def home(request):
if request.method == "POST":
url = request.POST.get("url")
if not url.startswith('http'):
url = 'http://' + url
if '.' not in url:
messages.error(request, "Need a valid URL.")
return HttpResponseRedirect("/")
try:
bf = BriticleFile(url, settings.KINDLE_LIVE_DIR)
except Exception, e:
if isinstance(e, URLError) or 'timed out' in str(e):
messages.error(request, "Open URL Error, Try again later.")
return HttpResponseRedirect("/")
elif isinstance (e, UnicodeEncodeError):
logger.info("UnicodeEncodeError: %s URL: %s" % (e, url))
messages.error(request, "Internal Error when fetch the URL.")
return HttpResponseRedirect("/")
raise
doc = bf.save_to_mobi(sent_by="Kindle.io")
if os.path.exists(doc):
if not settings.DEBUG:
send_to_kindle(request, [doc], subject=bf.title)
os.remove(doc)
messages.success(request, "The doc has been sent to your kindle successfully!")
return HttpResponseRedirect("/")
else:
messages.error(request, "Error: No file generated for this URL.")
return HttpResponseRedirect("/")
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:
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:
# len(u".. #note http://t.co/al28lfq5xx") == 32; 140 - 32 = 108
status = text[:108] + ".. #note http://kindle.io" + note.get_absolute_url()
status = shorten_status_urls(status)
if len(status) > 140:
status = text[:130] + "... #note"
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)
def update_news(self, article_list):
"""
Update HackerNews records
"""
count_created = count_updated = count_filed = 0
for article in article_list:
if self.filter(url=article['url']).exists():
news = self.get(url=article['url'])
# Update the points of the article, send the points update signal
if news.filed and news.file_path and article['points'] > news.points:
pre_points = news.points
news.points = article['points']
news.save()
signals.points_updated.send(sender=news, pre_points=pre_points)
count_updated += 1
# If the article is abort before. Ignore it.
# We can check the error log for reasons
if news.aborted:
continue
else:
# Create an new one if it does not exist
news = self.create(url=article['url'],
points=article['points'],
title=smart_str(article['title']))
count_created += 1
# Save article whose points is high enough into file
if (not news.filed) and article['points'] >= POINTS_LIMIT_TO_SAVE:
try:
year, week_number, _ = datetime.date.today().isocalendar()
dir_hackernews = settings.HACKER_NEWS_DIR
if not os.path.exists(dir_hackernews):
os.mkdir(dir_hackernews)
dir_year = os.path.join(dir_hackernews, str(year))
if not os.path.exists(dir_year):
os.mkdir(dir_year)
dir_week = os.path.join(dir_year, "%02d" % week_number)
if not os.path.exists(dir_week):
os.mkdir(dir_week)
bf = BriticleFile(news.url, dir_week)
except Exception, e:
if isinstance(e, URLError) or 'timed out' in str(e):
logger.error("URLError or Time out Exception: %s URL: %s" % (e, news.url))
news.aborted = True
news.save()
continue
elif isinstance (e, UnicodeEncodeError):
logger.error("UnicodeEncodeError: %s URL: %s" % (e, news.url))
news.aborted = True
news.save()
continue
raise
# Abort if there is not content
if bf.is_empty():
logger.info("No content found for: %s" % news.url)
news.aborted = True
news.save()
continue
try:
mobi = bf.save_to_mobi(title=news.title, sent_by="Kindle.io")
except Exception, e:
logger.error("Failed while calling bf.save_to_mobi(). %s: %s URL: %s" % \
(e.__class__, e, news.url))
news.aborted = True
news.save()
continue
if mobi:
news.filed = True
news.file_path = mobi
news.html = bf.html
news.save()
signals.file_saved.send(sender=news)
count_filed += 1
else:
logger.error("Failed to save file. URL: %s" % news.url)
news.aborted = True
news.save()
