Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 02:34:06 -04:00
Code Issues Packages Projects Releases Wiki Activity

Pass trough guide entries used by MOBI output

Browse Source
This commit is contained in:
Kovid Goyal 2009-07-07 15:51:00 -06:00
parent 8e9590373f
commit 6697b9bbb3
2 changed files with 17 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/calibre/ebooks/oeb/transforms/guide.py
View File

@ -34,7 +34,8 @@ class Clean(object):
for x in list(self.oeb.guide): for x in list(self.oeb.guide):
href = urldefrag(self.oeb.guide[x].href)[0] href = urldefrag(self.oeb.guide[x].href)[0]
if x.lower() not in ('cover', 'titlepage', 'masthead'): if x.lower() not in ('cover', 'titlepage', 'masthead', 'toc',
'title-page', 'copyright-page'):
self.oeb.guide.remove(x) self.oeb.guide.remove(x)

30
src/calibre/web/feeds/recipes/recipe_nytimes_sub.py
View File

@ -11,7 +11,7 @@ from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup from calibre.ebooks.BeautifulSoup import BeautifulSoup
class NYTimes(BasicNewsRecipe): class NYTimes(BasicNewsRecipe):
title = 'The New York Times (subscription)' title = 'The New York Times (subscription)'
__author__ = 'Kovid Goyal' __author__ = 'Kovid Goyal'
language = _('English') language = _('English')
@ -20,13 +20,13 @@ class NYTimes(BasicNewsRecipe):
needs_subscription = True needs_subscription = True
remove_tags_before = dict(id='article') remove_tags_before = dict(id='article')
remove_tags_after = dict(id='article') remove_tags_after = dict(id='article')
remove_tags = [dict(attrs={'class':['articleTools', 'post-tools', 'side_tool', 'nextArticleLink clearfix']}), remove_tags = [dict(attrs={'class':['articleTools', 'post-tools', 'side_tool', 'nextArticleLink clearfix']}),
dict(id=['footer', 'toolsRight', 'articleInline', 'navigation', 'archive', 'side_search', 'blog_sidebar', 'side_tool', 'side_index']), dict(id=['footer', 'toolsRight', 'articleInline', 'navigation', 'archive', 'side_search', 'blog_sidebar', 'side_tool', 'side_index']),
dict(name=['script', 'noscript', 'style'])] dict(name=['script', 'noscript', 'style'])]
encoding = 'cp1252' encoding = 'cp1252'
no_stylesheets = True no_stylesheets = True
extra_css = 'h1 {font: sans-serif large;}\n.byline {font:monospace;}' extra_css = 'h1 {font: sans-serif large;}\n.byline {font:monospace;}'
def get_browser(self): def get_browser(self):
br = BasicNewsRecipe.get_browser() br = BasicNewsRecipe.get_browser()
if self.username is not None and self.password is not None: if self.username is not None and self.password is not None:
@ -36,24 +36,24 @@ class NYTimes(BasicNewsRecipe):
br['PASSWORD'] = self.password br['PASSWORD'] = self.password
br.submit() br.submit()
return br return br
def parse_index(self): def parse_index(self):
soup = self.index_to_soup('http://www.nytimes.com/pages/todayspaper/index.html') soup = self.index_to_soup('http://www.nytimes.com/pages/todayspaper/index.html')
def feed_title(div): def feed_title(div):
return ''.join(div.findAll(text=True, recursive=False)).strip() return ''.join(div.findAll(text=True, recursive=False)).strip()
articles = {} articles = {}
key = None key = None
ans = [] ans = []
for div in soup.findAll(True, for div in soup.findAll(True,
attrs={'class':['section-headline', 'story', 'story headline']}): attrs={'class':['section-headline', 'story', 'story headline']}):
if div['class'] == 'section-headline': if div['class'] == 'section-headline':
key = string.capwords(feed_title(div)) key = string.capwords(feed_title(div))
articles[key] = [] articles[key] = []
ans.append(key) ans.append(key)
elif div['class'] in ['story', 'story headline']: elif div['class'] in ['story', 'story headline']:
a = div.find('a', href=True) a = div.find('a', href=True)
if not a: if not a:
@ -66,21 +66,21 @@ class NYTimes(BasicNewsRecipe):
summary = div.find(True, attrs={'class':'summary'}) summary = div.find(True, attrs={'class':'summary'})
if summary: if summary:
description = self.tag_to_string(summary, use_alt=False) description = self.tag_to_string(summary, use_alt=False)
feed = key if key is not None else 'Uncategorized' feed = key if key is not None else 'Uncategorized'
if not articles.has_key(feed): if not articles.has_key(feed):
articles[feed] = [] articles[feed] = []
if not 'podcasts' in url: if not 'podcasts' in url:
articles[feed].append( articles[feed].append(
dict(title=title, url=url, date=pubdate, dict(title=title, url=url, date=pubdate,
description=description, description=description,
content='')) content=''))
ans = self.sort_index_by(ans, {'The Front Page':-1, ans = self.sort_index_by(ans, {'The Front Page':-1,
'Dining In, Dining Out':1, 'Dining In, Dining Out':1,
'Obituaries':2}) 'Obituaries':2})
ans = [(key, articles[key]) for key in ans if articles.has_key(key)] ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
return ans return ans
def preprocess_html(self, soup): def preprocess_html(self, soup):
refresh = soup.find('meta', {'http-equiv':'refresh'}) refresh = soup.find('meta', {'http-equiv':'refresh'})
if refresh is None: if refresh is None: