From 7ba005f3e0516aa02ff2d4d86c08bd02430eddd6 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sun, 22 Nov 2009 08:14:34 -0700 Subject: [PATCH] IGN:... --- resources/recipes/fokkeensukke.recipe | 174 +++++++++++------------ src/calibre/ebooks/conversion/plumber.py | 8 +- src/calibre/ebooks/pml/pmlconverter.py | 4 +- src/calibre/manual/conversion.rst | 2 +- 4 files changed, 95 insertions(+), 93 deletions(-) diff --git a/resources/recipes/fokkeensukke.recipe b/resources/recipes/fokkeensukke.recipe index 5627631770..3ddbe1cfe5 100644 --- a/resources/recipes/fokkeensukke.recipe +++ b/resources/recipes/fokkeensukke.recipe @@ -1,87 +1,87 @@ -#!/usr/bin/python -from calibre.web.feeds.news import BasicNewsRecipe -from calibre.ebooks.BeautifulSoup import Tag - - -class FokkeEnSukkeRecipe(BasicNewsRecipe) : - __license__ = 'GPL v3' - __author__ = 'kwetal' - language = 'nl' - description = u'Popular Dutch daily cartoon Fokke en Sukke' - - title = u'Fokke en Sukke' - no_stylesheets = True - # For reasons unknown to me the extra css is, on the cartoon pages, inserted in the and not in the . My reader (Sony PRS-600) has a serious issue - # with that: it treats it as content and displays it as is. Setting this property to empty solves this for me. - template_css = '' - INDEX = u'http://foksuk.nl' - - # This cover is not as nice as it could be, needs some work - #cover_url = 'http://foksuk.nl/content/wysiwyg/simpleimages/image350.gif' - - keep_only_tags = [dict(name='div', attrs={'class' : 'cartoon'})] - - def parse_index(self) : - # A list with daynames as they _can_ appear in the index - dayNames = ['maandag', 'dinsdag', 'woensdag', 'donderdag', 'vrijdag', 'zaterdag & zondag'] - soup = self.index_to_soup(self.INDEX) - - # Find the links for the various cartoons for this week and loop through them - index = soup.find('div', attrs={'class' : 'selectcartoon'}) - links = index.findAll('a') - maxIndex = len(links) - 1 - articles = [] - for i in range(len(links)) : - # The first link does not interest us, as it points to no cartoon. A begin_at parameter in the range() function would be nice. - if i == 0 : - continue - - # There can be more than one cartoon for a given day (currently either one or two). If there's only one, there is just a link with the dayname. - # If there are two, there are three links in sequence: dayname 1 2. In that case we're interested in the last two. - if links[i].renderContents() in dayNames : - # If the link is not in daynames, we processed it already, but if it is, let's see if the next one has '1' as content - if (i + 1 <= maxIndex) and (links[i + 1].renderContents() == '1') : - # Got you! Add it to the list - article = {'title' : links[i].renderContents() + ' 1', 'date' : u'', 'url' : self.INDEX + links[i + 1]['href'], 'description' : ''} - articles.append(article) - # If there is a '1', there should be a '2' as well, but better save than sorry - if (i + 2 <= maxIndex) and (links[i + 2].renderContents() == '2') : - # Got you! Add it to the list - article = {'title' : links[i].renderContents() + ' 2', 'date' : u'', 'url' : self.INDEX + links[i + 2]['href'], 'description' : ''} - articles.append(article) - else : - # There is only one cartoon for this day. Add it to the list. - article = {'title' : links[i].renderContents(), 'date' : u'', 'url' : self.INDEX + links[i]['href'], 'description' : ''} - articles.append(article) - # Might as well use the weeknumber as title - week = index.find('span', attrs={'class' : 'week'}).renderContents() - - return [[week, articles]] - - def preprocess_html(self, soup) : - # This method is called for every page, be it cartoon or TOC. We need to process each in their own way - cartoon = soup.find('div', attrs={'class' : 'cartoon'}) - if cartoon : - # It is a cartoon. Extract the title. - title = '' - img = soup.find('img', attrs = {'alt' : True}) - if img : - title = img['alt'] - - # Using the 'extra_css' displays it in the and not in the . See comment at the top of this class. Setting the style this way solves that. - tag = Tag(soup, 'div', [('style', 'text-align: center; margin-bottom: 8px')]) - tag.insert(0, title) - cartoon.insert(0, tag) - - # I have not quite worked out why, but we have to throw out this part of the page. It contains the very same index we processed earlier, - # and Calibre does not like that too much. As far as I can tell it goes into recursion and the result is an empty eBook. - select = cartoon.find('div', attrs={'class' : 'selectcartoon'}) - if select : - select.extract() - - return cartoon - else : - # It is a TOC. Just return the whole lot. - return soup - - +#!/usr/bin/python +from calibre.web.feeds.news import BasicNewsRecipe +from calibre.ebooks.BeautifulSoup import Tag + + +class FokkeEnSukkeRecipe(BasicNewsRecipe) : + __license__ = 'GPL v3' + __author__ = 'kwetal' + language = 'nl' + description = u'Popular Dutch daily cartoon Fokke en Sukke' + + title = u'Fokke en Sukke' + no_stylesheets = True + # For reasons unknown to me the extra css is, on the cartoon pages, inserted in the and not in the . My reader (Sony PRS-600) has a serious issue + # with that: it treats it as content and displays it as is. Setting this property to empty solves this for me. + template_css = '' + INDEX = u'http://foksuk.nl' + + # This cover is not as nice as it could be, needs some work + #cover_url = 'http://foksuk.nl/content/wysiwyg/simpleimages/image350.gif' + + keep_only_tags = [dict(name='div', attrs={'class' : 'cartoon'})] + + def parse_index(self) : + # A list with daynames as they _can_ appear in the index + dayNames = ['maandag', 'dinsdag', 'woensdag', 'donderdag', 'vrijdag', 'zaterdag & zondag'] + soup = self.index_to_soup(self.INDEX) + + # Find the links for the various cartoons for this week and loop through them + index = soup.find('div', attrs={'class' : 'selectcartoon'}) + links = index.findAll('a') + maxIndex = len(links) - 1 + articles = [] + for i in range(len(links)) : + # The first link does not interest us, as it points to no cartoon. A begin_at parameter in the range() function would be nice. + if i == 0 : + continue + + # There can be more than one cartoon for a given day (currently either one or two). If there's only one, there is just a link with the dayname. + # If there are two, there are three links in sequence: dayname 1 2. In that case we're interested in the last two. + if links[i].renderContents() in dayNames : + # If the link is not in daynames, we processed it already, but if it is, let's see if the next one has '1' as content + if (i + 1 <= maxIndex) and (links[i + 1].renderContents() == '1') : + # Got you! Add it to the list + article = {'title' : links[i].renderContents() + ' 1', 'date' : u'', 'url' : self.INDEX + links[i + 1]['href'], 'description' : ''} + articles.append(article) + # If there is a '1', there should be a '2' as well, but better save than sorry + if (i + 2 <= maxIndex) and (links[i + 2].renderContents() == '2') : + # Got you! Add it to the list + article = {'title' : links[i].renderContents() + ' 2', 'date' : u'', 'url' : self.INDEX + links[i + 2]['href'], 'description' : ''} + articles.append(article) + else : + # There is only one cartoon for this day. Add it to the list. + article = {'title' : links[i].renderContents(), 'date' : u'', 'url' : self.INDEX + links[i]['href'], 'description' : ''} + articles.append(article) + # Might as well use the weeknumber as title + week = index.find('span', attrs={'class' : 'week'}).renderContents() + + return [[week, articles]] + + def preprocess_html(self, soup) : + # This method is called for every page, be it cartoon or TOC. We need to process each in their own way + cartoon = soup.find('div', attrs={'class' : 'cartoon'}) + if cartoon : + # It is a cartoon. Extract the title. + title = '' + img = soup.find('img', attrs = {'alt' : True}) + if img : + title = img['alt'] + + # Using the 'extra_css' displays it in the and not in the . See comment at the top of this class. Setting the style this way solves that. + tag = Tag(soup, 'div', [('style', 'text-align: center; margin-bottom: 8px')]) + tag.insert(0, title) + cartoon.insert(0, tag) + + # I have not quite worked out why, but we have to throw out this part of the page. It contains the very same index we processed earlier, + # and Calibre does not like that too much. As far as I can tell it goes into recursion and the result is an empty eBook. + select = cartoon.find('div', attrs={'class' : 'selectcartoon'}) + if select : + select.extract() + + return cartoon + else : + # It is a TOC. Just return the whole lot. + return soup + + diff --git a/src/calibre/ebooks/conversion/plumber.py b/src/calibre/ebooks/conversion/plumber.py index 262f64a9cc..30cc42480c 100644 --- a/src/calibre/ebooks/conversion/plumber.py +++ b/src/calibre/ebooks/conversion/plumber.py @@ -309,11 +309,13 @@ OptionRecommendation(name='remove_paragraph_spacing', 'paragraphs of 1.5em. Spacing removal will not work ' 'if the source file does not use paragraphs (

or

tags).') ), - + OptionRecommendation(name='remove_paragraph_spacing_indent_size', recommended_value=1.5, level=OptionRecommendation.LOW, - help=_('Width of the indent used with Remove spacing between paragraphs option') - ), + help=_('When calibre removes inter paragraph spacing, it automatically ' + 'sets a paragraph indent, to ensure that paragraphs can be easily ' + 'distinguished. This option controls the width of that indent.') + ), OptionRecommendation(name='prefer_metadata_cover', recommended_value=False, level=OptionRecommendation.LOW, diff --git a/src/calibre/ebooks/pml/pmlconverter.py b/src/calibre/ebooks/pml/pmlconverter.py index 05cf488617..cb8ae15298 100644 --- a/src/calibre/ebooks/pml/pmlconverter.py +++ b/src/calibre/ebooks/pml/pmlconverter.py @@ -256,7 +256,7 @@ class PML_HTMLizer(object): if code in self.SPAN_STATES: del spans[spans.index(code)] for c in divs+spans: - if state[c][0]: + if self.state[c][0]: if c in self.STATES_VALUE_REQ: text += self.STATES_TAGS[self.CODE_STATES[c]][0] % self.state[c][1] else: @@ -265,7 +265,7 @@ class PML_HTMLizer(object): if code in self.STATES_VALUE_REQ: val = self.code_value(stream) text = self.STATES_TAGS[code][0] % val - state[code][1] = val + self.state[code][1] = val else: text = self.STATES_TAGS[code][0] diff --git a/src/calibre/manual/conversion.rst b/src/calibre/manual/conversion.rst index 64d8b7b62b..a841b9cf04 100644 --- a/src/calibre/manual/conversion.rst +++ b/src/calibre/manual/conversion.rst @@ -163,7 +163,7 @@ Paragraph spacing Normally, paragraphs in XHTML are rendered with a blank line between them and no leading text indent. |app| has a couple of options to control this. :guilabel:`Remove spacing between paragraphs` forcefully ensure that all paragraphs have no inter paragraph spacing. It also sets the text -indent to 1.5em (can be changed) to mark that start of every paragraph. +indent to 1.5em (can be changed) to mark the start of every paragraph. :guilabel:`Insert blank line` does the opposite, guaranteeing that there is exactly one blank line between each pair of paragraphs. Both these options are very comprehensive, removing spacing, or inserting it for *all* paragraphs