Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix Economist not downloading all aticles from Technology Quarterly

Browse Source
This commit is contained in:
Kovid Goyal 2011-09-03 08:49:59 -06:00
parent 2425e2c09b
commit 384e24a06a
2 changed files with 34 additions and 52 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
recipes/economist.recipe
View File

@ -77,30 +77,21 @@ class Economist(BasicNewsRecipe):
continue
self.log('Found section: %s'%section_title)
articles = []
for h5 in section.findAll('h5'):
article_title = self.tag_to_string(h5).strip()
if not article_title:
continue
data = h5.findNextSibling(attrs={'class':'article'})
if data is None: continue
a = data.find('a', href=True)
if a is None: continue
url = a['href']
if url.startswith('/'): url = 'http://www.economist.com'+url
url += '/print'
article_title += ': %s'%self.tag_to_string(a).strip()
articles.append({'title':article_title, 'url':url,
'description':'', 'date':''})
if not articles:
# We have last or first section
for art in section.findAll(attrs={'class':'article'}):
a = art.find('a', href=True)
subsection = ''
for node in section.findAll(attrs={'class':'article'}):
subsec = node.findPreviousSibling('h5')
if subsec is not None:
subsection = self.tag_to_string(subsec)
prefix = (subsection+': ') if subsection else ''
a = node.find('a', href=True)
if a is not None:
url = a['href']
if url.startswith('/'): url = 'http://www.economist.com'+url
url += '/print'
title = self.tag_to_string(a)
if title:
title = prefix + title
self.log('\tFound article:', title)
articles.append({'title':title, 'url':url,
'description':'', 'date':''})

27
recipes/economist_free.recipe
View File

@ -69,30 +69,21 @@ class Economist(BasicNewsRecipe):
continue
self.log('Found section: %s'%section_title)
articles = []
for h5 in section.findAll('h5'):
article_title = self.tag_to_string(h5).strip()
if not article_title:
continue
data = h5.findNextSibling(attrs={'class':'article'})
if data is None: continue
a = data.find('a', href=True)
if a is None: continue
url = a['href']
if url.startswith('/'): url = 'http://www.economist.com'+url
url += '/print'
article_title += ': %s'%self.tag_to_string(a).strip()
articles.append({'title':article_title, 'url':url,
'description':'', 'date':''})
if not articles:
# We have last or first section
for art in section.findAll(attrs={'class':'article'}):
a = art.find('a', href=True)
subsection = ''
for node in section.findAll(attrs={'class':'article'}):
subsec = node.findPreviousSibling('h5')
if subsec is not None:
subsection = self.tag_to_string(subsec)
prefix = (subsection+': ') if subsection else ''
a = node.find('a', href=True)
if a is not None:
url = a['href']
if url.startswith('/'): url = 'http://www.economist.com'+url
url += '/print'
title = self.tag_to_string(a)
if title:
title = prefix + title
self.log('\tFound article:', title)
articles.append({'title':title, 'url':url,
'description':'', 'date':''})