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 #5951 (unable to retrieve news item)

Browse Source
This commit is contained in:
Kovid Goyal 2010-06-24 11:56:54 -06:00
parent da8a09694d
commit bb5ab06f3b
1 changed files with 11 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
resources/recipes/national_post.recipe
View File

@ -7,18 +7,18 @@ class NYTimes(BasicNewsRecipe):
__author__ = 'Krittika Goyal' __author__ = 'Krittika Goyal'
description = 'Canadian national newspaper' description = 'Canadian national newspaper'
timefmt = ' [%d %b, %Y]' timefmt = ' [%d %b, %Y]'
needs_subscription = False
language = 'en_CA' language = 'en_CA'
needs_subscription = False
no_stylesheets = True no_stylesheets = True
#remove_tags_before = dict(name='h1', attrs={'class':'heading'}) #remove_tags_before = dict(name='h1', attrs={'class':'heading'})
#remove_tags_after = dict(name='td', attrs={'class':'newptool1'}) remove_tags_after = dict(name='div', attrs={'class':'npStoryTools npWidth1-6 npRight npTxtStrong'})
remove_tags = [ remove_tags = [
dict(name='iframe'), dict(name='iframe'),
dict(name='div', attrs={'class':'story-tools'}), dict(name='div', attrs={'class':['story-tools', 'npStoryTools npWidth1-6 npRight npTxtStrong']}),
#dict(name='div', attrs={'id':['qrformdiv', 'inSection', 'alpha-inner']}), #dict(name='div', attrs={'id':['qrformdiv', 'inSection', 'alpha-inner']}),
#dict(name='form', attrs={'onsubmit':''}), #dict(name='form', attrs={'onsubmit':''}),
#dict(name='table', attrs={'cellspacing':'0'}), dict(name='ul', attrs={'class':'npTxtAlt npGroup npTxtCentre npStoryShare npTxtStrong npTxtDim'}),
] ]
# def preprocess_html(self, soup): # def preprocess_html(self, soup):
@ -37,7 +37,7 @@ class NYTimes(BasicNewsRecipe):
def parse_index(self): def parse_index(self):
soup = self.nejm_get_index() soup = self.nejm_get_index()
div = soup.find(id='LegoText4') div = soup.find(id='npContentMain')
current_section = None current_section = None
current_articles = [] current_articles = []
@ -50,7 +50,7 @@ class NYTimes(BasicNewsRecipe):
current_section = self.tag_to_string(x) current_section = self.tag_to_string(x)
current_articles = [] current_articles = []
self.log('\tFound section:', current_section) self.log('\tFound section:', current_section)
if current_section is not None and x.name == 'h3': 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=lambda x: x and 'story' in x)
@ -59,7 +59,7 @@ class NYTimes(BasicNewsRecipe):
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)
@ -70,28 +70,11 @@ class NYTimes(BasicNewsRecipe):
feeds.append((current_section, current_articles)) feeds.append((current_section, current_articles))
return feeds return feeds
def preprocess_html(self, soup): def preprocess_html(self, soup):
story = soup.find(name='div', attrs={'class':'triline'}) story = soup.find(name='div', attrs={'id':'npContentMain'})
page2_link = soup.find('p','pagenav') ##td = heading.findParent(name='td')
if page2_link: ##td.extract()
atag = page2_link.find('a',href=True)
if atag:
page2_url = atag['href']
if page2_url.startswith('story'):
page2_url = 'http://www.nationalpost.com/todays-paper/'+page2_url
elif page2_url.startswith( '/todays-paper/story.html'):
page2_url = 'http://www.nationalpost.com/'+page2_url
page2_soup = self.index_to_soup(page2_url)
if page2_soup:
page2_content = page2_soup.find('div','story-content')
if page2_content:
full_story = BeautifulSoup('<div></div>')
full_story.insert(0,story)
full_story.insert(1,page2_content)
story = full_story
soup = BeautifulSoup('<html><head><title>t</title></head><body></body></html>') soup = BeautifulSoup('<html><head><title>t</title></head><body></body></html>')
body = soup.find(name='body') body = soup.find(name='body')
body.insert(0, story) body.insert(0, story)
return soup return soup