def test_convert_to_cbz_adds_all_files_to_cbz(cleanup_test_directories,
three_webpages_uri):
comic = Comic("test", three_webpages_uri, "//img/@src", "//a/@href")
comic.download()
comic.convert_to_cbz()
with ZipFile("{}.cbz".format(comic.name), mode="r") as cbz_file:
assert len(cbz_file.infolist()) == 2
def test_download_does_not_add_crawlers_in_main_process(
mocker, cleanup_test_directories, three_webpages_uri):
mocker.patch("webcomix.scrapy.crawler_worker.CrawlerWorker.start")
mock_add_to_crawl = mocker.patch("scrapy.crawler.Crawler.crawl")
comic = Comic("test", three_webpages_uri, "//img/@src", "//a/@href")
comic.download()
assert mock_add_to_crawl.call_count == 0
def test_download_will_not_run_splash_settings_if_not_javascript(mocker):
mocker.patch("os.path.isdir")
mock_crawler_worker = mocker.patch("webcomix.comic.CrawlerWorker")
comic = Comic(mocker.ANY, mocker.ANY, mocker.ANY, mocker.ANY, mocker.ANY)
comic.download()
settings = mock_crawler_worker.call_args_list[0][0][0]
assert all(setting not in settings.items()
for setting in SPLASH_SETTINGS.items())
def test_download_saves_the_files_with_correct_first_item(
cleanup_test_directories, three_webpages_uri):
comic = Comic("test",
three_webpages_uri,
"//img/@src",
"//a/@href",
start_page=10)
comic.download()
files = next(os.walk("test"))[2]
assert sorted(files) == ["10", "11"]
def test_download_runs_the_worker(mocker, cleanup_test_directories):
mock_crawler_running = mocker.patch(
"webcomix.scrapy.crawler_worker.CrawlerWorker.start")
comic = Comic(
"xkcd",
"http://xkcd.com/1/",
"//div[@id='comic']//img/@src",
"//a[@rel='next']/@href",
False,
)
comic.download()
assert mock_crawler_running.call_count == 1
def test_download_with_alt_text_saves_the_text(cleanup_test_directories,
three_webpages_alt_text_uri):
comic = Comic(
"test",
three_webpages_alt_text_uri,
"//img/@src",
"//a/@href",
alt_text="//img/@title",
)
comic.download()
path, dirs, files = next(os.walk("test"))
assert len(files) == 4
def test_download_saves_the_files(cleanup_test_directories,
three_webpages_uri):
comic = Comic("test", three_webpages_uri, "//img/@src", "//a/@href")
comic.download()
path, dirs, files = next(os.walk("test"))
assert len(files) == 2
