def setUp(self):
if os.path.exists(self.IMG_DIR):
shutil.rmtree(self.IMG_DIR)
os.mkdir(self.IMG_DIR)
settings.set('ITEM_PIPELINES',
self.dds_settings['ITEM_PIPELINES'],
priority='cmdline')
settings.set('SPLASH_URL',
self.dds_settings['SPLASH_URL'],
priority='cmdline')
settings.set('DUPEFILTER_CLASS',
self.dds_settings['DUPEFILTER_CLASS'],
priority='cmdline')
settings.set('DOWNLOADER_MIDDLEWARES',
self.dds_settings['DOWNLOADER_MIDDLEWARES'],
priority='cmdline')
settings.set('IMAGES_STORE',
self.dds_settings['IMAGES_STORE'],
priority='cmdline')
if 'IMAGES_THUMBS' in self.dds_settings:
settings.set('IMAGES_THUMBS',
self.dds_settings['IMAGES_THUMBS'],
priority='cmdline')
if 'DSCRAPER_IMAGES_STORE_FORMAT' in self.dds_settings:
settings.set('DSCRAPER_IMAGES_STORE_FORMAT',
self.dds_settings['DSCRAPER_IMAGES_STORE_FORMAT'],
priority='cmdline')
settings.set('COOKIES_DEBUG', True)
self.crawler = Crawler(settings)
self.crawler.signals.connect(reactor.stop,
signal=signals.spider_closed)
self.crawler.configure()
self.sc = ScrapedObjClass(name='Event')
self.sc.save()
self.soa_base = ScrapedObjAttr(name=u'base',
attr_type='B',
obj_class=self.sc)
self.soa_base.save()
self.soa_title = ScrapedObjAttr(name=u'title',
attr_type='S',
obj_class=self.sc)
self.soa_title.save()
self.soa_url = ScrapedObjAttr(name=u'url',
attr_type='U',
obj_class=self.sc,
id_field=True)
self.soa_url.save()
self.soa_desc = ScrapedObjAttr(name=u'description',
attr_type='S',
obj_class=self.sc)
self.soa_desc.save()
self.scraper = Scraper(
name=u'Event Scraper',
scraped_obj_class=self.sc,
status='A',
)
self.scraper.save()
self.se_base = ScraperElem(scraped_obj_attr=self.soa_base,
scraper=self.scraper,
x_path=u'//ul/li',
from_detail_page=False)
self.se_base.save()
self.se_title = ScraperElem(scraped_obj_attr=self.soa_title,
scraper=self.scraper,
x_path=u'a/text()',
from_detail_page=False)
self.se_title.save()
self.se_url = ScraperElem(scraped_obj_attr=self.soa_url,
scraper=self.scraper,
x_path=u'a/@href',
from_detail_page=False)
self.se_url.save()
self.se_desc = ScraperElem(
scraped_obj_attr=self.soa_desc,
scraper=self.scraper,
x_path=u'//div/div[@class="description"]/text()',
from_detail_page=True,
mandatory=False)
self.se_desc.save()
self.sched_rt = SchedulerRuntime()
self.sched_rt.save()
self.event_website = EventWebsite(
pk=1,
name=u'Event Website',
scraper=self.scraper,
url=os.path.join(self.SERVER_URL, 'site_generic/event_main.html'),
scraper_runtime=self.sched_rt,
)
self.event_website.save()
for name, signal in vars(signals).items():
if not name.startswith('_'):
dispatcher.connect(self.record_signal, signal)
def setUp(self):
self.sc = ScrapedObjClass(name='Event')
self.sc.save()
self.soa_base = ScrapedObjAttr(name=u'base',
attr_type='B',
obj_class=self.sc)
self.soa_base.save()
self.soa_title = ScrapedObjAttr(name=u'title',
attr_type='S',
obj_class=self.sc)
self.soa_title.save()
self.soa_url = ScrapedObjAttr(name=u'url',
attr_type='U',
obj_class=self.sc)
self.soa_url.save()
self.soa_desc = ScrapedObjAttr(name=u'description',
attr_type='S',
obj_class=self.sc)
self.soa_desc.save()
self.scraper = Scraper(
name=u'Event Scraper',
scraped_obj_class=self.sc,
status='A',
)
self.scraper.save()
self.se_base = ScraperElem(scraped_obj_attr=self.soa_base,
scraper=self.scraper,
x_path=u'//ul/li',
from_detail_page=False)
self.se_base.save()
self.se_title = ScraperElem(scraped_obj_attr=self.soa_title,
scraper=self.scraper,
x_path=u'a/text()',
from_detail_page=False)
self.se_title.save()
self.se_url = ScraperElem(scraped_obj_attr=self.soa_url,
scraper=self.scraper,
x_path=u'a/@href',
from_detail_page=False)
self.se_url.save()
self.se_desc = ScraperElem(
scraped_obj_attr=self.soa_desc,
scraper=self.scraper,
x_path=u'//div/div[@class="description"]/text()',
from_detail_page=True,
mandatory=False)
self.se_desc.save()
self.sched_rt = SchedulerRuntime()
self.sched_rt.save()
self.event_website = EventWebsite(
pk=1,
name=u'Event Website',
scraper=self.scraper,
url=os.path.join(self.SERVER_URL, 'site_generic/event_main.html'),
scraper_runtime=self.sched_rt,
)
self.event_website.save()
settings.overrides['ITEM_PIPELINES'] = [
'dynamic_scraper.pipelines.DjangoImagesPipeline',
'dynamic_scraper.pipelines.ValidationPipeline',
'scraper.scraper_test.DjangoWriterPipeline',
]
settings.overrides['IMAGES_STORE'] = os.path.join(
self.PROJECT_ROOT, 'imgs')
settings.overrides['IMAGES_THUMBS'] = {
'small': (170, 170),
}
self.crawler = CrawlerProcess(settings)
self.crawler.install()
self.crawler.configure()
for name, signal in vars(signals).items():
if not name.startswith('_'):
dispatcher.connect(self.record_signal, signal)
def setUp(self):
if os.path.exists(self.IMG_DIR):
shutil.rmtree(self.IMG_DIR)
os.mkdir(self.IMG_DIR)
settings.set('ITEM_PIPELINES',
self.dds_settings['ITEM_PIPELINES'],
priority='cmdline')
settings.set('SPLASH_URL',
self.dds_settings['SPLASH_URL'],
priority='cmdline')
settings.set('DUPEFILTER_CLASS',
self.dds_settings['DUPEFILTER_CLASS'],
priority='cmdline')
settings.set('DOWNLOADER_MIDDLEWARES',
self.dds_settings['DOWNLOADER_MIDDLEWARES'],
priority='cmdline')
settings.set('IMAGES_STORE',
self.dds_settings['IMAGES_STORE'],
priority='cmdline')
if 'IMAGES_THUMBS' in self.dds_settings:
settings.set('IMAGES_THUMBS',
self.dds_settings['IMAGES_THUMBS'],
priority='cmdline')
if 'DSCRAPER_IMAGES_STORE_FORMAT' in self.dds_settings:
settings.set('DSCRAPER_IMAGES_STORE_FORMAT',
self.dds_settings['DSCRAPER_IMAGES_STORE_FORMAT'],
priority='cmdline')
settings.set('COOKIES_DEBUG', True)
settings.set('LOG_LEVEL', 'DEBUG')
settings.set('LOG_ENABLED', False)
#self.crawler = Crawler(settings)
#self.crawler.signals.connect(reactor.stop, signal=signals.spider_closed)
#self.crawler.configure()
self.process = CrawlerProcess(settings)
self.sc = ScrapedObjClass(name='Event')
self.sc.save()
self.soa_base = ScrapedObjAttr(name='base',
attr_type='B',
obj_class=self.sc)
self.soa_base.save()
self.soa_title = ScrapedObjAttr(name='title',
attr_type='S',
obj_class=self.sc)
self.soa_title.save()
self.soa_url = ScrapedObjAttr(name='url',
attr_type='U',
obj_class=self.sc,
id_field=True)
self.soa_url.save()
self.soa_url2 = ScrapedObjAttr(name='url2',
attr_type='U',
obj_class=self.sc)
self.soa_url2.save()
self.soa_desc = ScrapedObjAttr(name='description',
attr_type='S',
obj_class=self.sc)
self.soa_desc.save()
self.soa_desc2 = ScrapedObjAttr(name='description2',
attr_type='S',
obj_class=self.sc)
self.soa_desc2.save()
self.soa_es_1 = ScrapedObjAttr(name='extra_standard_1',
attr_type='S',
obj_class=self.sc,
save_to_db=False)
self.soa_es_1.save()
self.scraper = Scraper(
name='Event Scraper',
scraped_obj_class=self.sc,
status='A',
)
self.scraper.save()
self.se_base = ScraperElem(scraped_obj_attr=self.soa_base,
scraper=self.scraper,
x_path='//ul/li',
request_page_type='MP')
self.se_base.save()
self.se_title = ScraperElem(scraped_obj_attr=self.soa_title,
scraper=self.scraper,
x_path='a/text()',
request_page_type='MP')
self.se_title.save()
self.se_url = ScraperElem(scraped_obj_attr=self.soa_url,
scraper=self.scraper,
x_path='a/@href',
request_page_type='MP')
self.se_url.save()
self.se_desc = ScraperElem(
scraped_obj_attr=self.soa_desc,
scraper=self.scraper,
x_path='//div/div[@class="description"]/text()',
request_page_type='DP1',
mandatory=False)
self.se_desc.save()
self.se_es_1 = ScraperElem(scraped_obj_attr=self.soa_es_1,
scraper=self.scraper,
x_path='a/text()',
request_page_type='MP')
self.se_es_1.save()
self.rpt_mp = RequestPageType(page_type='MP', scraper=self.scraper)
self.rpt_mp.save()
self.rpt_dp1 = RequestPageType(page_type='DP1',
scraper=self.scraper,
scraped_obj_attr=self.soa_url)
self.rpt_dp1.save()
self.sched_rt = SchedulerRuntime()
self.sched_rt.save()
self.event_website = EventWebsite(
pk=1,
name='Event Website',
scraper=self.scraper,
url=os.path.join(self.SERVER_URL, 'site_generic/event_main.html'),
scraper_runtime=self.sched_rt,
)
self.event_website.save()
for name, signal in list(vars(signals).items()):
if not name.startswith('_'):
dispatcher.connect(self.record_signal, signal)
