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 test_make_pdf2(self):
"""
Make pdf from pages in memory - simulated by manually added pages
"""
directory_name = os.path.dirname(__file__)
dummy_manga_site = MangaSite('test_site')
dummy_manga = Manga('test_manga', 'test_manga_url', dummy_manga_site)
dummy_chapter = Chapter(dummy_manga, 'test_chapter_title')
self.assertTrue(dummy_chapter.number_of_pages() == 0)
source_images_dir = os.path.join(directory_name, 'images')
test_tmp_dir = os.path.join(directory_name, RESULTS_DIRECTORY)
for file in os.listdir(source_images_dir):
file_path = os.path.join(source_images_dir, file)
if os.path.isfile(file_path):
with open(file_path, 'rb') as f:
dummy_chapter.add_page(f.read())
result, path_to_pdf = dummy_chapter.make_pdf(test_tmp_dir)
self.assertTrue(result)
self.assertTrue(dummy_chapter.number_of_pages() == 4)
self.assertTrue(os.path.isfile(path_to_pdf))
self.assertTrue(os.path.getsize(path_to_pdf) > 0)
os.unlink(path_to_pdf)
shutil.rmtree(test_tmp_dir, ignore_errors=True)
def test_make_pdf1(self):
"""
Make pdf from previously downloaded images - simulated on copied files
"""
directory_name = os.path.dirname(__file__)
dummy_manga_site = MangaSite('test_site')
dummy_manga = Manga('test_manga', 'test_manga_url', dummy_manga_site)
dummy_chapter = Chapter(dummy_manga, 'test_chapter_title')
self.assertTrue(dummy_chapter.number_of_pages() == 0)
source_images_dir = os.path.join(directory_name, 'images')
test_tmp_dir = os.path.join(directory_name, RESULTS_DIRECTORY)
images_dir = dummy_chapter.get_download_path(test_tmp_dir)
os.makedirs(images_dir, exist_ok=True)
for file in os.listdir(source_images_dir):
file_path = os.path.join(source_images_dir, file)
if os.path.isfile(file_path):
shutil.copy(file_path, images_dir)
result, path_to_pdf = dummy_chapter.make_pdf(test_tmp_dir)
self.assertTrue(result)
self.assertTrue(dummy_chapter.number_of_pages() == 0)
self.assertTrue(os.path.isfile(path_to_pdf))
self.assertTrue(os.path.getsize(path_to_pdf) > 0)
os.unlink(path_to_pdf)
shutil.rmtree(test_tmp_dir, ignore_errors=True)
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)
def test_manga_site_1(self):
dummy_manga_site1 = MangaSite()
self.assertIsNone(dummy_manga_site1.site_name)
dummy_manga_site2 = MangaSite('test_site')
dummy_manga1 = Manga('test_manga', 'test_manga_url', dummy_manga_site2)
dummy_manga_site2.add_manga(dummy_manga1)
self.assertTrue(len(dummy_manga_site2.mangas) > 0)
dummy_manga_site2.clear_state()
self.assertTrue(len(dummy_manga_site2.mangas) == 0)
dump = dummy_manga_site2.dump()
self.assertIsInstance(dump, bytes)
self.assertTrue(len(dump) > 0)
def crawl_index(self, manga_site: MangaSite) -> None:
start_url = urljoin(self.base_url, self.manga_index)
response = requests.get(start_url)
if response.status_code == 200:
manga_site.url = self.base_url
tree = html.fromstring(response.content)
for element in tree.xpath(self.re_index_path):
title = str(element.xpath('text()')[0]).strip().replace('\t', ' ')
url = urljoin(self.base_url, str(element.xpath('@href')[0]))
manga = Manga(title, url, manga_site)
manga_site.add_manga(manga)
else:
raise ConnectionError(
_(F'Could not connect with {start_url} site, status code: {response.status_code}'))
def test_chapter_1(self):
dummy_manga_site = MangaSite('test_site')
dummy_manga = Manga('test_manga', 'test_manga_url', dummy_manga_site)
dummy_chapter1 = Chapter(dummy_manga)
self.assertTrue(dummy_chapter1.number_of_pages() == 0)
self.assertIsNone(dummy_chapter1.title)
dummy_chapter2 = Chapter(dummy_manga, 'test_chapter_title')
self.assertTrue(dummy_chapter2.title == 'test_chapter_title')
dummy_chapter2.set_downloaded(True)
self.assertTrue(dummy_chapter2.downloaded)
self.assertTrue(dummy_chapter2.in_memory)
dummy_chapter2.clear_state()
self.assertFalse(dummy_chapter2.downloaded)
self.assertFalse(dummy_chapter2.in_memory)
try:
dummy_chapter2.get_download_path(os.getcwd())
except Exception as e:
self.assertIsInstance(e, AttributeError)
self.assertTrue("NoneType" in str(e))
dump = dummy_chapter2.dump()
self.assertIsInstance(dump, bytes)
self.assertTrue(len(dump) > 0)
def crawl_index(self, manga_site: MangaSite) -> None:
start_url = urljoin(self.base_url, self.manga_index)
try:
with SeleniumDriver() as driver:
collected_all_pages = False
driver.get(start_url)
wait_for_page(driver, self.re_index_path)
manga_site.url = self.base_url
while collected_all_pages is False:
content = driver.find_element_by_xpath('//*').get_attribute('outerHTML')
tree = html.fromstring(content)
for element in tree.xpath(self.re_index_path):
title = str(element.xpath('text()')[0]).strip().replace('\t', ' ')
url = urljoin(self.base_url, str(element.xpath('@href')[0]))
manga = Manga(title, url, manga_site)
manga_site.add_manga(manga)
for element2 in tree.xpath(self.re_index_next_page):
if 'Next'.lower() in element2.xpath('text()')[0].lower():
driver.get(urljoin(self.base_url, element2.xpath('@href')[0]))
break
else:
collected_all_pages = True
except Exception as e:
raise ConnectionError(_(F'Could not connect with {start_url} site, error message: {e}'))