def crawl_detail(self, manga: Manga) -> None:
start_url = manga.url
response = requests.get(start_url)
if response.status_code == 200:
tree = html.fromstring(response.content)
for element in tree.xpath(self.re_chapter_path):
title = str(element.xpath('text()')[0]).strip().replace('\t', ' ')
url = urljoin(self.base_url, str(element.xpath('@href')[0]))
chapter = Chapter(manga, title)
chapter.url = url
manga.add_chapter(chapter)
else:
raise ConnectionError(_(F'Could not connect with {start_url} site, status code: {response.status_code}'))
def crawl_detail(self, manga: Manga) -> None:
start_url = manga.url
try:
with SeleniumDriver() as driver:
driver.get(start_url)
wait_for_page(driver, self.re_chapter_path)
content = driver.find_element_by_xpath('//*').get_attribute('outerHTML')
tree = html.fromstring(content)
# crawl for manga chapters
for element in tree.xpath(self.re_chapter_path):
title = str(element.xpath('text()')[0]).strip().replace('\t', ' ')
url = urljoin(self.base_url, str(element.xpath('@href')[0]))
chapter = Chapter(manga, title)
chapter.url = url
manga.add_chapter(chapter)
except Exception as e:
raise ConnectionError(_(F'Could not connect with {start_url} site, error message: {e}'))
def test_manga_1(self):
dummy_manga_site = MangaSite('test_site')
dummy_manga1 = Manga('test_manga', 'test_manga_url', dummy_manga_site)
self.assertTrue(dummy_manga1.title == 'test_manga')
dummy_manga1.downloaded = True
self.assertTrue(dummy_manga1.downloaded)
dummy_chapter1 = Chapter(dummy_manga1)
dummy_manga1.add_chapter(dummy_chapter1)
self.assertTrue(len(dummy_manga1.chapters) > 0)
dummy_manga1.clear_state()
self.assertFalse(dummy_manga1.downloaded)
self.assertTrue(len(dummy_manga1.chapters) == 0)
try:
dummy_manga1.get_download_path(os.getcwd())
except Exception as e:
self.assertIsInstance(e, AttributeError)
self.assertTrue("NoneType" in str(e))
dump = dummy_manga1.dump()
self.assertIsInstance(dump, bytes)
self.assertTrue(len(dump) > 0)