From 27fe903c511691c078942bef5ee9a05a43b15c8f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jes=C3=BAs?= Date: Wed, 9 Jun 2021 17:54:27 -0500 Subject: initial --- test/test_InfoExtractor.py | 1132 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 1132 insertions(+) create mode 100644 test/test_InfoExtractor.py (limited to 'test/test_InfoExtractor.py') diff --git a/test/test_InfoExtractor.py b/test/test_InfoExtractor.py new file mode 100644 index 0000000..5029072 --- /dev/null +++ b/test/test_InfoExtractor.py @@ -0,0 +1,1132 @@ +#!/usr/bin/env python + +from __future__ import unicode_literals + +# Allow direct execution +import io +import os +import sys +import unittest +sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) + +from test.helper import FakeYDL, expect_dict, expect_value, http_server_port +from hypervideo_dl.compat import compat_etree_fromstring, compat_http_server +from hypervideo_dl.extractor.common import InfoExtractor +from hypervideo_dl.extractor import YoutubeIE, get_info_extractor +from hypervideo_dl.utils import encode_data_uri, strip_jsonp, ExtractorError, RegexNotFoundError +import threading + + +TEAPOT_RESPONSE_STATUS = 418 +TEAPOT_RESPONSE_BODY = "

418 I'm a teapot

" + + +class InfoExtractorTestRequestHandler(compat_http_server.BaseHTTPRequestHandler): + def log_message(self, format, *args): + pass + + def do_GET(self): + if self.path == '/teapot': + self.send_response(TEAPOT_RESPONSE_STATUS) + self.send_header('Content-Type', 'text/html; charset=utf-8') + self.end_headers() + self.wfile.write(TEAPOT_RESPONSE_BODY.encode()) + else: + assert False + + +class TestIE(InfoExtractor): + pass + + +class TestInfoExtractor(unittest.TestCase): + def setUp(self): + self.ie = TestIE(FakeYDL()) + + def test_ie_key(self): + self.assertEqual(get_info_extractor(YoutubeIE.ie_key()), YoutubeIE) + + def test_html_search_regex(self): + html = '

Watch this video

' + search = lambda re, *args: self.ie._html_search_regex(re, html, *args) + self.assertEqual(search(r'

(.+?)

', 'foo'), 'Watch this video') + + def test_opengraph(self): + ie = self.ie + html = ''' + + + + + + + + + ''' + self.assertEqual(ie._og_search_title(html), 'Foo') + self.assertEqual(ie._og_search_description(html), 'Some video\'s description ') + self.assertEqual(ie._og_search_thumbnail(html), 'http://domain.com/pic.jpg?key1=val1&key2=val2') + self.assertEqual(ie._og_search_video_url(html, default=None), None) + self.assertEqual(ie._og_search_property('foobar', html), 'Foo') + self.assertEqual(ie._og_search_property('test1', html), 'foo > < bar') + self.assertEqual(ie._og_search_property('test2', html), 'foo >//< bar') + self.assertEqual(ie._og_search_property('test3', html), 'Ill-formatted opengraph') + self.assertEqual(ie._og_search_property(('test0', 'test1'), html), 'foo > < bar') + self.assertRaises(RegexNotFoundError, ie._og_search_property, 'test0', html, None, fatal=True) + self.assertRaises(RegexNotFoundError, ie._og_search_property, ('test0', 'test00'), html, None, fatal=True) + + def test_html_search_meta(self): + ie = self.ie + html = ''' + + + + + + + ''' + + self.assertEqual(ie._html_search_meta('a', html), '1') + self.assertEqual(ie._html_search_meta('b', html), '2') + self.assertEqual(ie._html_search_meta('c', html), '3') + self.assertEqual(ie._html_search_meta('d', html), '4') + self.assertEqual(ie._html_search_meta('e', html), '5') + self.assertEqual(ie._html_search_meta('f', html), '6') + self.assertEqual(ie._html_search_meta(('a', 'b', 'c'), html), '1') + self.assertEqual(ie._html_search_meta(('c', 'b', 'a'), html), '3') + self.assertEqual(ie._html_search_meta(('z', 'x', 'c'), html), '3') + self.assertRaises(RegexNotFoundError, ie._html_search_meta, 'z', html, None, fatal=True) + self.assertRaises(RegexNotFoundError, ie._html_search_meta, ('z', 'x'), html, None, fatal=True) + + def test_search_json_ld_realworld(self): + # https://github.com/ytdl-org/youtube-dl/issues/23306 + expect_dict( + self, + self.ie._search_json_ld(r'''''', None), + { + 'title': '1 On 1 With Kleio', + 'description': 'Kleio Valentien', + 'url': 'https://gvideo.eporner.com/xN49A1cT3eB/xN49A1cT3eB.mp4', + 'timestamp': 1449347075, + 'duration': 743.0, + 'view_count': 1120958, + 'width': 1920, + 'height': 1080, + }) + + def test_download_json(self): + uri = encode_data_uri(b'{"foo": "blah"}', 'application/json') + self.assertEqual(self.ie._download_json(uri, None), {'foo': 'blah'}) + uri = encode_data_uri(b'callback({"foo": "blah"})', 'application/javascript') + self.assertEqual(self.ie._download_json(uri, None, transform_source=strip_jsonp), {'foo': 'blah'}) + uri = encode_data_uri(b'{"foo": invalid}', 'application/json') + self.assertRaises(ExtractorError, self.ie._download_json, uri, None) + self.assertEqual(self.ie._download_json(uri, None, fatal=False), None) + + def test_parse_html5_media_entries(self): + # inline video tag + expect_dict( + self, + self.ie._parse_html5_media_entries( + 'https://127.0.0.1/video.html', + r'