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

Fix National Post

Browse Source
This commit is contained in:
Kovid Goyal 2012-05-03 16:17:27 +05:30
parent df1195e9ff
commit 61aa60ab07
1 changed files with 5 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
recipes/national_post.recipe
View File

@ -1,5 +1,4 @@
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
class NYTimes(BasicNewsRecipe): class NYTimes(BasicNewsRecipe):
@ -11,22 +10,8 @@ class NYTimes(BasicNewsRecipe):
needs_subscription = False needs_subscription = False
no_stylesheets = True no_stylesheets = True
#remove_tags_before = dict(name='h1', attrs={'class':'heading'}) auto_cleanup = True
remove_tags_after = dict(name='div', attrs={'class':'npStoryTools npWidth1-6 npRight npTxtStrong'}) auto_cleanup_keep = '//*[@class="npStoryPhoto npTxtPlain"]'
remove_tags = [
dict(name='iframe'),
dict(name='div', attrs={'class':['story-tools', 'npStoryTools npWidth1-6 npRight npTxtStrong']}),
#dict(name='div', attrs={'id':['qrformdiv', 'inSection', 'alpha-inner']}),
#dict(name='form', attrs={'onsubmit':''}),
dict(name='ul', attrs={'class':'npTxtAlt npGroup npTxtCentre npStoryShare npTxtStrong npTxtDim'}),
]
# def preprocess_html(self, soup):
# table = soup.find('table')
# if table is not None:
# table.extract()
# return soup
#TO GET ARTICLE TOC #TO GET ARTICLE TOC
@ -53,14 +38,14 @@ class NYTimes(BasicNewsRecipe):
if current_section is not None and x.name == 'h5': if current_section is not None and x.name == 'h5':
# Article found # Article found
title = self.tag_to_string(x) title = self.tag_to_string(x)
a = x.find('a', href=lambda x: x and 'story' in x) a = x.find('a', href=True)
if a is None: if a is None:
continue continue
url = a.get('href', False) url = a.get('href', False)
if not url or not title: if not url or not title:
continue continue
#if url.startswith('story'): #if url.startswith('story'):
url = 'http://www.nationalpost.com/todays-paper/'+url #url = 'http://www.nationalpost.com/todays-paper/'+url
self.log('\t\tFound article:', title) self.log('\t\tFound article:', title)
self.log('\t\t\t', url) self.log('\t\t\t', url)
current_articles.append({'title': title, 'url':url, current_articles.append({'title': title, 'url':url,
@ -70,11 +55,4 @@ class NYTimes(BasicNewsRecipe):
feeds.append((current_section, current_articles)) feeds.append((current_section, current_articles))
return feeds return feeds
def preprocess_html(self, soup):
story = soup.find(name='div', attrs={'id':'npContentMain'})
##td = heading.findParent(name='td')
##td.extract()
soup = BeautifulSoup('<html><head><title>t</title></head><body></body></html>')
body = soup.find(name='body')
body.insert(0, story)
return soup