nojhan/weboob-devel
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

fix parsing of comments when templeet sucks, and display comments URL in signatures

Browse source
This commit is contained in:
Romain Bignon 2010-09-09 16:00:08 +02:00
commit d1f805145d
2 changed files with 12 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

3
weboob/backends/dlfp/backend.py
View file

@ -110,7 +110,8 @@ class DLFPBackend(BaseBackend, ICapMessages, ICapMessagesPost):
date=com.date, date=com.date,
parent=parent, parent=parent,
content=com.body, content=com.body,
signature='Score: %d' % com.score, signature='<br />'.join(['Score: %d' % com.score,
'URL: %s' % com.url]),
children=[], children=[],
flags=flags) flags=flags)

13
weboob/backends/dlfp/pages/news.py
View file

@ -34,27 +34,34 @@ class Comment(object):
self.date = None self.date = None
self.body = u'' self.body = u''
self.score = 0 self.score = 0
self.url = u''
self.comments = [] self.comments = []
for sub in div.getchildren(): for sub in div.getchildren():
if sub.tag == 'a': if sub.tag == 'a':
self.id = sub.attrib['name'] self.id = sub.attrib['name']
self.url = u'https://linuxfr.org/comments/%s.html#%s' % (self.id, self.id)
elif sub.tag == 'h1': elif sub.tag == 'h1':
try: try:
self.title = sub.find('b').text self.title = sub.find('b').text
except UnicodeError: except UnicodeError:
warning('Bad encoded title, but DLFP sucks') warning('Bad encoded title, but DLFP sucks')
elif sub.tag == 'div' and sub.attrib.get('class', '').startswith('comment'): elif sub.tag == 'div' and sub.attrib.get('class', '').startswith('comment'):
self.author = sub.find('a').text self.author = sub.find('a').text if sub.find('a') is not None else 'Unknown'
self.date = self.parse_date(sub.find('i').tail) self.date = self.parse_date(sub.find('i').tail)
self.score = int(sub.findall('i')[1].find('span').text) self.score = int(sub.findall('i')[-1].find('span').text)
self.body = self.browser.parser.tostring(sub.find('p')) self.body = self.browser.parser.tostring(sub.find('p'))
elif sub.attrib.get('class', '') == 'commentsul': elif sub.attrib.get('class', '') == 'commentsul':
comment = Comment(self.browser, sub.find('li'), self.id) comment = Comment(self.browser, sub.find('li'), self.id)
self.comments.append(comment) self.comments.append(comment)
def parse_date(self, date_s): def parse_date(self, date_s):
return local2utc(datetime.strptime(date_s.strip().encode('utf-8'), u'le %d/%m/%Y \xe0 %H:%M.'.encode('utf-8'))) date_s = date_s.strip().encode('utf-8')
if not date_s:
date = datetime.now()
else:
date = datetime.strptime(date_s, u'le %d/%m/%Y \xe0 %H:%M.'.encode('utf-8'))
return local2utc(date)
def iter_all_comments(self): def iter_all_comments(self):
for comment in self.comments: for comment in self.comments: