def test_scrape_chapter_contents(self):
chapter = Chapter(
"Prologue",
"https://forums.spacebattles.com/threads/the-last-angel.244209/#post-9354450"
)
Scraper.scrape_chapter_contents(chapter)
self.assertIsNotNone(chapter.text)
def test_filter_chapters(self):
soup = self.tla_scraper.get_toc_as_soup()
all_links = self.tla_scraper.get_links_from_soup(soup)
all_chapters = Scraper.links_to_chapters(all_links)
filtered_chapters = self.tla_scraper.filter_chapters(all_chapters)
self.assertIsNotNone(filtered_chapters)
self.assertEqual(48, len(filtered_chapters))
def test_get_page_as_soup_not_null(self):
self.assertIsNotNone(Scraper.get_page_as_soup(self.GOOGLE_URL))
def test_links_to_chapters(self):
soup = Scraper.get_page_as_soup(self.GOOGLE_URL)
chapters = Scraper.get_links_from_soup(soup)
self.assertIsNotNone(chapters)
self.assertEqual(21, len(chapters))
def __init__(self, name, data, pk):
Scraper.__init__(self, name)
self.name = name
self.data = data
# Pk is unique identifier of object that will be updated
self.pk = pk
def __init__(self, name, data, **kwargs):
Scraper.__init__(self, name)
self.data = data