def set_tag():
"""
{
name: ['tagname'],
tab: 'tabname'
}
"""
try:
data = json.loads(request.data)
tags = data['name']
tabname = data['tab']
assert isinstance(tabname, basestring)
assert isinstance(tags, list)
for tag in tags:
assert isinstance(tag, basestring)
except:
return {'error': 'illegal format'}
u = get_user(current_user.username)
for tab in u['tab']:
if tabname == tab['name']:
tab['tags'] = tags
get_mongo('user').save(u)
log_info('user {0} set tag to {1} on tab \
{2}'.format(current_user.username, tags, tabname))
return {'tabs': u['tab']}
return {'error': 'no such tab'}
def add_tab():
"""add a new tab to current user
{
name: 'string' # name of the tab
priority: integer # bigger, better. default to be 0
}
"""
try:
data = json.loads(request.data)
name = data['name']
priority = int(data.get('priority', 0))
assert isinstance(name, basestring)
except:
return {'error': 'illegal format'}
username = current_user.username
doc = get_user(username)
for tab in doc['tab']:
if tab['name'] == name:
return {'error': 'tab with this name already exists!'}
doc['tab'].append({
'name': name,
'priority': priority,
'tags': []
})
get_mongo('user').save(doc)
log_info('user {0} add tab {1}'.format(username, name))
return {'success': 1}
def del_tag():
"""
GET /del_tag?name=xxx&tab=xxx
"""
try:
data = request.args
tagname = data['name']
tabname = data['tab']
assert isinstance(tagname, basestring) \
and isinstance(tabname, basestring)
except:
return {'error': 'illegal format'}
u = get_user(current_user.username)
for tab in u['tab']:
if tabname == tab['name']:
try:
tab['tags'].remove(tagname)
except ValueError:
return {'error': 'tag {0} not in tab {1}'.format(tagname,
tabname)}
get_mongo('user').save(u)
log_info('user {0} del tag {1} in tab \
{2}'.format(current_user.username, tagname, tabname))
return {'tabs': u['tab']}
return {'error': 'no such tab'}
def start_server():
"""start the server for all general fetchers"""
import_all_modules(__file__, __name__)
if not register_fetcher.fetcher_list:
uklogger.log_err('no general fetcher available, exit')
return
def worker(fetcher):
try:
while True:
uklogger.log_info('run fetcher {}'.format(
fetcher.fetcher_name))
fetcher.run()
gevent.sleep(fetcher.sleep_time)
except KeyboardInterrupt:
uklogger.log_info('worker {} got KeyboardInterrupt, exit'.format(
fetcher.fetcher_name))
jobs = [gevent.spawn(worker, i) for i in register_fetcher.fetcher_list]
try:
for i in jobs:
i.join()
except KeyboardInterrupt:
uklogger.log_info('got KeyboardInterrupt, exit')
def register():
"""user registration api.
username: string
password: string XXX TODO
"""
try:
username = request.values['username']
password = request.values['password']
assert isinstance(username, basestring)
assert isinstance(password, basestring)
except:
return {'error': 'illegal format'}
if len(username) < 3 or len(password) < 3:
return {'error':
'length of username and password must' +
' be at least 3 characters'}
exist = get_user(username)
if exist:
return {"error": "user {0} already exists".format(username)}
db = get_mongo('user')
db.insert({
'username': username,
'password': password,
'tab': []
})
log_info('new user: {0}:{1}'.format(username, password))
return {'success': 1}
def add_tag():
"""
{
name: 'tagname',
tab: 'tabname'
}
"""
try:
data = json.loads(request.data)
tagname = data['name']
tabname = data['tab']
assert isinstance(tagname, basestring) \
and isinstance(tabname, basestring)
except:
return {'error': 'illegal format'}
u = get_user(current_user.username)
for tab in u['tab']:
if tabname == tab['name']:
l = tab['tags']
l.append(tagname)
l = list(set(l))
tab['tags'] = l
get_mongo('user').save(u)
log_info('user {0} add tag {1} to tab \
{2}'.format(current_user.username, tagname, tabname))
return {'tabs': u['tab']}
return {'error': 'no such tab'}
def worker(fetcher):
try:
while True:
uklogger.log_info('run fetcher {}'.format(
fetcher.fetcher_name))
fetcher.run()
gevent.sleep(fetcher.sleep_time)
except KeyboardInterrupt:
uklogger.log_info('worker {} got KeyboardInterrupt, exit'.format(
fetcher.fetcher_name))
def xkcd_rss_fetcher(ctx):
"""fetcher xkcd.com/rss.xml, save each title with tag `xkcd`"""
URL = 'http://www.xkcd.com/rss.xml'
coll = ctx.get_mongo_collection()
for entry in fetch_rss(URL).entries:
try:
coll.insert({'_id': entry.id})
except DuplicateKeyError:
continue
ctx.new_item(TextOnlyItem(entry.title, entry.description),
['xkcd'], parse_entry_time(entry),
{'id': entry.id})
log_info(u'xkcd rss: new entry: {} {}'.format(entry.id,
entry.title))
def on_user_activated(user_id):
try:
user_fetcher = get_db_set(user_id, 'fetcher')
for i in user_fetcher:
fetcher = register_fetcher.fetcher_map.get(i)
if fetcher is None:
uklogger.log_err(
'fetcher {} not exist, requested by user {}'.format(
i, user_id))
else:
uklogger.log_info('run fetcher {} for user {}'.format(
i, user_id))
fetcher.run(user_id)
except Exception as ex:
uklogger.log_exc(ex)
def zhihu_rss_fetcher(ctx):
"""fetcher zhihu.com/rss/, save each title with tag `zhihu`"""
URL = 'http://www.zhihu.com/rss'
coll = ctx.get_mongo_collection()
for entry in fetch_rss(URL).entries:
try:
coll.insert({'_id': entry.link})
except DuplicateKeyError:
continue
ctx.new_item(TextOnlyItem(entry.title, entry.description), ['zhihu'],
parse_entry_time(entry),
{'id': entry.link})
log_info(u'zhihu: new entry: {} {}'.format(entry.link,
entry.title))
def stackoverflow_rss_fetcher(ctx):
"""fetcher stackoverflow.com/feeds,
save each title with tag `stackoverflow`"""
URL = 'http://stackoverflow.com/feeds'
coll = ctx.get_mongo_collection()
for entry in fetch_rss(URL).entries:
try:
coll.insert({'_id': entry.id})
except DuplicateKeyError:
continue
ctx.new_item(TextOnlyItem(entry.title, entry.summary),
['Stackoverflow'], parse_entry_time(entry),
{'id': entry.id})
log_info(u'stackoverflow: new entry: {} {}'.format(entry.id,
entry.title))
def login():
"""login api"""
try:
username = request.values['username']
password = request.values['password']
assert isinstance(username, basestring) \
and isinstance(password, basestring)
except Exception as e:
return {'error': 'illegal login format!' + str(e)}
auth = User(username, password)
err = auth.get_error()
if err:
return err
login_user(auth)
log_info('user {0} succesfully logged in'.format(username))
return {'success': 1}
def quora_rss_fetcher(ctx):
"""fetcher quora.com/rss/, save each title with tag `quora`"""
URL = 'https://www.quora.com/rss'
coll = ctx.get_mongo_collection()
for entry in fetch_rss(URL).entries:
try:
coll.insert({'_id': entry.id})
except DuplicateKeyError:
continue
try:
content = entry.content[0].value
except:
content = entry.summary
ctx.new_item(TextOnlyItem(entry.title, content), ['Quora'],
parse_entry_time(entry), {'id': entry.id})
log_info(u'quora rss: new entry: {} {}'.format(entry.id, entry.title))
def tsinghua_portal_fetcher(ctx):
"""fetcher portal.tsinghua.edu.cn, save each title with tag `portal`"""
coll = ctx.get_mongo_collection()
for entry in Tsinghua.getInfoNotices():
try:
coll.insert({'_id': entry['link']})
except DuplicateKeyError:
continue
ctx.new_item(TextOnlyItem(entry['title'], ""), ['Tsinghua info'],
other={"id": entry['link']})
log_info(u'Tsinghua Info: new entry: {} {}'.format(entry['link'],
entry['title']))
for entry in Tsinghua.getLibNotices():
try:
coll.insert({'_id': entry['link']})
except DuplicateKeyError:
continue
ctx.new_item(TextOnlyItem(entry['title'], ""), ['Tsinghua library'],
other={"id": entry['link']})
log_info(u'Tsinghua Library: new entry: {} {}'.format(entry['link'],
entry['title']))
def run(cls, ctx):
conf = cls.load_config(ctx.user_id)
if not conf:
ctx.new_item(TextOnlyItem(u'网络学堂验证失败', ''), ['THU learn'])
return
coll = ctx.get_mongo_collection()
if is_in_unittest():
entries = [{'id': 'test-{}'.format(uuid.uuid4()),
'title': 'thu learn in testcase',
'content': '{}@{}'.format(conf['username'],
conf['password']),
'create_time': '2013-12-14'}]
else:
try:
entries = fetch(conf['username'], conf['password'])
print entries
except Exception as e:
print e
ctx.new_item(TextOnlyItem(u'网络学堂抓取失败:' +
str(e), ''),
['THU learn'])
log_exc(e)
return
for entry in entries:
try:
coll.insert({'_id': str(ctx.user_id) + entry['id']})
except DuplicateKeyError:
continue
ctx.new_item(
TextOnlyItem(entry['title'], entry['content']),
['THU learn'], time.strptime(entry['create_time'], '%Y-%m-%d'),
{'id': entry['id']})
log_info(u'THU learn: new entry: {} {}'.format(entry['id'],
entry['title']))
def auto_tagging(ctx, doc):
"""auto tagging an item.
It will load tagger model from `ukconfig.tagger_path`.
Model should be trained prior to make this function work"""
global _tagger
if _tagger is None:
try:
log_info('loading tagger ...')
_tagger = TextTagger.load(ukconfig.tagger_path)
except IOError:
log_info('tagger model not found.')
return
tags = _tagger.predict_one(doc['desc'].render_content())
declare_tag(tags)
log_info('original tag: ' + str(doc['tag']))
log_info('autotagging: ' + str(tags))
doc['tag'] = list(set(doc['tag'] + tags))
"""auto tag """
def logout():
""" logout api"""
log_info('user {0} logged out'.format(current_user.username))
logout_user()
return {'success': 1}
def bitcoin_fetcher(ctx):
"""fetcher btcchina.com, save with tag `bitcoin`"""
price = getPrice()
ctx.new_item(TextOnlyItem("Last Bitcoin Price: " +
u"¥" + str(price), ""), ['Bitcoin'])
log_info(u'bitcoin price update: {}'.format(price))
