class DOCParser(HTMLParser):
def __init__(self, *args, **kwargs):
HTMLParser.__init__(self, *args, **kwargs)
self._logger = logging.getLogger(self.__class__.__name__)
self.msg = {}
# local (per-document) href cache
self.hrefs = []
self.protocols_r = r"^http://"
self.mimetype_r = r"^text\/html"
self.queue = QueueManager(
mqhost="localhost",
mqport=61613,
userid="",
passwd="",
qin="to_parse",
qout="to_persist",
recv_callback=self.worker,
encode_parms=["data"],
encoding="base64",
)
def start(self):
self.queue.subscribe()
def handle_starttag(self, tag, attrs):
attrs_h = dict(attrs)
if (
tag == "a"
and attrs_h.has_key("href")
and attrs_h["href"] is not self.msg["url"]
and attrs_h["href"] not in self.hrefs
and re.search(self.protocols_r, attrs_h["href"], re.IGNORECASE)
):
self._logger.info("Found %s. Enqueuing..." % attrs_h["href"])
try:
self.queue.enqueue(msg={"parent": self.msg["url"], "url": attrs_h["href"]})
except:
pass
else:
self.hrefs.append(attrs_h["href"])
def worker(self, msg={}):
self.reset()
self.msg = msg
self.hrefs = []
if re.search(self.mimetype_r, self.msg["headers"]["content-type"], re.IGNORECASE):
self._logger.info("Received %s" % msg["url"])
self.feed(msg["data"])
def __init__(self, url="http://www.python.org/", timeout=10):
self._logger = logging.getLogger(self.__class__.__name__)
self.url = url
self.extensions_blacklist_r = r'\.(?:jpg|jpeg|png|gif|zip|gz|rar|tar|pdf|doc|docx|ppt|pptx|xls|xlsx|iso|mp3|wav|mid|wmv|wma|txt|scr|exe|com|bat|eml)$'
self.timeout = timeout
self.cache = CacheManager()
self.queue = QueueManager(mqhost="localhost", mqport=61613, userid="",
passwd="", qin="to_fetch", qout="to_parse",
recv_callback=self.worker, encode_parms=["data"],
encoding="base64")
class Fetcher(object):
def __init__(self, url="http://www.python.org/", timeout=10):
self._logger = logging.getLogger(self.__class__.__name__)
self.url = url
self.extensions_blacklist_r = r'\.(?:jpg|jpeg|png|gif|zip|gz|rar|tar|pdf|doc|docx|ppt|pptx|xls|xlsx|iso|mp3|wav|mid|wmv|wma|txt|scr|exe|com|bat|eml)$'
self.timeout = timeout
self.cache = CacheManager()
self.queue = QueueManager(mqhost="localhost", mqport=61613, userid="",
passwd="", qin="to_fetch", qout="to_parse",
recv_callback=self.worker, encode_parms=["data"],
encoding="base64")
def start(self):
self.queue.subscribe()
# REMOVE
import simplejson
QueueManager._qinst.send(simplejson.dumps({"url": self.url, "parent": "start"}),
destination="/queue/to_fetch")
def worker(self, msg={}):
url = msg["url"]
if re.search(self.extensions_blacklist_r, url, re.IGNORECASE):
return
try:
self._logger.info("Fetching %s" % msg["url"])
req = urlopen(url, timeout=self.timeout)
except Exception, e:
self._logger.error("Error on trying to fetch %s" % url)
self._logger.exception(e)
else:
def __init__(self, *args, **kwargs):
HTMLParser.__init__(self, *args, **kwargs)
self._logger = logging.getLogger(self.__class__.__name__)
self.msg = {}
# local (per-document) href cache
self.hrefs = []
self.protocols_r = r"^http://"
self.mimetype_r = r"^text\/html"
self.queue = QueueManager(
mqhost="localhost",
mqport=61613,
userid="",
passwd="",
qin="to_parse",
qout="to_persist",
recv_callback=self.worker,
encode_parms=["data"],
encoding="base64",
)
from qmanager import QueueManager
from fuzzywuzzy import process
from hashlib import md5
import os
from ryclass import SonicAuth
import random
from pprint import pprint
# Enter Info Here
sshost = "https://subsonic.example.org"
ssuser = "******"
sspass = "******"
sauth = SonicAuth(sshost, ssuser, sspass)
ssconn = sauth._ssconn
queue = QueueManager()
@ask.launch
def start_skill():
#print 'the amazon user id is ' + session.user['userId']
text = 'Welcome to Subsonic. \
Try asking me to play a song or start a playlist'
prompt = 'For example say, play music by Ozzy Osbourne'
return question(text).reprompt(prompt) \
.simple_card(title='Welcome to Subsonic!',
content='Try asking me to play a song')
@ask.intent("AMAZON.SearchAction<object@MusicCreativeWork>",