def __init__(self,
name,
spec,
item_schemas,
all_extractors,
settings=None,
**kw):
self.start_url_generators = {
'start_urls': IdentityGenerator(),
'generated_urls': UrlGenerator(settings, kw),
'url': IdentityGenerator(),
'feed': FeedGenerator(self.parse),
'generated': FragmentGenerator(),
}
self.generic_form = GenericForm(**kw)
super(IblSpider, self).__init__(name, **kw)
spec = deepcopy(spec)
self._add_spider_args_to_spec(spec, kw)
self._configure_js(spec, settings)
self.plugins = self._configure_plugins(settings, spec, item_schemas,
all_extractors)
self.login_requests, self.form_requests = [], []
self._start_urls = self._create_start_urls(spec)
self._start_requests = self._create_start_requests(spec)
self._create_init_requests(spec)
self._add_allowed_domains(spec)
self.page_actions = spec.get('page_actions', [])
def test_advanced_search_form_regex(self):
url = 'http://www.ebay.com/sch/ebayadvsearch/?rt=nc'
body = open(join(_PATH, "data", "ebay_advanced_search.html")).read()
form_descriptor = json.loads("""{
"type": "form",
"form_url": "http://www.ebay.com/sch/ebayadvsearch/?rt=nc",
"xpath": "//form[@name='adv_search_from']",
"fields": [
{
"xpath": ".//*[@name='_nkw']",
"type": "constants",
"value": ["Cars"]
},
{
"xpath": ".//*[@name='_in_kw']",
"type": "iterate",
"value": "[1-2]"
}
]
}""")
generic_form = GenericForm()
start_requests = list(generic_form.fill_generic_form(url, body, form_descriptor))
expected_requests = [([('_adv', '1'), ('_ex_kw', ''), ('_ftrv', '1'), ('_ftrt', '901'), ('_sabdlo', u''), ('_sabdhi', u''), ('_sop', '12'), ('_samihi', u''), ('_ipg', '50'), ('_salic', '1'), ('_sasl', ''), ('_udlo', ''), ('_okw', u''), ('_fsradio', '&LH_SpecificSeller=1'), ('_udhi', ''), ('_in_kw', '1'), ('_nkw', u'Cars'), ('_sacat', '0'), ('_oexkw', u''), ('_dmd', '1'), ('_saslop', '1'), ('_samilow', u'')], 'http://www.ebay.com/sch/i.html', 'GET'), ([('_adv', '1'), ('_ex_kw', ''), ('_ftrv', '1'), ('_ftrt', '901'), ('_sabdlo', u''), ('_sabdhi', u''), ('_sop', '12'), ('_samihi', u''), ('_ipg', '50'), ('_salic', '1'), ('_sasl', ''), ('_udlo', ''), ('_okw', u''), ('_fsradio', '&LH_SpecificSeller=1'), ('_udhi', ''), ('_in_kw', '2'), ('_nkw', u'Cars'), ('_sacat', '0'), ('_oexkw', u''), ('_dmd', '1'), ('_saslop', '1'), ('_samilow', u'')], 'http://www.ebay.com/sch/i.html', 'GET')]
self.assertEqual(start_requests, expected_requests)
def __init__(self, name, spec, item_schemas, all_extractors, **kw):
super(IblSpider, self).__init__(name, **kw)
spec = deepcopy(spec)
for key, val in kw.items():
if isinstance(val, basestring) and key in ['start_urls', 'exclude_patterns', 'follow_patterns', 'allowed_domains']:
val = val.splitlines()
spec[key] = val
self._item_template_pages = sorted((
[t['scrapes'], dict_to_page(t, 'annotated_body'),
t.get('extractors', [])] \
for t in spec['templates'] if t.get('page_type', 'item') == 'item'
), key=lambda pair: pair[0])
# generate ibl extractor for links pages
_links_pages = [dict_to_page(t, 'annotated_body')
for t in spec['templates'] if t.get('page_type') == 'links']
_links_item_descriptor = create_slybot_item_descriptor({'fields': {}})
self._links_ibl_extractor = InstanceBasedLearningExtractor([(t, _links_item_descriptor) for t in _links_pages]) \
if _links_pages else None
self._ipages = [page for _, page, _ in self._item_template_pages]
self.html_link_extractor = HtmlLinkExtractor()
self.rss_link_extractor = RssLinkExtractor()
self.build_url_filter(spec)
self.itemcls_info = {}
for itemclass_name, triplets in itertools.groupby(self._item_template_pages, operator.itemgetter(0)):
page_extractors_pairs = map(operator.itemgetter(1, 2), triplets)
schema = item_schemas[itemclass_name]
item_cls = SlybotItem.create_iblitem_class(schema)
page_descriptor_pairs = []
for page, template_extractors in page_extractors_pairs:
item_descriptor = create_slybot_item_descriptor(schema)
apply_extractors(item_descriptor, template_extractors, all_extractors)
page_descriptor_pairs.append((page, item_descriptor))
extractor = InstanceBasedLearningExtractor(page_descriptor_pairs)
self.itemcls_info[itemclass_name] = {
'class': item_cls,
'descriptor': item_descriptor,
'extractor': extractor,
}
self.login_requests = []
self.form_requests = []
self._start_requests = []
self.generic_form = GenericForm(**kw)
self._create_init_requests(spec.get("init_requests", []))
self._process_start_urls(spec)
self.allowed_domains = spec.get('allowed_domains',
self._get_allowed_domains(self._ipages))
if not self.allowed_domains:
self.allowed_domains = None
def test_simple_search_form_with_file_type(self):
url = 'http://www.ebay.com/sch/ebayadvsearch/?rt=nc'
body = open(join(_PATH, "data", "ebay_advanced_search.html")).read()
form_descriptor = json.loads("""{
"type": "form",
"form_url": "http://www.ebay.com/sch/ebayadvsearch/?rt=nc",
"xpath": "//form[@name='adv_search_from']",
"fields": [
{
"name": "my_param",
"type": "inurl",
"value": "file://%s/test_params.txt",
"file_values": ["Cars", "Boats", "Houses", "Electronics"]
}
]
}""" % join(_PATH, "data"))
generic_form = GenericForm()
start_requests = list(
generic_form.fill_generic_form(url, body, form_descriptor))
expected_requests = [
([('_adv', '1'), ('_ex_kw', ''), ('_ftrv', '1'), ('_ftrt', '901'),
('_sabdlo', u''), ('_sabdhi', u''), ('_sop', '12'),
('_samihi', u''), ('_ipg', '50'), ('_salic', '1'),
(u'my_param', u'Cars'), ('_sasl', ''), ('_udlo', ''),
('_okw', u''), ('_fsradio', '&LH_SpecificSeller=1'),
('_udhi', ''), ('_in_kw', '1'), ('_nkw', ''), ('_sacat', '0'),
('_oexkw', u''), ('_dmd', '1'), ('_saslop', '1'),
('_samilow', u'')], 'http://www.ebay.com/sch/i.html', 'GET'),
([('_adv', '1'), ('_ex_kw', ''), ('_ftrv', '1'), ('_ftrt', '901'),
('_sabdlo', u''), ('_sabdhi', u''), ('_sop', '12'),
('_samihi', u''), ('_ipg', '50'), ('_salic', '1'),
(u'my_param', u'Boats'), ('_sasl', ''), ('_udlo', ''),
('_okw', u''), ('_fsradio', '&LH_SpecificSeller=1'),
('_udhi', ''), ('_in_kw', '1'), ('_nkw', ''), ('_sacat', '0'),
('_oexkw', u''), ('_dmd', '1'), ('_saslop', '1'),
('_samilow', u'')], 'http://www.ebay.com/sch/i.html', 'GET'),
([('_adv', '1'), ('_ex_kw', ''), ('_ftrv', '1'), ('_ftrt', '901'),
('_sabdlo', u''), ('_sabdhi', u''), ('_sop', '12'),
('_samihi', u''), ('_ipg', '50'), ('_salic', '1'),
(u'my_param', u'Houses'), ('_sasl', ''), ('_udlo', ''),
('_okw', u''), ('_fsradio', '&LH_SpecificSeller=1'),
('_udhi', ''), ('_in_kw', '1'), ('_nkw', ''), ('_sacat', '0'),
('_oexkw', u''), ('_dmd', '1'), ('_saslop', '1'),
('_samilow', u'')], 'http://www.ebay.com/sch/i.html', 'GET'),
([('_adv', '1'), ('_ex_kw', ''), ('_ftrv', '1'), ('_ftrt', '901'),
('_sabdlo', u''), ('_sabdhi', u''), ('_sop', '12'),
('_samihi', u''), ('_ipg', '50'), ('_salic', '1'),
(u'my_param', u'Electronics'), ('_sasl', ''), ('_udlo', ''),
('_okw', u''), ('_fsradio', '&LH_SpecificSeller=1'),
('_udhi', ''), ('_in_kw', '1'), ('_nkw', ''), ('_sacat', '0'),
('_oexkw', u''), ('_dmd', '1'), ('_saslop', '1'),
('_samilow', u'')], 'http://www.ebay.com/sch/i.html', 'GET')
]
self.assertEqual(request_to_set(start_requests),
request_to_set(expected_requests))
def __init__(self,
name,
spec,
item_schemas,
all_extractors,
settings=None,
**kw):
super(IblSpider, self).__init__(name, **kw)
self._job_id = settings.get('JOB', '')
spec = deepcopy(spec)
for key, val in kw.items():
if isinstance(val, six.string_types) and key in STRING_KEYS:
val = val.splitlines()
spec[key] = val
self._item_template_pages = sorted(
((t['scrapes'], t) for t in spec['templates']
if t.get('page_type', 'item') == 'item'),
key=itemgetter(0))
self._templates = [templ for _, templ in self._item_template_pages]
self.plugins = IndexedDict()
for plugin_class, plugin_name in zip(load_plugins(settings),
load_plugin_names(settings)):
instance = plugin_class()
instance.setup_bot(settings, spec, item_schemas, all_extractors)
self.plugins[plugin_name] = instance
self.js_enabled = False
self.SPLASH_HOST = None
if settings.get('SPLASH_URL'):
self.SPLASH_HOST = urlparse(settings.get('SPLASH_URL')).hostname
self.js_enabled = spec.get('js_enabled', False)
if self.js_enabled and (settings.get('SPLASH_PASS') is not None
or settings.get('SPLASH_USER') is not None):
self.splash_auth = basic_auth_header(
settings.get('SPLASH_USER', ''),
settings.get('SPLASH_PASS', ''))
self._filter_js_urls = self._build_js_url_filter(spec)
self.login_requests = []
self.form_requests = []
self._start_requests = []
self.generic_form = GenericForm(**kw)
self._create_init_requests(spec.get("init_requests", []))
self._process_start_urls(spec)
self.allowed_domains = spec.get(
'allowed_domains', self._get_allowed_domains(self._templates))
self.page_actions = spec.get('page_actions', [])
if not self.allowed_domains:
self.allowed_domains = None
def __init__(self,
name,
spec,
item_schemas,
all_extractors,
settings=None,
**kw):
super(IblSpider, self).__init__(name, **kw)
spec = deepcopy(spec)
for key, val in kw.items():
if isinstance(val, basestring) and key in STRING_KEYS:
val = val.splitlines()
spec[key] = val
self._item_template_pages = sorted(
((t['scrapes'], t) for t in spec['templates']
if t.get('page_type', 'item') == 'item'),
key=itemgetter(0))
self._templates = [templ for _, templ in self._item_template_pages]
self.plugins = IndexedDict()
for plugin_class, plugin_name in zip(load_plugins(settings),
load_plugin_names(settings)):
instance = plugin_class()
instance.setup_bot(settings, spec, item_schemas, all_extractors)
self.plugins[plugin_name] = instance
self.login_requests = []
self.form_requests = []
self._start_requests = []
self.generic_form = GenericForm(**kw)
self._create_init_requests(spec.get("init_requests", []))
self._process_start_urls(spec)
self.allowed_domains = spec.get(
'allowed_domains', self._get_allowed_domains(self._templates))
if not self.allowed_domains:
self.allowed_domains = None
def __init__(self, name, spec, item_schemas, all_extractors, settings=None,
**kw):
self.start_url_generators = {
'start_urls': IdentityGenerator(),
'generated_urls': UrlGenerator(settings, kw),
'url': IdentityGenerator(),
'feed': FeedGenerator(self.parse),
'generated': FragmentGenerator(),
}
self.generic_form = GenericForm(**kw)
super(IblSpider, self).__init__(name, **kw)
spec = deepcopy(spec)
self._add_spider_args_to_spec(spec, kw)
#if actions configured, then set js_enabled as true, and put url of each action to js_enable_patterns.
self.actions = spec.get('actions', [])
'''
if len(self.actions):
spec['js_enabled']= True
enable_patterns = spec.get('js_enable_patterns', [] )
for action in self.actions:
enable_patterns.append(action.get('url'))
spec['js_enable_patterns']= enable_patterns
'''
self._configure_js(spec, settings)
self.plugins = self._configure_plugins(
settings, spec, item_schemas, all_extractors)
self.login_requests, self.form_requests = [], []
self._start_urls = self._create_start_urls(spec)
self._start_requests = self._create_start_requests(spec)
self._create_init_requests(spec)
self._add_allowed_domains(spec)
self.page_actions = spec.get('page_actions', [])
def __init__(self, name, spec, item_schemas, all_extractors, **kw):
super(IblSpider, self).__init__(name, **kw)
self._item_template_pages = sorted((
[t['scrapes'], dict_to_page(t, 'annotated_body'),
t.get('extractors', [])] \
for t in spec['templates'] if t.get('page_type', 'item') == 'item'
), key=lambda pair: pair[0])
# generate ibl extractor for links pages
_links_pages = [dict_to_page(t, 'annotated_body')
for t in spec['templates'] if t.get('page_type') == 'links']
_links_item_descriptor = create_slybot_item_descriptor({'fields': {}})
self._links_ibl_extractor = InstanceBasedLearningExtractor([(t, _links_item_descriptor) for t in _links_pages]) \
if _links_pages else None
self._ipages = [page for _, page, _ in self._item_template_pages]
self.start_urls = self.start_urls or spec.get('start_urls')
if isinstance(self.start_urls, basestring):
self.start_urls = self.start_urls.splitlines()
self.html_link_extractor = HtmlLinkExtractor()
self.rss_link_extractor = RssLinkExtractor()
self.allowed_domains = spec.get('allowed_domains',
self._get_allowed_domains(self._ipages))
if not self.allowed_domains:
self.allowed_domains = None
self.build_url_filter(spec)
self.itemcls_info = {}
for itemclass_name, triplets in itertools.groupby(self._item_template_pages, operator.itemgetter(0)):
page_extractors_pairs = map(operator.itemgetter(1, 2), triplets)
schema = item_schemas[itemclass_name]
item_cls = get_iblitem_class(schema)
page_descriptor_pairs = []
for page, template_extractors in page_extractors_pairs:
item_descriptor = create_slybot_item_descriptor(schema)
apply_extractors(item_descriptor, template_extractors, all_extractors)
page_descriptor_pairs.append((page, item_descriptor))
extractor = InstanceBasedLearningExtractor(page_descriptor_pairs)
self.itemcls_info[itemclass_name] = {
'class': item_cls,
'descriptor': item_descriptor,
'extractor': extractor,
}
self.login_requests = []
self.form_requests = []
for rdata in spec.get("init_requests", []):
if rdata["type"] == "login":
request = Request(url=rdata.pop("loginurl"), meta=rdata,
callback=self.parse_login_page, dont_filter=True)
self.login_requests.append(request)
elif rdata["type"] == "form":
self.generic_form = GenericForm(**kw)
self.form_requests.append(self.get_generic_form_start_request(rdata))
