diff --git a/resources/images/news/science_news_recent_issues.png b/resources/images/news/science_news_recent_issues.png new file mode 100644 index 0000000000..355fb8c3a6 Binary files /dev/null and b/resources/images/news/science_news_recent_issues.png differ diff --git a/resources/recipes/science_news_recent_issues.recipe b/resources/recipes/science_news_recent_issues.recipe new file mode 100644 index 0000000000..7eb93e0d59 --- /dev/null +++ b/resources/recipes/science_news_recent_issues.recipe @@ -0,0 +1,78 @@ +#!/usr/bin/env python + +__license__ = 'GPL v3' +''' +sciencenews.org +''' +from calibre.web.feeds.news import BasicNewsRecipe + +class ScienceNewsIssue(BasicNewsRecipe): + title = u'Science News Recent Issues' + __author__ = u'Darko Miletic, Sujata Raman and Starson17' + description = u'''Science News is an award-winning weekly + newsmagazine covering the most important research in all fields of science. + Its 16 pages each week are packed with short, accurate articles that appeal + to both general readers and scientists. Published since 1922, the magazine + now reaches about 150,000 subscribers and more than 1 million readers. + These are the latest News Items from Science News. This recipe downloads + the last 30 days worth of articles.''' + category = u'Science, Technology, News' + publisher = u'Society for Science & the Public' + oldest_article = 30 + language = 'en' + max_articles_per_feed = 100 + no_stylesheets = True + use_embedded_content = False + timefmt = ' [%A, %d %B, %Y]' + recursions = 1 + remove_attributes = ['style'] + + conversion_options = {'linearize_tables' : True + , 'comment' : description + , 'tags' : category + , 'publisher' : publisher + , 'language' : language + } + + extra_css = ''' + .content_description{font-family:georgia ;font-size:x-large; color:#646464 ; font-weight:bold;} + .content_summary{font-family:georgia ;font-size:small ;color:#585858 ; font-weight:bold;} + .content_authors{font-family:helvetica,arial ;font-size: xx-small ;color:#14487E ;} + .content_edition{font-family:helvetica,arial ;font-size: xx-small ;} + .exclusive{color:#FF0000 ;} + .anonymous{color:#14487E ;} + .content_content{font-family:helvetica,arial ;font-size: medium ; color:#000000;} + .description{color:#585858;font-family:helvetica,arial ;font-size: large ;} + .credit{color:#A6A6A6;font-family:helvetica,arial ;font-size: xx-small ;} + ''' + + keep_only_tags = [ dict(name='div', attrs={'id':'column_action'}) ] + remove_tags_after = dict(name='ul', attrs={'id':'content_functions_bottom'}) + remove_tags = [ + dict(name='ul', attrs={'id':'content_functions_bottom'}) + ,dict(name='div', attrs={'id':['content_functions_top','breadcrumb_content']}) + ,dict(name='img', attrs={'class':'icon'}) + ,dict(name='div', attrs={'class': 'embiggen'}) + ] + + feeds = [(u"Science News Current Issues", u'http://www.sciencenews.org/view/feed/type/edition/name/issues.rss')] + + match_regexps = [ + r'www.sciencenews.org/view/feature/id/', + r'www.sciencenews.org/view/generic/id' + ] + + def get_cover_url(self): + cover_url = None + index = 'http://www.sciencenews.org/view/home' + soup = self.index_to_soup(index) + link_item = soup.find(name = 'img',alt = "issue") + if link_item: + cover_url = 'http://www.sciencenews.org' + link_item['src'] + '.jpg' + + return cover_url + + def preprocess_html(self, soup): + for tag in soup.findAll(name=['span']): + tag.name = 'div' + return soup diff --git a/src/calibre/customize/profiles.py b/src/calibre/customize/profiles.py index 0310f09242..1d879f0c5d 100644 --- a/src/calibre/customize/profiles.py +++ b/src/calibre/customize/profiles.py @@ -255,6 +255,9 @@ class OutputProfile(Plugin): #: Unsupported unicode characters to be replaced during preprocessing unsupported_unicode_chars = [] + #: Number of ems that the left margin of a blockquote is rendered as + mobi_ems_per_blockquote = 1.0 + @classmethod def tags_to_string(cls, tags): return escape(', '.join(tags)) @@ -564,6 +567,7 @@ class KindleOutput(OutputProfile): supports_mobi_indexing = True periodical_date_in_title = False ratings_char = u'\u2605' + mobi_ems_per_blockquote = 2.0 @classmethod def tags_to_string(cls, tags): @@ -582,6 +586,7 @@ class KindleDXOutput(OutputProfile): comic_screen_size = (741, 1022) supports_mobi_indexing = True periodical_date_in_title = False + mobi_ems_per_blockquote = 2.0 @classmethod def tags_to_string(cls, tags): diff --git a/src/calibre/ebooks/epub/input.py b/src/calibre/ebooks/epub/input.py index 214511ae14..cdd69ea50f 100644 --- a/src/calibre/ebooks/epub/input.py +++ b/src/calibre/ebooks/epub/input.py @@ -117,7 +117,8 @@ class EPUBInput(InputFormatPlugin): encfile = os.path.abspath(os.path.join('META-INF', 'encryption.xml')) opf = None for f in walk(u'.'): - if f.lower().endswith('.opf') and '__MACOSX' not in f: + if f.lower().endswith('.opf') and '__MACOSX' not in f and \ + not os.path.basename(f).startswith('.'): opf = os.path.abspath(f) break path = getattr(stream, 'name', 'stream') diff --git a/src/calibre/ebooks/metadata/fb2.py b/src/calibre/ebooks/metadata/fb2.py index 576fbaa6fc..6e0d56dfa0 100644 --- a/src/calibre/ebooks/metadata/fb2.py +++ b/src/calibre/ebooks/metadata/fb2.py @@ -33,7 +33,10 @@ def get_metadata(stream): le = XPath('descendant::fb2:last-name')(au) if le: lname = tostring(le[0]) - author += ' '+lname + if author: + author += ' '+lname + else: + author = lname if author: authors.append(author) if len(authors) == 1 and author is not None: diff --git a/src/calibre/ebooks/mobi/mobiml.py b/src/calibre/ebooks/mobi/mobiml.py index 231ad51eee..a822e66758 100644 --- a/src/calibre/ebooks/mobi/mobiml.py +++ b/src/calibre/ebooks/mobi/mobiml.py @@ -184,13 +184,14 @@ class MobiMLizer(object): elif tag in NESTABLE_TAGS and istate.rendered: para = wrapper = bstate.nested[-1] elif left > 0 and indent >= 0: + ems = self.profile.mobi_ems_per_blockquote para = wrapper = etree.SubElement(parent, XHTML('blockquote')) para = wrapper - emleft = int(round(left / self.profile.fbase)) - 1 + emleft = int(round(left / self.profile.fbase)) - ems emleft = min((emleft, 10)) while emleft > 0: para = etree.SubElement(para, XHTML('blockquote')) - emleft -= 1 + emleft -= ems else: para = wrapper = etree.SubElement(parent, XHTML('p')) bstate.inline = bstate.para = para diff --git a/src/calibre/ebooks/mobi/output.py b/src/calibre/ebooks/mobi/output.py index 49da18ea7b..d82704a0df 100644 --- a/src/calibre/ebooks/mobi/output.py +++ b/src/calibre/ebooks/mobi/output.py @@ -41,6 +41,24 @@ class MOBIOutput(OutputFormatPlugin): ), ]) + def remove_image_transparencies(self): + from calibre.utils.magick.draw import save_cover_data_to + for item in self.oeb.manifest: + if item.media_type.startswith('image'): + raw = item.data + ext = item.media_type.split('/')[-1].lower() + if ext not in ('png', 'gif') or not raw: + continue + try: + data = save_cover_data_to(raw, 'img.'+ext, return_data=True) + except: + self.log.exception('Failed to remove transparency from', + item.href) + data = None + if data is not None: + item.data = data + item.unload_data_from_memory() + def check_for_periodical(self): if self.oeb.metadata.publication_type and \ unicode(self.oeb.metadata.publication_type[0]).startswith('periodical:'): @@ -160,6 +178,7 @@ class MOBIOutput(OutputFormatPlugin): from calibre.ebooks.oeb.transforms.rasterize import SVGRasterizer, Unavailable from calibre.ebooks.oeb.transforms.htmltoc import HTMLTOCAdder from calibre.customize.ui import plugin_for_input_format + self.remove_image_transparencies() imagemax = PALM_MAX_IMAGE_SIZE if opts.rescale_images else None if not opts.no_inline_toc: tocadder = HTMLTOCAdder(title=opts.toc_title) diff --git a/src/calibre/ebooks/mobi/reader.py b/src/calibre/ebooks/mobi/reader.py index 6a44c2aa77..dbe6854006 100644 --- a/src/calibre/ebooks/mobi/reader.py +++ b/src/calibre/ebooks/mobi/reader.py @@ -234,7 +234,7 @@ class MobiReader(object): self.debug = debug self.embedded_mi = None self.base_css_rules = textwrap.dedent(''' - blockquote { margin: 0em 0em 0em 1.25em; text-align: justify } + blockquote { margin: 0em 0em 0em 2em; text-align: justify } p { margin: 0em; text-align: justify } diff --git a/src/calibre/ebooks/oeb/transforms/rescale.py b/src/calibre/ebooks/oeb/transforms/rescale.py index c3b4d6d40c..79d4c76487 100644 --- a/src/calibre/ebooks/oeb/transforms/rescale.py +++ b/src/calibre/ebooks/oeb/transforms/rescale.py @@ -39,7 +39,7 @@ class RescaleImages(object): if item.media_type.startswith('image'): ext = item.media_type.split('/')[-1].upper() if ext == 'JPG': ext = 'JPEG' - if ext not in ('PNG', 'JPEG'): + if ext not in ('PNG', 'JPEG', 'GIF'): ext = 'JPEG' raw = item.data diff --git a/src/calibre/gui2/dialogs/tweak_epub.ui b/src/calibre/gui2/dialogs/tweak_epub.ui index 063460aaae..fc6f24675f 100644 --- a/src/calibre/gui2/dialogs/tweak_epub.ui +++ b/src/calibre/gui2/dialogs/tweak_epub.ui @@ -10,7 +10,7 @@ 0 0 382 - 242 + 265 diff --git a/src/calibre/gui2/preferences/plugboard.ui b/src/calibre/gui2/preferences/plugboard.ui index 289518816f..b73c396481 100644 --- a/src/calibre/gui2/preferences/plugboard.ui +++ b/src/calibre/gui2/preferences/plugboard.ui @@ -19,7 +19,7 @@ Here you can change the metadata calibre uses to update a book when saving to disk or sending to device. -Use this dialog to define a 'plugboard' for a format (or all formats) and a device (or all devices). The plugboard spefies what template is connected to what field. The template is used to compute a value, and that value is assigned to the connected field. +Use this dialog to define a 'plugboard' for a format (or all formats) and a device (or all devices). The plugboard specifies what template is connected to what field. The template is used to compute a value, and that value is assigned to the connected field. Often templates will contain simple references to composite columns, but this is not necessary. You can use any template in a source box that you can use elsewhere in calibre.