def process_item(self, item, spider):
try:
item['news_website'] = spider.ref_object
item['search_term'] = spider.search_terms #I added this its how we see what was searched per item
checker_rt = SchedulerRuntime(runtime_type='C')
checker_rt.save()
item['checker_runtime'] = checker_rt
item.save()
# p1 = Den.objects.get(title='baby')
# a1 = Article(search_term=spider.search_terms)
# a1.dens.add(p1)
# busi = item.save(commit=False)
# p1 = Den.objects.get(title='pretty')
# busi.dens.add(p1)
# p1 = Den(title='pretty')
# a1 = Article(search_term=spider.search_terms)
# a1.dens.add(p1)
# p1 = Den(title='pretty')
# a1 = Article(search_term=spider.search_terms)
# a1.dens.add(p1)
spider.action_successful = True
spider.log("Item saved.", log.INFO)
except IntegrityError, e:
spider.log(str(e), log.ERROR)
raise DropItem("Missing attribute.")
def test_double_standard_id_field(self):
checker_rt = SchedulerRuntime()
checker_rt.save()
event = Event(title=u'Event 1', event_website=self.event_website,
description=u'Event 1 description',
url=u'http://localhost:8010/static/site_generic/event5.html',
checker_runtime=checker_rt)
event.save()
event = Event(title=u'Event 2', event_website=self.event_website,
description=u'Event 1 description',
url=u'http://localhost:8010/static/site_generic/event6.html',
checker_runtime=checker_rt)
event.save()
event = Event(title=u'Event 1', event_website=self.event_website,
description=u'Event 2 description',
url=u'http://localhost:8010/static/site_generic/event7.html',
checker_runtime=checker_rt)
event.save()
self.soa_url.id_field = False
self.soa_url.save()
self.soa_title.id_field = True
self.soa_title.save()
self.soa_desc.id_field = True
self.soa_desc.save()
self.run_event_spider(1)
self.assertEqual(len(Event.objects.all()), 6)
self.assertEqual(Event.objects.filter(description='Event 1 description').count(), 2)
def process_item(self, item, spider):
if spider.conf['DO_ACTION']: # Necessary since DDS v.0.9+
try:
item['races_website'] = spider.ref_object
checker_rt = SchedulerRuntime(runtime_type='C')
checker_rt.save()
item['checker_runtime'] = checker_rt
item['date'] = self.process_date(item['date'], spider)
item['city'] = self.process_city(item['city'], spider)
item['province'] = self.process_province(item['province'], spider)
item.save()
spider.action_successful = True
spider.log("Item saved.", logging.INFO)
except IntegrityError as e:
spider.log(str(e), logging.ERROR)
spider.log(str(item._errors), logging.ERROR)
raise DropItem("Missing attribute.")
else:
if not item.is_valid():
spider.log(str(item._errors), logging.ERROR)
raise DropItem("Missing attribute.")
return item
def process_item(self, item, spider):
try:
checker_rt = SchedulerRuntime(runtime_type='C')
checker_rt.save()
item['checker_runtime'] = checker_rt
item['source'] = spider.ref_object
try:
item_model = item_to_model(item)
except TypeError:
return item
model, created = get_or_create(item_model)
update_model(model, item_model)
if created:
spider.log('==' + model.name + '== created.', log.INFO)
else:
spider.log('==' + model.name + '== updated.', log.INFO)
spider.action_successful = True
except IntegrityError, e:
spider.log(str(e), log.ERROR)
raise DropItem("Missing attribute.")
def process_item(self, item, spider):
if spider.conf['DO_ACTION']: # Necessary since DDS v.0.9+
try:
item['source'] = spider.ref_object
checker_rt = SchedulerRuntime(runtime_type='C')
checker_rt.save()
item['checker_runtime'] = checker_rt
item.save()
spider.action_successful = True
dds_id_str = str(item._dds_item_page) + '-' + str(
item._dds_item_id)
spider.struct_log(
"{cs}Item {id} saved to Django DB.{ce}".format(
id=dds_id_str,
cs=spider.bcolors['OK'],
ce=spider.bcolors['ENDC']))
except IntegrityError as e:
spider.log(str(e), logging.ERROR)
spider.log(str(item._errors), logging.ERROR)
raise DropItem("Missing attribute.")
else:
if not item.is_valid():
spider.log(str(item._errors), logging.ERROR)
raise DropItem("Missing attribute.")
return item
def process_item(self, item, spider):
if isinstance(spider,ProductSpider):
#spider.log("spider: " + spider.name)
spider.log("item time is: " + item['time'])
item['time']=process_date(item['time'])
# to do:
# drop item if price is null
# drop item if time > no
try:
#if (item == ArticleItem):
#item['news_website'] = spider.ref_object
#else:
item['source'] = spider.ref_object
checker_rt = SchedulerRuntime(runtime_type='C')
checker_rt.save()
item['checker_runtime'] = checker_rt
item.save()
spider.action_successful = True
spider.log("Item saved.", log.INFO)
except IntegrityError, e:
spider.log(str(e), log.ERROR)
raise DropItem("Missing attribute.")
def process_item(self, item, spider):
if spider.conf['DO_ACTION']:
try:
item['website'] = spider.ref_object
checker_rt = SchedulerRuntime(runtime_type='C')
checker_rt.save()
item['checker_runtime'] = checker_rt
item.save()
spider.action_successful = True
spider.log("Item saved.", logging.INFO)
except IntegrityError as e:
spider.log(str(e), logging.ERROR)
spider.log(str(item._errors), logging.ERROR)
raise DropItem("Missing attribute.")
else:
if not item.is_valid():
spider.log(str(item._errors), logging.ERROR)
raise DropItem("Missing attribute.")
return item
def process_item(self, item, spider):
if spider.conf['DO_ACTION']: # Necessary since DDS v.0.9+
try:
item['news_website'] = spider.ref_object
if 'description' in item:
item['description'] = convert_Html_to_text_and_make_sumarization(item['description'])
if 'image' in item:
item['image'] = change_image_size(item['image'],spider.ref_object.name)
checker_rt = SchedulerRuntime(runtime_type='C')
checker_rt.save()
item['checker_runtime'] = checker_rt
item.save()
spider.action_successful = True
dds_id_str = str(item._dds_item_page) + '-' + str(item._dds_item_id)
spider.struct_log("{cs}Item {id} saved to Django DB.{ce}".format(
id=dds_id_str,
cs=spider.bcolors['OK'],
ce=spider.bcolors['ENDC']))
except IntegrityError as e:
spider.log(str(e), logging.ERROR)
spider.log(str(item._errors), logging.ERROR)
raise DropItem("Missing attribute.")
else:
if not item.is_valid():
spider.log(str(item._errors), logging.ERROR)
raise DropItem("Missing attribute.")
return item
def test_double(self):
checker_rt = SchedulerRuntime()
checker_rt.save()
event = Event(title=u'Event 1', url=u'http://localhost:8010/static/site_generic/event1.html',
checker_runtime=checker_rt)
event.save()
self.run_event_spider(1)
self.assertEqual(len(Event.objects.all()), 4)
self.assertEqual(len(Event.objects.filter(title='Event 1')), 1)
def add_listing_checker(listing): listing_source_cfg = ListingSourceScraperConfig.objects.get(pk=listing.listing_source_id) checker_rt = SchedulerRuntime(runtime_type='C', next_action_time=timezone.now() + timedelta(days=1)) checker_rt.save() checker_config = ListingCheckerConfig(listing=listing, checker_runtime=checker_rt, scraper=listing_source_cfg.scraper) checker_config.save() return checker_config
def test_detail_page_url_id_field(self):
checker_rt = SchedulerRuntime()
checker_rt.save()
event = Event(title=u'Event 1', event_website=self.event_website,
url=u'http://localhost:8010/static/site_generic/event5.html',
checker_runtime=checker_rt)
event.save()
self.run_event_spider(1)
self.assertEqual(len(Event.objects.all()), 5)
self.assertEqual(Event.objects.filter(title='Event 1').count(), 2)
def test_double(self):
checker_rt = SchedulerRuntime()
checker_rt.save()
event = Event(title=u'Event 1', event_website=self.event_website,
url=u'http://localhost:8010/static/site_generic/event1.html',
checker_runtime=checker_rt)
event.save()
self.run_event_spider(1)
self.assertEqual(len(Event.objects.all()), 4)
self.assertEqual(len(Event.objects.filter(title='Event 1')), 1)
def setUp(self):
super(CheckerRunTest, self).setUp()
self.scraper.checker_x_path = u'//div[@class="event_not_found"]/div/text()'
self.scraper.checker_x_path_result = u'Event was deleted!'
self.scraper.save()
scheduler_rt = SchedulerRuntime()
scheduler_rt.save()
self.event = Event(title='Event 1', event_website=self.event_website,
description='Event 1 description',
url='http://localhost:8010/static/site_for_checker/event1.html',
checker_runtime=scheduler_rt)
self.event.save()
def process_item(self, item, spider):
try:
item['news_website'] = spider.ref_object
checker_rt = SchedulerRuntime(runtime_type='C')
checker_rt.save()
item['checker_runtime'] = checker_rt
item.save()
spider.action_successful = True
spider.log("Item saved.", log.INFO)
except IntegrityError, e:
spider.log(str(e), log.ERROR)
raise DropItem("Missing attribute.")
def process_item(self, item, spider):
try:
item['news_website'] = spider.ref_object
checker_rt = SchedulerRuntime(runtime_type='C')
checker_rt.save()
item['checker_runtime'] = checker_rt
item.save()
spider.action_successful = True
spider.log("Item saved.", log.INFO)
except IntegrityError, e:
spider.log(str(e), log.ERROR)
raise DropItem("Missing attribute.")
def process_item(self, item, spider):
if spider.conf['DO_ACTION']:
try:
item['job_website'] = spider.ref_object
checker_rt = SchedulerRuntime(runtime_type='C')
checker_rt.save()
item['checker_runtime'] = checker_rt
item.save()
spider.action_successful = True
spider.log("Items saved in the DB", logging.INFO)
except IntegrityError, e:
spider.log(str(e), logging.ERROR)
raise DropItem("missing attrib")
def test_standard_update_field_update(self):
checker_rt = SchedulerRuntime()
checker_rt.save()
event = Event(title=u'Event 1 - Old Title', event_website=self.event_website,
url=u'http://localhost:8010/static/site_generic/event1.html',
checker_runtime=checker_rt)
event.save()
self.soa_title.attr_type = 'T'
self.soa_title.save()
self.run_event_spider(1)
event_updated = Event.objects.get(pk=event.id)
self.assertEqual(event_updated.title, 'Event 1')
self.assertEqual(len(Event.objects.filter(title='Event 1 - Old Title')), 0)
def extraSetUpHTMLChecker(self):
self.scraper.checker_type = 'X'
self.scraper.checker_x_path = u'//div[@class="event_not_found"]/div/text()'
self.scraper.checker_x_path_result = u'Event not found!'
self.scraper.checker_ref_url = u'http://localhost:8010/static/site_with_json_content_type/event_not_found.html'
self.scraper.save()
scheduler_rt = SchedulerRuntime()
scheduler_rt.save()
self.event = Event(title='Event 1', event_website=self.event_website,
description='Event 1 description',
url='http://localhost:8010/static/site_with_json_content_type/event_not_found.html',
checker_runtime=scheduler_rt)
self.event.save()
def test_single_standard_id_field(self):
checker_rt = SchedulerRuntime()
checker_rt.save()
event = Event(title='Event 1', event_website=self.event_website,
url='http://localhost:8010/static/site_generic/event5.html',
checker_runtime=checker_rt)
event.save()
self.soa_url.id_field = False
self.soa_url.save()
self.soa_title.id_field = True
self.soa_title.save()
self.run_event_spider(1)
self.assertEqual(len(Event.objects.all()), 4)
self.assertEqual(Event.objects.filter(title='Event 1').count(), 1)
def setUpScraperJSChecker(self, path):
super(ScraperJSRunTest, self).setUp()
self.scraper.checker_type = 'X'
self.scraper.checker_x_path = u'//div[@class="event_not_found"]/div/text()'
self.scraper.checker_ref_url = u'%ssite_with_js/event_not_found.html' % path
self.scraper.save()
scheduler_rt = SchedulerRuntime()
scheduler_rt.save()
self.event = Event(title='Event 1', event_website=self.event_website,
description='Event 1 description',
url='%ssite_with_js/event_not_found.html' % path,
checker_runtime=scheduler_rt)
self.event.save()
def process_item(self, item, spider):
try:
# This name must match Article's source
item["source"] = spider.ref_object
checker_rt = SchedulerRuntime(runtime_type="C")
checker_rt.save()
item["checker_runtime"] = checker_rt
item.save()
spider.action_successful = True
spider.log("Item saved.", log.INFO)
except IntegrityError, e:
spider.log(str(e), log.ERROR)
raise DropItem("Missing attribute.")
def extraSetUpJSONChecker(self):
self.scraper.detail_page_content_type = 'J'
self.scraper.checker_type = 'X'
self.scraper.checker_x_path = u'event_not_found'
self.scraper.checker_x_path_result = u'Event not found!'
self.scraper.checker_ref_url = u'http://localhost:8010/static/site_with_json_content_type/event_not_found.json'
self.scraper.save()
scheduler_rt = SchedulerRuntime()
scheduler_rt.save()
self.event = Event(title='Event 1', event_website=self.event_website,
description='Event 1 description',
url='http://localhost:8010/static/site_with_json_content_type/event_not_found.json',
checker_runtime=scheduler_rt)
self.event.save()
def setUpScraperJSChecker(self, path):
super(ScraperJSRunTest, self).setUp()
self.scraper.checker_type = 'X'
self.scraper.checker_x_path = u'//div[@class="event_not_found"]/div/text()'
self.scraper.checker_ref_url = u'%ssite_with_js/event_not_found.html' % path
self.scraper.save()
scheduler_rt = SchedulerRuntime()
scheduler_rt.save()
self.event = Event(title='Event 1',
event_website=self.event_website,
description='Event 1 description',
url='%ssite_with_js/event_not_found.html' % path,
checker_runtime=scheduler_rt)
self.event.save()
def extraSetUpHTMLChecker(self):
self.scraper.checker_type = 'X'
self.scraper.checker_x_path = u'//div[@class="event_not_found"]/div/text()'
self.scraper.checker_x_path_result = u'Event not found!'
self.scraper.checker_ref_url = u'http://localhost:8010/static/site_with_json_content_type/event_not_found.html'
self.scraper.save()
scheduler_rt = SchedulerRuntime()
scheduler_rt.save()
self.event = Event(
title='Event 1',
event_website=self.event_website,
description='Event 1 description',
url=
'http://localhost:8010/static/site_with_json_content_type/event_not_found.html',
checker_runtime=scheduler_rt)
self.event.save()
def process_item(self, item, spider):
if spider.conf['DO_ACTION']: #Necessary since DDS v.0.9+
try:
print('HJ start saving')
item['post_site'] = spider.ref_object
checker_rt = SchedulerRuntime(runtime_type='C')
checker_rt.save()
item['checker_runtime'] = checker_rt
print(item['foo'])
if len(item['foo']) != 0:
selector = Selector(text=item['foo'])
options = selector.xpath('//option')
option_items = []
for option in options:
option_items.append(option.xpath("text()").extract())
print(option_items)
option_items.pop(0)
item['foo'] = option_items
# item['foo'] = json.dumps(option_items)
print(item['foo'])
item.save()
spider.action_successful = True
dds_id_str = str(item._dds_item_page) + '-' + str(item._dds_item_id)
spider.struct_log("{cs}Item {id} saved to Django DB.{ce}".format(
id=dds_id_str,
cs=spider.bcolors['OK'],
ce=spider.bcolors['ENDC']))
except IntegrityError as e:
print('HJ integrity error')
spider.log(str(e), logging.ERROR)
spider.log(str(item._errors), logging.ERROR)
raise DropItem("Missing attribute.")
else:
print('HJ not do_action')
if not item.is_valid():
spider.log(str(item._errors), logging.ERROR)
raise DropItem("Missing attribute.")
return item
def extraSetUpJSONChecker(self):
self.scraper.detail_page_content_type = 'J'
self.scraper.checker_type = 'X'
self.scraper.checker_x_path = u'event_not_found'
self.scraper.checker_x_path_result = u'Event not found!'
self.scraper.checker_ref_url = u'http://localhost:8010/static/site_with_json_content_type/event_not_found.json'
self.scraper.save()
scheduler_rt = SchedulerRuntime()
scheduler_rt.save()
self.event = Event(
title='Event 1',
event_website=self.event_website,
description='Event 1 description',
url=
'http://localhost:8010/static/site_with_json_content_type/event_not_found.json',
checker_runtime=scheduler_rt)
self.event.save()
def setUp(self):
super(CheckerRunTest, self).setUp()
self.scraper.checker_type = 'X'
self.scraper.checker_x_path = u'//div[@class="event_not_found"]/div/text()'
self.scraper.checker_x_path_result = u'Event was deleted!'
self.scraper.checker_ref_url = u'http://localhost:8010/static/site_for_checker/event_not_found.html'
self.scraper.save()
scheduler_rt = SchedulerRuntime()
scheduler_rt.save()
self.event = Event(
title='Event 1',
event_website=self.event_website,
description='Event 1 description',
url='http://localhost:8010/static/site_for_checker/event1.html',
checker_runtime=scheduler_rt)
self.event.save()
def setUp(self):
super(CheckerRunTest, self).setUp()
self.scraper.checker_type = "X"
self.scraper.checker_x_path = u'//div[@class="event_not_found"]/div/text()'
self.scraper.checker_x_path_result = u"Event was deleted!"
self.scraper.checker_ref_url = u"http://localhost:8010/static/site_for_checker/event_not_found.html"
self.scraper.save()
scheduler_rt = SchedulerRuntime()
scheduler_rt.save()
self.event = Event(
title="Event 1",
event_website=self.event_website,
description="Event 1 description",
url="http://localhost:8010/static/site_for_checker/event1.html",
checker_runtime=scheduler_rt,
)
self.event.save()
def process_item(self, item, spider):
try:
if isinstance(spider.ref_object, LoanScraper):
item["loan_scraper"] = spider.ref_object
elif isinstance(spider.ref_object, InsuranceWebsite):
item["insurance_website"] = spider.ref_object
else:
item["news_website"] = spider.ref_object
checker_rt = SchedulerRuntime(runtime_type="C")
checker_rt.save()
item["checker_runtime"] = checker_rt
item.save()
spider.action_successful = True
spider.log("Item saved.", log.INFO)
except IntegrityError, e:
spider.log(str(e), log.ERROR)
raise DropItem("Missing attribute.")
def extraSetUpHTMLChecker(self):
self.checker = Checker()
self.checker.scraped_obj_attr = self.soa_url
self.checker.scraper = self.scraper
self.checker.checker_type = "X"
self.checker.checker_x_path = '//div[@class="event_not_found"]/div/text()'
self.checker.checker_x_path_result = "Event not found!"
self.checker.checker_ref_url = "http://localhost:8010/static/site_with_json_content_type/event_not_found.html"
self.checker.save()
scheduler_rt = SchedulerRuntime()
scheduler_rt.save()
self.event = Event(
title="Event 1",
event_website=self.event_website,
description="Event 1 description",
url="http://localhost:8010/static/site_with_json_content_type/event_not_found.html",
checker_runtime=scheduler_rt,
)
self.event.save()
def process_item(self, item, spider):
if spider.conf['DO_ACTION']:
try:
item['news_website'] = spider.ref_object
checker_rt = SchedulerRuntime(runtime_type='C')
checker_rt.save()
item['checker_runtime'] = checker_rt
item.save()
spider.action_successful = True
spider.struct_log("{cs}Item {id} saved to Django DB.{ce}".format(
id=item._dds_id_str,
cs=spider.bcolors['OK'],
ce=spider.bcolors['ENDC']))
except IntegrityError as e:
spider.log(str(e), logging.ERROR)
raise DropItem("Missing attribute.")
return item
def process_item(self, item, spider):
if spider.conf['DO_ACTION']:
try:
item['food_website'] = spider.ref_object
checker_rt = SchedulerRuntime(runtime_type='C')
checker_rt.save()
item['checker_runtime'] = checker_rt
item.save()
spider.action_successful = True
spider.struct_log(
"{cs}Item {id} saved to Django DB.{ce}".format(
id=item._dds_id_str,
cs=spider.bcolors['OK'],
ce=spider.bcolors['ENDC']))
except IntegrityError as e:
spider.log(str(e), logging.ERROR)
raise DropItem("Missing attribute.")
return item
def process_item(self, item, spider):
'''
this is the processing portion of the spider to the django ORM/Database. What this particular
portion does is that it gets the spider and based on the configuration it will save the
information in my DB. It follows the same rules and principles of the scrapy pipeline model. In
case there is an intgrity error, it will drop the items and give back and errot of missing attrib
'''
if spider.conf['DO_ACTION']:
try:
item['news_website'] = spider.ref_object
checker_rt = SchedulerRuntime(runtime_type='C')
checker_rt.save()
item['checker_runtime'] = checker_rt
item.save()
spider.action_successful = True
spider.log("Items saved in the DB", logging.INFO)
except IntegrityError, e:
spider.log(str(e), logging.ERROR)
raise DropItem("missing attrib")
def process_item(self, item, spider):
if spider.conf['DO_ACTION']: #Necessary since DDS v.0.9+
try:
item['source'] = spider.ref_object
checker_rt = SchedulerRuntime(runtime_type='C')
checker_rt.save()
item['checker_runtime'] = checker_rt
if 'started_at' in item:
item['started_at'] = item['started_at'] + '-01-01'
item['industy'], created = Industy.objects.get_or_create(name=item['industy'])
try:
item_model = item_to_model(item)
except TypeError:
return item
model, created = get_or_create(item_model)
model.tags_raw = ''
model.save();
tags = ast.literal_eval(item['tags_raw'].encode('utf-8'))
tag_objs = []
for tag in tags:
tag_name = tag['tag_name']
tag_obj, tag_created = Tag.objects.get_or_create(name=tag_name)
if tag:
tag_obj.save()
tag_objs.append(tag_obj)
if tag_objs:
model.tags.add(*tag_objs)
model.tags_raw = ','.join(t.name for t in tag_objs)
# 保存融资信息
invest_firm = ''
investments = ast.literal_eval(item['investment_raw'].encode('utf-8'))
for i in investments:
invest_date = '-'.join(str(i) for i in [i['invse_year'], i['invse_month'],i['invse_month']])
if i['invse_detail_money'] == 0:
invest_amount = i['invse_similar_money']['invse_similar_money_name'] + i['invse_currency']['invse_currency_name']
else:
invest_amount = str(i['invse_detail_money']) + i['invse_currency']['invse_currency_name']
if i['invse_rel_invst_name']:
invest_firm = i['invse_rel_invst_name']
else:
invest_firm = ' '.join([org['invst_name'] for org in i['invse_orags_list']])
invest_round = i['invse_round']['invse_round_name']
investment, investment_created = Investment.objects.get_or_create(invest_date = invest_date,
invest_firm = invest_firm,
invest_round = invest_round,
invest_amount = invest_amount,
invest_to = model)
investment.save()
model.investment_raw = invest_firm
model.save()
# backup
# save tags_soup
# tags_soup = Soup(item['tags_raw'], 'lxml')
# tags = []
# for tag_soup in select(tags_soup, 'a span'):
# tag = tag_soup.string
# tag_obj, tag_created = Tag.objects.get_or_create(name=tag)
# if tag:
# tag_obj.save()
# tags.append(tag_obj)
# if tags:
# model.tags.add(*tags)
# model.tags_raw = ','.join(t.name for t in tags)
#save investment
# soup = Soup(item['investment_raw'], 'lxml')
# invest_firm = ''
# for investment_soup in soup.find_all('tr'):
# invest_date = select(investment_soup, 'span.date')[0].string.replace('.', '-')
# invest_amount = select(investment_soup, 'span.finades a')[0].string
# tds = select(investment_soup, 'td')
# if tds[3]:
# invest_firm = ','.join(i.string for i in tds[3].find_all('a'))
# invest_round = select(investment_soup, 'span.round a')[0].string
# investment, investment_created = Investment.objects.get_or_create(invest_date = invest_date,
# invest_firm = invest_firm,
# invest_round = invest_round,
# invest_amount = invest_amount,
# invest_to = model)
# investment.save()
# model.investment_raw = invest_firm
if created:
spider.log('==' + model.name + '== created.', log.INFO)
else:
spider.log('==' + model.name + '== updated.', log.INFO)
spider.action_successful = True
except IntegrityError, e:
spider.log(str(e), logging.ERROR)
spider.log(str(item._errors), logging.ERROR)
raise DropItem("Missing attribute.")
