def testParsingError(self):
url = "http://test.co.kr"
def loadHtml(self,url):
with open('parse_error.html') as f: return f.read()
Scraper.loadHtml = loadHtml
scraper = Scraper(url).load()
self.assertEquals ("no title", scraper.title)
thumbnailImages = scraper.makeThumbnails(scraper.extractImageUrls(scraper.soup, scraper.siteUrl))
self.assertEquals([], thumbnailImages)
def testEtomato(self):
url = "http://news.etomato.com/Home/ReadNews.aspx?no=201886"
scraper = Scraper(url)
def loadHtml(url):
with open('news_etomato.html') as f: return f.read()
scraper.loadHtml = loadHtml
self.assertEquals (url, scraper.url)
self.assertEquals ('http://news.etomato.com', scraper.siteUrl)
scraper.load()
expectedTitle = u'경제전문 멀티미디어 뉴스 - 뉴스 토마토 -'
self.assertEquals (expectedTitle, scraper.title)
thumbnailImages = scraper.makeThumbnails(scraper.extractImageUrls(scraper.soup, scraper.siteUrl))
self.assertTrue (thumbnailImages is not None)
