X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=test%2Ftest_InfoExtractor.py;h=f0aa8466b7fc7a24310e6719a78ca11d287b1976;hb=fca9baf0da9720bac25d160924204395930191fe;hp=7b31d5198b561f7e3725a15055439ca5f35b791b;hpb=1dd38dc0f40a7c3adbd9e346aa603d8ac566045a;p=youtube-dl
diff --git a/test/test_InfoExtractor.py b/test/test_InfoExtractor.py
index 7b31d5198..f0aa8466b 100644
--- a/test/test_InfoExtractor.py
+++ b/test/test_InfoExtractor.py
@@ -9,11 +9,30 @@ 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
-from youtube_dl.compat import compat_etree_fromstring
+from test.helper import FakeYDL, expect_dict, expect_value, http_server_port
+from youtube_dl.compat import compat_etree_fromstring, compat_http_server
from youtube_dl.extractor.common import InfoExtractor
from youtube_dl.extractor import YoutubeIE, get_info_extractor
from youtube_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):
@@ -42,6 +61,7 @@ class TestInfoExtractor(unittest.TestCase):
+
'''
self.assertEqual(ie._og_search_title(html), 'Foo')
self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
@@ -50,6 +70,7 @@ class TestInfoExtractor(unittest.TestCase):
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)
@@ -478,7 +499,64 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
'width': 1280,
'height': 720,
}]
- )
+ ),
+ (
+ # https://github.com/rg3/youtube-dl/issues/18923
+ # https://www.ted.com/talks/boris_hesser_a_grassroots_healthcare_revolution_in_africa
+ 'ted_18923',
+ 'http://hls.ted.com/talks/31241.m3u8',
+ [{
+ 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b',
+ 'format_id': '600k-Audio',
+ 'vcodec': 'none',
+ }, {
+ 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b',
+ 'format_id': '68',
+ 'vcodec': 'none',
+ }, {
+ 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/64k.m3u8?nobumpers=true&uniqueId=76011e2b',
+ 'format_id': '163',
+ 'acodec': 'none',
+ 'width': 320,
+ 'height': 180,
+ }, {
+ 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/180k.m3u8?nobumpers=true&uniqueId=76011e2b',
+ 'format_id': '481',
+ 'acodec': 'none',
+ 'width': 512,
+ 'height': 288,
+ }, {
+ 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/320k.m3u8?nobumpers=true&uniqueId=76011e2b',
+ 'format_id': '769',
+ 'acodec': 'none',
+ 'width': 512,
+ 'height': 288,
+ }, {
+ 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/450k.m3u8?nobumpers=true&uniqueId=76011e2b',
+ 'format_id': '984',
+ 'acodec': 'none',
+ 'width': 512,
+ 'height': 288,
+ }, {
+ 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/600k.m3u8?nobumpers=true&uniqueId=76011e2b',
+ 'format_id': '1255',
+ 'acodec': 'none',
+ 'width': 640,
+ 'height': 360,
+ }, {
+ 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/950k.m3u8?nobumpers=true&uniqueId=76011e2b',
+ 'format_id': '1693',
+ 'acodec': 'none',
+ 'width': 853,
+ 'height': 480,
+ }, {
+ 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/1500k.m3u8?nobumpers=true&uniqueId=76011e2b',
+ 'format_id': '2462',
+ 'acodec': 'none',
+ 'width': 1280,
+ 'height': 720,
+ }]
+ ),
]
for m3u8_file, m3u8_url, expected_formats in _TEST_CASES:
@@ -694,6 +772,74 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
self.ie._sort_formats(formats)
expect_value(self, formats, expected_formats, None)
+ def test_parse_xspf(self):
+ _TEST_CASES = [
+ (
+ 'foo_xspf',
+ 'https://example.org/src/foo_xspf.xspf',
+ [{
+ 'id': 'foo_xspf',
+ 'title': 'Pandemonium',
+ 'description': 'Visit http://bigbrother404.bandcamp.com',
+ 'duration': 202.416,
+ 'formats': [{
+ 'manifest_url': 'https://example.org/src/foo_xspf.xspf',
+ 'url': 'https://example.org/src/cd1/track%201.mp3',
+ }],
+ }, {
+ 'id': 'foo_xspf',
+ 'title': 'Final Cartridge (Nichico Twelve Remix)',
+ 'description': 'Visit http://bigbrother404.bandcamp.com',
+ 'duration': 255.857,
+ 'formats': [{
+ 'manifest_url': 'https://example.org/src/foo_xspf.xspf',
+ 'url': 'https://example.org/%E3%83%88%E3%83%A9%E3%83%83%E3%82%AF%E3%80%80%EF%BC%92.mp3',
+ }],
+ }, {
+ 'id': 'foo_xspf',
+ 'title': 'Rebuilding Nightingale',
+ 'description': 'Visit http://bigbrother404.bandcamp.com',
+ 'duration': 287.915,
+ 'formats': [{
+ 'manifest_url': 'https://example.org/src/foo_xspf.xspf',
+ 'url': 'https://example.org/src/track3.mp3',
+ }, {
+ 'manifest_url': 'https://example.org/src/foo_xspf.xspf',
+ 'url': 'https://example.com/track3.mp3',
+ }]
+ }]
+ ),
+ ]
+
+ for xspf_file, xspf_url, expected_entries in _TEST_CASES:
+ with io.open('./test/testdata/xspf/%s.xspf' % xspf_file,
+ mode='r', encoding='utf-8') as f:
+ entries = self.ie._parse_xspf(
+ compat_etree_fromstring(f.read().encode('utf-8')),
+ xspf_file, xspf_url=xspf_url, xspf_base_url=xspf_url)
+ expect_value(self, entries, expected_entries, None)
+ for i in range(len(entries)):
+ expect_dict(self, entries[i], expected_entries[i])
+
+ def test_response_with_expected_status_returns_content(self):
+ # Checks for mitigations against the effects of
+ # that affect Python 3.4.1+, which
+ # manifest as `_download_webpage`, `_download_xml`, `_download_json`,
+ # or the underlying `_download_webpage_handle` returning no content
+ # when a response matches `expected_status`.
+
+ httpd = compat_http_server.HTTPServer(
+ ('127.0.0.1', 0), InfoExtractorTestRequestHandler)
+ port = http_server_port(httpd)
+ server_thread = threading.Thread(target=httpd.serve_forever)
+ server_thread.daemon = True
+ server_thread.start()
+
+ (content, urlh) = self.ie._download_webpage_handle(
+ 'http://127.0.0.1:%d/teapot' % port, None,
+ expected_status=TEAPOT_RESPONSE_STATUS)
+ self.assertEqual(content, TEAPOT_RESPONSE_BODY)
+
if __name__ == '__main__':
unittest.main()