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 Newsweek recipe

Browse Source
This commit is contained in:
Kovid Goyal 2009-09-04 09:41:37 -06:00
parent 0a840e9e2b
commit f457341a36
2 changed files with 20 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/calibre/web/feeds/recipes/recipe_economist.py
View File

@ -62,7 +62,9 @@ class Economist(BasicNewsRecipe):
a = tag.find('a', href=True)
if a is not None:
url=a['href'].replace('displaystory', 'PrinterFriendly').strip()
if url.startswith('/') or url.startswith('PrinterF'):
if url.startswith('Printer'):
url = '/'+url
if url.startswith('/'):
url = 'http://www.economist.com' + url
try:
subtitle = tag.previousSibling.contents[0].contents[0]

15
src/calibre/web/feeds/recipes/recipe_newsweek.py
View File

@ -89,6 +89,17 @@ class Newsweek(BasicNewsRecipe):
return cmp(tx, ty)
return sorted(ans, cmp=fcmp)
def ensure_html(self, soup):
root = soup.find(name=True)
if root.name == 'html': return soup
nsoup = BeautifulSoup('<html><head></head><body/></html>')
nroot = nsoup.find(name='body')
for x in soup.contents:
if getattr(x, 'name', False):
x.extract()
nroot.insert(len(nroot), x)
return nsoup
def postprocess_html(self, soup, first_fetch):
if not first_fetch:
h1 = soup.find(id='headline')
@ -99,7 +110,7 @@ class Newsweek(BasicNewsRecipe):
div.extract()
divs = list(soup.findAll('div', 'pagination'))
if not divs:
return soup
return self.ensure_html(soup)
for div in divs[1:]: div.extract()
all_a = divs[0].findAll('a', href=True)
divs[0]['style']="display:none"
@ -109,7 +120,7 @@ class Newsweek(BasicNewsRecipe):
for a in soup.findAll('a', href=test):
if a not in all_a:
del a['href']
return soup
return self.ensure_html(soup)
def get_current_issue(self):
soup = self.index_to_soup('http://www.newsweek.com')