrift' @@ -246,4 +246,4 @@ plugins = [HTML2ZIP] plugins += [x for x in list(locals().values()) if isinstance(x, type) and \ x.__name__.endswith('MetadataReader')] plugins += [x for x in list(locals().values()) if isinstance(x, type) and \ - x.__name__.endswith('MetadataWriter')] \ No newline at end of file + x.__name__.endswith('MetadataWriter')] diff --git a/src/calibre/web/feeds/recipes/__init__.py b/src/calibre/web/feeds/recipes/__init__.py index eed5670cac..579291a83b 100644 --- a/src/calibre/web/feeds/recipes/__init__.py +++ b/src/calibre/web/feeds/recipes/__init__.py @@ -31,7 +31,7 @@ recipe_modules = ['recipe_' + r for r in ( 'pobjeda', 'chicago_breaking_news', 'glasgow_herald', 'linuxdevices', 'hindu', 'cincinnati_enquirer', 'physics_world', 'pressonline', 'la_republica', 'physics_today', 'chicago_tribune', 'e_novine', - 'al_jazeera', + 'al_jazeera', 'winsupersite', )] import re, imp, inspect, time, os diff --git a/src/calibre/web/feeds/recipes/recipe_winsupersite.py b/src/calibre/web/feeds/recipes/recipe_winsupersite.py new file mode 100644 index 0000000000..fc6bc54da2 --- /dev/null +++ b/src/calibre/web/feeds/recipes/recipe_winsupersite.py @@ -0,0 +1,28 @@ +import re + +from calibre.web.feeds.news import BasicNewsRecipe + +class Winsupersite(BasicNewsRecipe): + title = u'Supersite for Windows' + description = u'Paul Thurrott SuperSite for Windows' + publisher = 'Paul Thurrott' + __author__ = 'Hypernova' + language = _('English') + oldest_article = 30 + max_articles_per_feed = 100 + no_stylesheets = True + use_embedded_content = False + remove_javascript = True + html2lrf_options = ['--ignore-tables'] + html2epub_options = 'linearize_tables = True' + remove_tags_before = dict(name='h1') + preprocess_regexps = [ + (re.compile(r'

--Paul Thurrott.*', re.DOTALL|re.IGNORECASE), + lambda match: ''), +] + def get_browser(self): + br = BasicNewsRecipe.get_browser() + br.open('http://www.winsupersite.com') + return br + + feeds = [(u'Supersite for Windows', u'http://www.winsupersite.com/supersite.xml')]