def async_parser(_, objconf, skip=False, **kwargs):
""" Asynchronously parses the pipe content
Args:
_ (None): Ignored
objconf (obj): The pipe configuration (an Objectify instance)
skip (bool): Don't parse the content
kwargs (dict): Keyword arguments
Kwargs:
assign (str): Attribute to assign parsed content (default: content)
stream (dict): The original item
Returns:
Iter[dict]: The stream of items
Examples:
>>> from riko import get_path
>>> from riko.bado import react
>>> from riko.bado.mock import FakeReactor
>>> from meza.fntools import Objectify
>>>
>>> @coroutine
... def run(reactor):
... xml_url = get_path('ouseful.xml')
... xml_conf = {'url': xml_url, 'xpath': '/rss/channel/item'}
... xml_objconf = Objectify(xml_conf)
... xml_args = (None, xml_objconf)
... html_url = get_path('sciencedaily.html')
... html_conf = {'url': html_url, 'xpath': '/html/head/title'}
... html_objconf = Objectify(html_conf)
... html_args = (None, html_objconf)
... kwargs = {'stream': {}}
...
... try:
... xml_stream = yield async_parser(*xml_args, **kwargs)
... html_stream = yield async_parser(*html_args, **kwargs)
... print(next(xml_stream)['title'][:44])
... print(next(html_stream))
... except Exception as e:
... logger.error(e)
... logger.error(traceback.format_exc())
...
>>>
>>> try:
... react(run, _reactor=FakeReactor())
... except SystemExit:
... pass
...
Running “Native” Data Wrangling Applications
Help Page -- ScienceDaily
"""
if skip:
stream = kwargs['stream']
else:
url = get_abspath(objconf.url)
ext = splitext(url)[1].lstrip('.')
xml = (ext == 'xml') or objconf.strict
try:
f = yield io.async_url_open(url)
tree = yield util.xml2etree(f, xml=xml)
except Exception as e:
logger.error(e)
logger.error(traceback.format_exc())
elements = xpath(tree, objconf.xpath)
f.close()
items = map(util.etree2dict, elements)
stringified = ({kwargs['assign']: encode(i)} for i in items)
stream = stringified if objconf.stringify else items
return_value(stream)
def async_parser(_, objconf, skip=False, **kwargs):
""" Asynchronously parses the pipe content
Args:
_ (None): Ignored
objconf (obj): The pipe configuration (an Objectify instance)
skip (bool): Don't parse the content
kwargs (dict): Keyword arguments
Kwargs:
assign (str): Attribute to assign parsed content (default: content)
stream (dict): The original item
Returns:
Deferred: twisted.internet.defer.Deferred stream
Examples:
>>> from six.moves.urllib.request import urlopen
>>> from riko import get_path
>>> from riko.bado import react
>>> from riko.bado.mock import FakeReactor
>>> from riko.utils import get_abspath
>>> from meza.fntools import Objectify
>>>
>>> feed = 'http://feeds.feedburner.com/TechCrunch/'
>>> url = 'http://query.yahooapis.com/v1/public/yql'
>>> query = "select * from feed where url='%s'" % feed
>>> f = urlopen(get_abspath(get_path('yql.xml')))
>>>
>>> def run(reactor):
... callback = lambda x: print(next(x)['title'])
... conf = {'query': query, 'url': url, 'debug': False}
... objconf = Objectify(conf)
... kwargs = {'stream': {}, 'response': f}
... d = async_parser(None, objconf, **kwargs)
... d.addCallbacks(callback, logger.error)
... d.addCallback(lambda _: f.close())
... return d
>>>
>>> try:
... react(run, _reactor=FakeReactor())
... except SystemExit:
... pass
... finally:
... f.close()
Bring pizza home
"""
if skip:
stream = kwargs['stream']
else:
f = kwargs.get('response')
if not f:
params = {'q': objconf.query, 'diagnostics': objconf.debug}
r = yield treq.get(objconf.url, params=params)
f = yield treq.content(r)
tree = yield util.xml2etree(f)
results = next(tree.getElementsByTagName('results'))
stream = map(util.etree2dict, results.childNodes)
return_value(stream)
def async_parser(_, objconf, skip, **kwargs):
""" Asynchronously parses the pipe content
Args:
_ (None): Ignored
objconf (obj): The pipe configuration (an Objectify instance)
skip (bool): Don't parse the content
kwargs (dict): Keyword arguments
Kwargs:
assign (str): Attribute to assign parsed content (default: content)
stream (dict): The original item
Returns:
Deferred: twisted.internet.defer.Deferred Tuple of (stream, skip)
Examples:
>>> from six.moves.urllib.request import urlopen
>>> from riko import get_path
>>> from riko.bado import react
>>> from riko.bado.mock import FakeReactor
>>> from riko.lib.utils import Objectify, get_abspath
>>>
>>> feed = 'http://feeds.feedburner.com/TechCrunch/'
>>> url = 'http://query.yahooapis.com/v1/public/yql'
>>> query = "select * from feed where url='%s'" % feed
>>> f = urlopen(get_abspath(get_path('yql.xml')))
>>>
>>> def run(reactor):
... callback = lambda x: print(next(x[0])['title'])
... conf = {'query': query, 'url': url, 'debug': False}
... objconf = Objectify(conf)
... kwargs = {'stream': {}, 'response': f}
... d = async_parser(None, objconf, False, **kwargs)
... d.addCallbacks(callback, logger.error)
... d.addCallback(lambda _: f.close())
... return d
>>>
>>> try:
... react(run, _reactor=FakeReactor())
... except SystemExit:
... pass
...
Bring pizza home
"""
if skip:
stream = kwargs['stream']
else:
f = kwargs.get('response')
if not f:
params = {'q': objconf.query, 'diagnostics': objconf.debug}
r = yield treq.get(objconf.url, params=params)
f = yield treq.content(r)
tree = yield util.xml2etree(f)
results = next(tree.getElementsByTagName('results'))
stream = map(util.etree2dict, results.childNodes)
result = (stream, skip)
return_value(result)
def async_parser(_, objconf, skip=False, **kwargs):
""" Asynchronously parses the pipe content
Args:
_ (None): Ignored
objconf (obj): The pipe configuration (an Objectify instance)
skip (bool): Don't parse the content
kwargs (dict): Keyword arguments
Kwargs:
assign (str): Attribute to assign parsed content (default: content)
stream (dict): The original item
Returns:
Iter[dict]: The stream of items
Examples:
>>> from riko import get_path
>>> from riko.bado import react
>>> from riko.bado.mock import FakeReactor
>>> from meza.fntools import Objectify
>>>
>>> @coroutine
... def run(reactor):
... xml_url = get_path('ouseful.xml')
... xml_conf = {'url': xml_url, 'xpath': '/rss/channel/item'}
... xml_objconf = Objectify(xml_conf)
... xml_args = (None, xml_objconf)
... html_url = get_path('sciencedaily.html')
... html_conf = {'url': html_url, 'xpath': '/html/head/title'}
... html_objconf = Objectify(html_conf)
... html_args = (None, html_objconf)
... kwargs = {'stream': {}}
...
... try:
... xml_stream = yield async_parser(*xml_args, **kwargs)
... html_stream = yield async_parser(*html_args, **kwargs)
... print(next(xml_stream)['title'][:44])
... print(next(html_stream))
... except Exception as e:
... logger.error(e)
... logger.error(traceback.format_exc())
...
>>>
>>> try:
... react(run, _reactor=FakeReactor())
... except SystemExit:
... pass
...
Running “Native” Data Wrangling Applications
Help Page -- ScienceDaily
"""
if skip:
stream = kwargs['stream']
else:
url = get_abspath(objconf.url)
ext = splitext(url)[1].lstrip('.')
xml = (ext == 'xml') or objconf.strict
try:
f = yield io.async_url_open(url)
tree = yield util.xml2etree(f, xml=xml)
except Exception as e:
logger.error(e)
logger.error(traceback.format_exc())
elements = xpath(tree, objconf.xpath)
f.close()
items = map(util.etree2dict, elements)
stringified = ({kwargs['assign']: encode(i)} for i in items)
stream = stringified if objconf.stringify else items
return_value(stream)
