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 #521

Browse Source
This commit is contained in:
Kovid Goyal 2008-02-13 04:52:28 +00:00
parent ac0c54d15c
commit a1389cfd57
1 changed files with 14 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
src/libprs500/ebooks/lrf/web/profiles/__init__.py
View File

@ -232,12 +232,16 @@ class DefaultProfile(object):
pubdate = pubdate.replace('+0000', 'GMT')
url = self.get_article_url(item)
url = self.tag_to_string(url)
if require_url and not url:
self.logger.debug('Skipping article as it does not have a link url')
continue
purl = url
try:
purl = self.print_version(url)
except Exception, err:
self.logger.debug('Skipping %s as could not find URL for print version. Error:\n%s'%(url, err))
continue
content = item.find('content:encoded')
if not content:
@ -246,12 +250,7 @@ class DefaultProfile(object):
content = self.process_html_description(content, strip_links=False)
else:
content = ''
purl = url
try:
purl = self.print_version(url)
except Exception, err:
self.logger.debug('Skipping %s as could not find URL for print version. Error:\n%s'%(url, err))
continue
d = {
'title' : self.tag_to_string(item.find('title')),
'url' : purl,
@ -266,18 +265,23 @@ class DefaultProfile(object):
added_articles[title].append(d['title'])
if delta > self.oldest_article*3600*24:
continue
except Exception, err:
if self.verbose:
self.logger.exception('Error parsing article:\n%s'%(item,))
continue
try:
desc = item.find('description')
desc = ''
for c in item.findAll('description'):
desc = self.tag_to_string(c)
if desc:
break
d['description'] = self.process_html_description(desc) if self.html_description else desc.string
except:
d['description'] = ''
articles[title].append(d)
articles[title].sort(key=operator.itemgetter('timestamp'), reverse=True)
articles[title][self.max_articles_per_feed:] = []
articles[title] = articles[title][:self.max_articles_per_feed+1]
for item in articles[title]:
item.pop('timestamp')
if not articles[title]: