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 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 test_simple_search_form_with_named_parameter(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://*****:*****@name='adv_search_from']",
"fields": [
{
"name": "my_param",
"type": "constants",
"value": ["Cars"]
}
]
}""")
generic_form = GenericForm()
start_requests = list(generic_form.fill_generic_form(url, body, form_descriptor))
expected_requests = [([('_in_kw', '1'), ('_udlo', ''), ('_ex_kw', ''), ('_nkw', ''), ('_ipg', '50'), ('_adv', '1'), ('_salic', '1'), ('_dmd', '1'), ('_fsradio', '&LH_SpecificSeller=1'), ('_udhi', ''), ('_sop', '12'), (u'my_param', u'Cars'), ('_sasl', '')], 'http://www.ebay.com/sch/i.html', 'GET')]
self.assertEqual(start_requests, expected_requests)
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(start_requests, expected_requests)
class IblSpider(BaseSpider):
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.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 _process_start_urls(self, spec):
self.start_urls = self.start_urls or spec.get('start_urls')
if isinstance(self.start_urls, basestring):
self.start_urls = self.start_urls.splitlines()
for url in self.start_urls:
self._start_requests.append(Request(url, callback=self.parse, dont_filter=True))
def _create_init_requests(self, spec):
for rdata in spec:
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.form_requests.append(self.get_generic_form_start_request(rdata))
elif rdata["type"] == "start":
self._start_requests.append(self._create_start_request_from_specs(rdata))
def parse_login_page(self, response):
username = response.request.meta["username"]
password = response.request.meta["password"]
args, url, method = fill_login_form(response.url, response.body, username, password)
return FormRequest(url, method=method, formdata=args, callback=self.after_login, dont_filter=True)
def after_login(self, response):
for result in self.parse(response):
yield result
for req in self._start_requests:
yield req
def get_generic_form_start_request(self, form_descriptor):
file_fields = list(self.generic_form.get_url_field(form_descriptor))
if file_fields:
(field_index, field_descriptor) = file_fields.pop(0)
form_descriptor['field_index'] = field_index
return FormRequest(self.generic_form.get_value(field_descriptor), meta=form_descriptor,
callback=self.parse_field_url_page, dont_filter=True)
else:
return Request(url=form_descriptor.pop("form_url"), meta=form_descriptor,
callback=self.parse_form_page, dont_filter=True)
def parse_field_url_page(self, response):
form_descriptor = response.request.meta
field_index = form_descriptor['field_index']
field_descriptor = form_descriptor['fields'][field_index]
self.generic_form.set_values_url_field(field_descriptor, response.body)
yield self.get_generic_form_start_request(form_descriptor)
def parse_form_page(self, response):
try:
for (args, url, method) in self.generic_form.fill_generic_form(response.url,
response.body,
response.request.meta):
yield FormRequest(url, method=method, formdata=args,
callback=self.after_form_page, dont_filter=True)
except Exception, e:
self.log(str(e), log.WARNING)
for req in self._start_requests:
yield req
class IblSpider(BaseSpider):
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))
def parse_login_page(self, response):
username = response.request.meta["username"]
password = response.request.meta["password"]
args, url, method = fill_login_form(response.url, response.body, username, password)
return FormRequest(url, method=method, formdata=args, callback=self.after_login, dont_filter=True)
def after_login(self, response):
for result in self.parse(response):
yield result
for req in self._start_requests():
yield req
def get_generic_form_start_request(self, form_descriptor):
file_fields = list(self.generic_form.get_url_field(form_descriptor))
if file_fields:
(field_index, field_descriptor) = file_fields.pop(0)
form_descriptor['field_index'] = field_index
return FormRequest(self.generic_form.get_value(field_descriptor), meta=form_descriptor,
callback=self.parse_field_url_page, dont_filter=True)
else:
return Request(url=form_descriptor.pop("form_url"), meta=form_descriptor,
callback=self.parse_form_page, dont_filter=True)
def parse_field_url_page(self, response):
form_descriptor = response.request.meta
field_index = form_descriptor['field_index']
field_descriptor = form_descriptor['fields'][field_index]
self.generic_form.set_values_url_field(field_descriptor, response.body)
yield self.get_generic_form_start_request(form_descriptor)
def parse_form_page(self, response):
try:
for (args, url, method) in self.generic_form.fill_generic_form(response.url,
response.body,
response.request.meta):
yield FormRequest(url, method=method, formdata=args,
callback=self.after_form_page, dont_filter=True)
except Exception, e:
self.log(str(e), log.WARNING)
for req in self._start_requests():
yield req
