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

...

Browse Source
This commit is contained in:
Kovid Goyal 2011-06-03 09:57:14 -06:00
commit 3048729e8c
4 changed files with 23 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
recipes/guardian.recipe
View File

@ -28,7 +28,7 @@ class Guardian(BasicNewsRecipe):
# List of section titles to ignore # List of section titles to ignore
# For example: ['Sport'] # For example: ['Sport']
ignore_sections = [] ignore_sections = []
timefmt = ' [%a, %d %b %Y]' timefmt = ' [%a, %d %b %Y]'
keep_only_tags = [ keep_only_tags = [
dict(name='div', attrs={'id':["content","article_header","main-article-info",]}), dict(name='div', attrs={'id':["content","article_header","main-article-info",]}),
@ -87,8 +87,14 @@ class Guardian(BasicNewsRecipe):
idx = soup.find('div', id='book-index') idx = soup.find('div', id='book-index')
for s in idx.findAll('strong', attrs={'class':'book'}): for s in idx.findAll('strong', attrs={'class':'book'}):
a = s.find('a', href=True) a = s.find('a', href=True)
yield (self.tag_to_string(a), a['href']) section_title = self.tag_to_string(a)
if not section_title in self.ignore_sections:
prefix = ''
if section_title != 'Main section':
prefix = section_title + ': '
for subsection in s.parent.findAll('a', attrs={'class':'book-section'}):
yield (prefix + self.tag_to_string(subsection), subsection['href'])
def find_articles(self, url): def find_articles(self, url):
soup = self.index_to_soup(url) soup = self.index_to_soup(url)
div = soup.find('div', attrs={'class':'book-index'}) div = soup.find('div', attrs={'class':'book-index'})
@ -109,15 +115,12 @@ class Guardian(BasicNewsRecipe):
'title': title, 'url':url, 'description':desc, 'title': title, 'url':url, 'description':desc,
'date' : strftime('%a, %d %b'), 'date' : strftime('%a, %d %b'),
} }
def parse_index(self): def parse_index(self):
try: try:
feeds = [] feeds = []
for title, href in self.find_sections(): for title, href in self.find_sections():
if not title in self.ignore_sections: feeds.append((title, list(self.find_articles(href))))
feeds.append((title, list(self.find_articles(href))))
return feeds return feeds
except: except:
raise NotImplementedError raise NotImplementedError

1
recipes/telegraph_uk.recipe
View File

@ -49,6 +49,7 @@ class TelegraphUK(BasicNewsRecipe):
(u'UK News' , u'http://www.telegraph.co.uk/news/uknews/rss' ) (u'UK News' , u'http://www.telegraph.co.uk/news/uknews/rss' )
,(u'World News' , u'http://www.telegraph.co.uk/news/worldnews/rss' ) ,(u'World News' , u'http://www.telegraph.co.uk/news/worldnews/rss' )
,(u'Politics' , u'http://www.telegraph.co.uk/news/newstopics/politics/rss' ) ,(u'Politics' , u'http://www.telegraph.co.uk/news/newstopics/politics/rss' )
,(u'Finance' , u'http://www.telegraph.co.uk/finance/rss' )
,(u'Technology News', u'http://www.telegraph.co.uk/scienceandtechnology/technology/technologynews/rss' ) ,(u'Technology News', u'http://www.telegraph.co.uk/scienceandtechnology/technology/technologynews/rss' )
,(u'UK News' , u'http://www.telegraph.co.uk/scienceandtechnology/technology/technologyreviews/rss') ,(u'UK News' , u'http://www.telegraph.co.uk/scienceandtechnology/technology/technologyreviews/rss')
,(u'Science News' , u'http://www.telegraph.co.uk/scienceandtechnology/science/sciencenews/rss' ) ,(u'Science News' , u'http://www.telegraph.co.uk/scienceandtechnology/science/sciencenews/rss' )

4
recipes/time_magazine.recipe
View File

@ -10,8 +10,8 @@ import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Time(BasicNewsRecipe): class Time(BasicNewsRecipe):
recipe_disabled = ('This recipe has been disabled as TIME no longer' #recipe_disabled = ('This recipe has been disabled as TIME no longer'
' publish complete articles on the web.') # ' publish complete articles on the web.')
title = u'Time' title = u'Time'
__author__ = 'Kovid Goyal and Sujata Raman' __author__ = 'Kovid Goyal and Sujata Raman'
description = 'Weekly magazine' description = 'Weekly magazine'

18
recipes/zaobao.recipe
View File

@ -82,7 +82,7 @@ class ZAOBAO(BasicNewsRecipe):
return soup return soup
def parse_feeds(self): def parse_feeds(self):
self.log_debug(_('ZAOBAO overrided parse_feeds()')) self.log(_('ZAOBAO overrided parse_feeds()'))
parsed_feeds = BasicNewsRecipe.parse_feeds(self) parsed_feeds = BasicNewsRecipe.parse_feeds(self)
for id, obj in enumerate(self.INDEXES): for id, obj in enumerate(self.INDEXES):
@ -99,7 +99,7 @@ class ZAOBAO(BasicNewsRecipe):
a_title = self.tag_to_string(a) a_title = self.tag_to_string(a)
date = '' date = ''
description = '' description = ''
self.log_debug(_('adding %s at %s')%(a_title,a_url)) self.log(_('adding %s at %s')%(a_title,a_url))
articles.append({ articles.append({
'title':a_title, 'title':a_title,
'date':date, 'date':date,
@ -110,23 +110,23 @@ class ZAOBAO(BasicNewsRecipe):
pfeeds = feeds_from_index([(title, articles)], oldest_article=self.oldest_article, pfeeds = feeds_from_index([(title, articles)], oldest_article=self.oldest_article,
max_articles_per_feed=self.max_articles_per_feed) max_articles_per_feed=self.max_articles_per_feed)
self.log_debug(_('adding %s to feed')%(title)) self.log(_('adding %s to feed')%(title))
for feed in pfeeds: for feed in pfeeds:
self.log_debug(_('adding feed: %s')%(feed.title)) self.log(_('adding feed: %s')%(feed.title))
feed.description = self.DESC_SENSE feed.description = self.DESC_SENSE
parsed_feeds.append(feed) parsed_feeds.append(feed)
for a, article in enumerate(feed): for a, article in enumerate(feed):
self.log_debug(_('added article %s from %s')%(article.title, article.url)) self.log(_('added article %s from %s')%(article.title, article.url))
self.log_debug(_('added feed %s')%(feed.title)) self.log(_('added feed %s')%(feed.title))
for i, feed in enumerate(parsed_feeds): for i, feed in enumerate(parsed_feeds):
# workaorund a strange problem: Somethimes the xml encoding is not apllied correctly by parse() # workaorund a strange problem: Somethimes the xml encoding is not apllied correctly by parse()
weired_encoding_detected = False weired_encoding_detected = False
if not isinstance(feed.description, unicode) and self.encoding and feed.description: if not isinstance(feed.description, unicode) and self.encoding and feed.description:
self.log_debug(_('Feed %s is not encoded correctly, manually replace it')%(feed.title)) self.log(_('Feed %s is not encoded correctly, manually replace it')%(feed.title))
feed.description = feed.description.decode(self.encoding, 'replace') feed.description = feed.description.decode(self.encoding, 'replace')
elif feed.description.find(self.DESC_SENSE) == -1 and self.encoding and feed.description: elif feed.description.find(self.DESC_SENSE) == -1 and self.encoding and feed.description:
self.log_debug(_('Feed %s is weired encoded, manually redo all')%(feed.title)) self.log(_('Feed %s is weired encoded, manually redo all')%(feed.title))
feed.description = feed.description.encode('cp1252', 'replace').decode(self.encoding, 'replace') feed.description = feed.description.encode('cp1252', 'replace').decode(self.encoding, 'replace')
weired_encoding_detected = True weired_encoding_detected = True
@ -148,7 +148,7 @@ class ZAOBAO(BasicNewsRecipe):
article.text_summary = article.text_summary.encode('cp1252', 'replace').decode(self.encoding, 'replace') article.text_summary = article.text_summary.encode('cp1252', 'replace').decode(self.encoding, 'replace')
if article.title == "Untitled article": if article.title == "Untitled article":
self.log_debug(_('Removing empty article %s from %s')%(article.title, article.url)) self.log(_('Removing empty article %s from %s')%(article.title, article.url))
# remove the article # remove the article
feed.articles[a:a+1] = [] feed.articles[a:a+1] = []
return parsed_feeds return parsed_feeds