def fetch(self):
def is_home_page(url):
return '/' not in url.replace('//', '').strip('/')
try:
soup = get_soup_by_url(self.url)
except Exception, e:
return
def save_note(user, url, date, tweet_id):
soup = get_soup_by_url(url)
if not soup:
return
tag = soup.find("div", {'class': 'highlightText'})
if not tag:
return
text = ''.join(tag.findAll(text=True)).strip()
remark = ''
tag = soup.find("div", {'class': 'note'})
if tag:
remark = ''.join(tag.findAll(text=True)).replace('Note:', '').replace('@zzrt', '').strip()
cover_tag = soup.find('div', {'class': 'cover'})
tag = cover_tag.find("span", {'class': 'title'})
if tag:
book = ''.join(tag.findAll(text=True)).strip()
if 'Personal Document' in book:
book = ''
else:
book = ''
tag = cover_tag.find("span", {'class': 'author'})
if tag:
author = ''.join(tag.findAll(text=True)).replace(' by ', '').strip()
else:
author = ''
if ' ' not in text \
and text[0] in string.ascii_letters \
and len(text) <= 64:
if Word.objects.filter(word=text).count() == 0:
Word.objects.create(user=user, url=url, word=text)
else:
note = Note(user=user, url=url, text=text)
note.uuid = str(uuid.uuid4())
note.added = date or datetime.datetime.now()
if remark:
note.remark = remark[:128]
if book:
note.book = book[:128]
if author:
note.author = author[:128]
note.save()
# Delete this tweet and tweet it's content
user_api = get_twitter_api(user=user)
if not user_api:
return
if len(text) <= 140:
status = text
if len(status) + len(" #note") <= 140:
status += " #note"
if remark and len(status) + len(remark) <= 138:
status = remark + ": " + status
try:
user_api.PostUpdates(status)
user_api.DestroyStatus(tweet_id)
except Exception, e:
logger.info("Error: %s tweeted: %s, delete: %s", e, status, tweet_id)
else:
