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 multipage articles in The National Post

Browse Source
This commit is contained in:
Kovid Goyal 2010-01-17 19:40:31 -07:00
parent 5c243cda3b
commit c6692c859e
1 changed files with 19 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
resources/recipes/national_post.recipe
View File

@ -70,11 +70,28 @@ 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={'class':'triline'})
#td = heading.findParent(name='td') page2_link = soup.find('p','pagenav')
#td.extract() if page2_link:
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