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 Economist recipe for new website layout

Browse Source
This commit is contained in:
Kovid Goyal 2010-06-10 23:09:10 -06:00
parent efe64efe25
commit 0ed7568ae1
2 changed files with 13 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
resources/recipes/economist.recipe
View File

@ -24,9 +24,10 @@ class Economist(BasicNewsRecipe):
oldest_article = 7.0 oldest_article = 7.0
cover_url = 'http://www.economist.com/images/covers/currentcoverus_large.jpg' cover_url = 'http://www.economist.com/images/covers/currentcoverus_large.jpg'
remove_tags = [dict(name=['script', 'noscript', 'title', 'iframe', 'cf_floatingcontent']), remove_tags = [dict(name=['script', 'noscript', 'title', 'iframe', 'cf_floatingcontent']),
dict(attrs={'class':['dblClkTrk']})] dict(attrs={'class':['dblClkTrk', 'ec-article-info']})]
remove_tags_before = dict(name=lambda tag: tag.name=='title' and tag.parent.name=='body') keep_only_tags = [dict(id='ec-article-body')]
needs_subscription = True needs_subscription = True
no_stylesheets = True
preprocess_regexps = [(re.compile('</html>.*', re.DOTALL), preprocess_regexps = [(re.compile('</html>.*', re.DOTALL),
lambda x:'</html>')] lambda x:'</html>')]
@ -87,7 +88,7 @@ class Economist(BasicNewsRecipe):
continue continue
a = tag.find('a', href=True) a = tag.find('a', href=True)
if a is not None: if a is not None:
url=a['href'].replace('displaystory', 'PrinterFriendly').strip() url=a['href'].split('?')[0]+'/print'
if url.startswith('Printer'): if url.startswith('Printer'):
url = '/'+url url = '/'+url
if url.startswith('/'): if url.startswith('/'):

16
resources/recipes/economist_free.recipe
View File

@ -17,8 +17,9 @@ class Economist(BasicNewsRecipe):
oldest_article = 7.0 oldest_article = 7.0
cover_url = 'http://www.economist.com/images/covers/currentcoverus_large.jpg' cover_url = 'http://www.economist.com/images/covers/currentcoverus_large.jpg'
remove_tags = [dict(name=['script', 'noscript', 'title', 'iframe', 'cf_floatingcontent']), remove_tags = [dict(name=['script', 'noscript', 'title', 'iframe', 'cf_floatingcontent']),
dict(attrs={'class':['dblClkTrk']})] dict(attrs={'class':['dblClkTrk', 'ec-article-info']})]
remove_tags_before = dict(name=lambda tag: tag.name=='title' and tag.parent.name=='body') keep_only_tags = [dict(id='ec-article-body')]
no_stylesheets = True
preprocess_regexps = [(re.compile('</html>.*', re.DOTALL), preprocess_regexps = [(re.compile('</html>.*', re.DOTALL),
lambda x:'</html>')] lambda x:'</html>')]
@ -88,19 +89,20 @@ class Economist(BasicNewsRecipe):
br = browser() br = browser()
ret = br.open(url) ret = br.open(url)
raw = ret.read() raw = ret.read()
url = br.geturl().replace('displaystory', 'PrinterFriendly').strip() url = br.geturl().split('?')[0]+'/print'
root = html.fromstring(raw) root = html.fromstring(raw)
matches = root.xpath('//*[@class = "article-section"]') matches = root.xpath('//*[@class = "ec-article-info"]')
feedtitle = 'Miscellaneous' feedtitle = 'Miscellaneous'
if matches: if matches:
feedtitle = string.capwords(html.tostring(matches[0], method='text', feedtitle = string.capwords(html.tostring(matches[-1], method='text',
encoding=unicode)) encoding=unicode).split('|')[-1].strip())
return (i, feedtitle, url, title, description, author, published) return (i, feedtitle, url, title, description, author, published)
def eco_article_found(self, req, result): def eco_article_found(self, req, result):
from calibre.web.feeds import Article from calibre.web.feeds import Article
i, feedtitle, link, title, description, author, published = result i, feedtitle, link, title, description, author, published = result
self.log('Found print version for article:', title) self.log('Found print version for article:', title, 'in', feedtitle,
'at', link)
a = Article(i, title, link, author, description, published, '') a = Article(i, title, link, author, description, published, '')