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

Updated Ars Technica

Browse Source
This commit is contained in:
Kovid Goyal 2011-01-17 20:43:27 -07:00
parent 9d1de8b46d
commit 39bffe0983
1 changed files with 40 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

51
resources/recipes/ars_technica.recipe
View File

@ -1,6 +1,5 @@
__license__ = 'GPL v3'
__copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2008-2011, Darko Miletic <darko.miletic at gmail.com>'
'''
arstechnica.com
'''
@ -9,19 +8,26 @@ import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
class ArsTechnica2(BasicNewsRecipe):
class ArsTechnica(BasicNewsRecipe):
title = u'Ars Technica'
language = 'en'
__author__ = 'Darko Miletic and Sujata Raman'
__author__ = 'Darko Miletic, Sujata Raman, Alexis Rohou'
description = 'The art of technology'
publisher = 'Ars Technica'
category = 'news, IT, technology'
oldest_article = 2
oldest_article = 5
max_articles_per_feed = 100
no_stylesheets = True
encoding = 'utf-8'
use_embedded_content = False
extra_css = ' body {font-family: Arial,Helvetica,sans-serif} .title{text-align: left} .byline{font-weight: bold; line-height: 1em; font-size: 0.625em; text-decoration: none} '
extra_css = '''
body {font-family: Arial,Helvetica,sans-serif}
.title{text-align: left}
.byline{font-weight: bold; line-height: 1em; font-size: 0.625em; text-decoration: none}
.news-item-figure-caption-text{font-size:small; font-style:italic}
.news-item-figure-caption-byline{font-size:small; font-style:italic; font-weight:bold}
'''
ignoreEtcArticles = True # Etc feed items can be ignored, as they're not real stories
conversion_options = {
'comments' : description
@ -31,10 +37,10 @@ class ArsTechnica2(BasicNewsRecipe):
}
preprocess_regexps = [
(re.compile(r'<div class="news-item-figure', re.DOTALL|re.IGNORECASE),lambda match: '<div class="news-item-figure"')
,(re.compile(r'</title>.*?</head>', re.DOTALL|re.IGNORECASE),lambda match: '</title></head>')
]
#preprocess_regexps = [
# (re.compile(r'<div class="news-item-figure', re.DOTALL|re.IGNORECASE),lambda match: '<div class="news-item-figure"')
# ,(re.compile(r'</title>.*?</head>', re.DOTALL|re.IGNORECASE),lambda match: '</title></head>')
# ]
keep_only_tags = [dict(name='div', attrs={'id':['story','etc-story']})]
@ -42,7 +48,7 @@ class ArsTechnica2(BasicNewsRecipe):
dict(name=['object','link','embed'])
,dict(name='div', attrs={'class':'read-more-link'})
]
remove_attributes=['width','height']
#remove_attributes=['width','height']
feeds = [
(u'Infinite Loop (Apple content)' , u'http://feeds.arstechnica.com/arstechnica/apple/' )
@ -56,6 +62,7 @@ class ArsTechnica2(BasicNewsRecipe):
,(u'Law & Disorder (Tech policy content)' , u'http://feeds.arstechnica.com/arstechnica/tech-policy/')
]
# This deals with multi-page stories
def append_page(self, soup, appendtag, position):
pager = soup.find('div',attrs={'class':'pager'})
if pager:
@ -81,6 +88,7 @@ class ArsTechnica2(BasicNewsRecipe):
def preprocess_html(self, soup):
# Adds line breaks near the byline (not sure why this is needed)
ftag = soup.find('div', attrs={'class':'byline'})
if ftag:
brtag = Tag(soup,'br')
@ -88,12 +96,33 @@ class ArsTechnica2(BasicNewsRecipe):
ftag.insert(4,brtag)
ftag.insert(5,brtag2)
# Remove style items
for item in soup.findAll(style=True):
del item['style']
# Remove id
for item in soup.findAll(id=True):
del item['id']
# For some reason, links to authors don't have the domainname
a_author = soup.find('a',{'href':re.compile("^/author")})
if a_author:
a_author['href'] = 'http://arstechnica.com'+a_author['href']
# within div class news-item-figure, we need to grab images
# Deal with multi-page stories
self.append_page(soup, soup.body, 3)
return soup
def get_article_url(self, article):
# If the article title starts with Etc:, don't return it
if self.ignoreEtcArticles:
article_title = article.get('title',None)
if re.match('Etc: ',article_title) is not None:
return None
# The actual article is in a guid tag
return article.get('guid', None).rpartition('?')[0]