2012-12-12 05:15:21 -08:00
|
|
|
#!/usr/bin/env python
|
|
|
|
|
2013-10-14 17:00:53 -07:00
|
|
|
# Allow direct execution
|
|
|
|
import os
|
|
|
|
import sys
|
|
|
|
import unittest
|
|
|
|
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
|
|
|
|
2013-10-28 15:03:26 -07:00
|
|
|
from test.helper import (
|
|
|
|
get_params,
|
2014-03-17 06:30:13 -07:00
|
|
|
gettestcases,
|
2014-03-23 07:52:21 -07:00
|
|
|
expect_info_dict,
|
|
|
|
try_rm,
|
|
|
|
report_warning,
|
2013-10-28 15:03:26 -07:00
|
|
|
)
|
2013-10-14 17:00:53 -07:00
|
|
|
|
|
|
|
|
2012-09-28 06:34:56 -07:00
|
|
|
import hashlib
|
2012-12-12 05:15:21 -08:00
|
|
|
import io
|
2012-10-15 04:01:36 -07:00
|
|
|
import json
|
2012-12-20 07:30:55 -08:00
|
|
|
import socket
|
2012-11-28 06:09:56 -08:00
|
|
|
|
2013-06-18 13:14:21 -07:00
|
|
|
import youtube_dl.YoutubeDL
|
2013-10-14 17:00:53 -07:00
|
|
|
from youtube_dl.utils import (
|
2014-02-05 19:19:55 -08:00
|
|
|
compat_http_client,
|
2013-10-14 17:00:53 -07:00
|
|
|
compat_urllib_error,
|
2013-10-28 16:07:16 -07:00
|
|
|
compat_HTTPError,
|
2013-10-14 17:00:53 -07:00
|
|
|
DownloadError,
|
|
|
|
ExtractorError,
|
|
|
|
UnavailableVideoError,
|
|
|
|
)
|
2013-11-03 10:14:53 -08:00
|
|
|
from youtube_dl.extractor import get_info_extractor
|
2012-12-12 05:15:21 -08:00
|
|
|
|
2013-03-09 01:05:43 -08:00
|
|
|
RETRIES = 3
|
|
|
|
|
2013-06-18 13:14:21 -07:00
|
|
|
class YoutubeDL(youtube_dl.YoutubeDL):
|
2012-12-12 05:15:21 -08:00
|
|
|
def __init__(self, *args, **kwargs):
|
|
|
|
self.to_stderr = self.to_screen
|
2012-12-20 05:14:43 -08:00
|
|
|
self.processed_info_dicts = []
|
2013-06-18 13:14:21 -07:00
|
|
|
super(YoutubeDL, self).__init__(*args, **kwargs)
|
2013-06-06 06:07:05 -07:00
|
|
|
def report_warning(self, message):
|
2013-06-07 02:19:27 -07:00
|
|
|
# Don't accept warnings during tests
|
|
|
|
raise ExtractorError(message)
|
2012-12-20 05:14:43 -08:00
|
|
|
def process_info(self, info_dict):
|
|
|
|
self.processed_info_dicts.append(info_dict)
|
2013-06-18 13:14:21 -07:00
|
|
|
return super(YoutubeDL, self).process_info(info_dict)
|
2012-12-11 18:55:06 -08:00
|
|
|
|
2012-12-12 05:15:21 -08:00
|
|
|
def _file_md5(fn):
|
|
|
|
with open(fn, 'rb') as f:
|
|
|
|
return hashlib.md5(f.read()).hexdigest()
|
|
|
|
|
2014-03-17 06:30:13 -07:00
|
|
|
defs = gettestcases()
|
2013-06-27 09:28:45 -07:00
|
|
|
|
2012-12-20 05:14:43 -08:00
|
|
|
|
2012-12-11 18:55:06 -08:00
|
|
|
class TestDownload(unittest.TestCase):
|
2013-04-11 09:38:43 -07:00
|
|
|
maxDiff = None
|
2012-12-12 05:15:21 -08:00
|
|
|
def setUp(self):
|
|
|
|
self.defs = defs
|
|
|
|
|
2013-01-01 10:07:01 -08:00
|
|
|
### Dynamically generate tests
|
2012-12-12 06:14:58 -08:00
|
|
|
def generator(test_case):
|
|
|
|
|
2012-12-11 18:55:06 -08:00
|
|
|
def test_template(self):
|
2013-06-23 13:53:42 -07:00
|
|
|
ie = youtube_dl.extractor.get_info_extractor(test_case['name'])
|
2013-11-03 10:14:53 -08:00
|
|
|
other_ies = [get_info_extractor(ie_key) for ie_key in test_case.get('add_ie', [])]
|
2014-08-21 02:52:07 -07:00
|
|
|
is_playlist = any(k.startswith('playlist') for k in test_case)
|
|
|
|
test_cases = test_case.get(
|
|
|
|
'playlist', [] if is_playlist else [test_case])
|
|
|
|
|
2013-06-28 02:20:00 -07:00
|
|
|
def print_skipping(reason):
|
|
|
|
print('Skipping %s: %s' % (test_case['name'], reason))
|
2013-11-03 10:14:53 -08:00
|
|
|
if not ie.working():
|
2013-06-28 02:20:00 -07:00
|
|
|
print_skipping('IE marked as not _WORKING')
|
2012-12-12 05:15:21 -08:00
|
|
|
return
|
2014-08-21 02:52:07 -07:00
|
|
|
|
|
|
|
for tc in test_cases:
|
|
|
|
info_dict = tc.get('info_dict', {})
|
|
|
|
if not tc.get('file') and not (info_dict.get('id') and info_dict.get('ext')):
|
2014-02-25 15:12:02 -08:00
|
|
|
raise Exception('Test definition incorrect. The output file cannot be known. Are both \'id\' and \'ext\' keys present?')
|
2014-08-21 02:52:07 -07:00
|
|
|
|
2012-12-12 05:15:21 -08:00
|
|
|
if 'skip' in test_case:
|
2013-06-28 02:20:00 -07:00
|
|
|
print_skipping(test_case['skip'])
|
2012-12-12 05:15:21 -08:00
|
|
|
return
|
2013-11-03 10:14:53 -08:00
|
|
|
for other_ie in other_ies:
|
|
|
|
if not other_ie.working():
|
|
|
|
print_skipping(u'test depends on %sIE, marked as not WORKING' % other_ie.ie_key())
|
|
|
|
return
|
2012-12-20 05:14:43 -08:00
|
|
|
|
2013-10-14 17:00:53 -07:00
|
|
|
params = get_params(test_case.get('params', {}))
|
2014-08-21 02:52:07 -07:00
|
|
|
if is_playlist and 'playlist' not in test_case:
|
|
|
|
params.setdefault('extract_flat', True)
|
|
|
|
params.setdefault('skip_download', True)
|
2012-12-20 05:14:43 -08:00
|
|
|
|
2013-06-18 13:14:21 -07:00
|
|
|
ydl = YoutubeDL(params)
|
2013-06-27 14:51:06 -07:00
|
|
|
ydl.add_default_info_extractors()
|
2013-01-12 11:34:50 -08:00
|
|
|
finished_hook_called = set()
|
|
|
|
def _hook(status):
|
|
|
|
if status['status'] == 'finished':
|
|
|
|
finished_hook_called.add(status['filename'])
|
2013-12-23 01:37:27 -08:00
|
|
|
ydl.add_progress_hook(_hook)
|
2013-01-01 10:30:29 -08:00
|
|
|
|
2013-10-28 14:01:37 -07:00
|
|
|
def get_tc_filename(tc):
|
|
|
|
return tc.get('file') or ydl.prepare_filename(tc.get('info_dict', {}))
|
|
|
|
|
|
|
|
def try_rm_tcs_files():
|
|
|
|
for tc in test_cases:
|
|
|
|
tc_filename = get_tc_filename(tc)
|
|
|
|
try_rm(tc_filename)
|
|
|
|
try_rm(tc_filename + '.part')
|
2013-11-19 21:34:48 -08:00
|
|
|
try_rm(os.path.splitext(tc_filename)[0] + '.info.json')
|
2013-10-28 14:01:37 -07:00
|
|
|
try_rm_tcs_files()
|
2013-01-01 10:30:29 -08:00
|
|
|
try:
|
2013-10-28 15:03:26 -07:00
|
|
|
try_num = 1
|
|
|
|
while True:
|
2013-03-09 01:05:43 -08:00
|
|
|
try:
|
2014-08-21 02:52:07 -07:00
|
|
|
# We're not using .download here sine that is just a shim
|
|
|
|
# for outside error handling, and returns the exit code
|
|
|
|
# instead of the result dict.
|
|
|
|
res_dict = ydl.extract_info(test_case['url'])
|
2013-03-09 01:05:43 -08:00
|
|
|
except (DownloadError, ExtractorError) as err:
|
|
|
|
# Check if the exception is not a network related one
|
2014-02-05 19:19:55 -08:00
|
|
|
if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError, compat_http_client.BadStatusLine) or (err.exc_info[0] == compat_HTTPError and err.exc_info[1].code == 503):
|
2013-03-09 01:05:43 -08:00
|
|
|
raise
|
|
|
|
|
2013-10-28 15:03:26 -07:00
|
|
|
if try_num == RETRIES:
|
|
|
|
report_warning(u'Failed due to network errors, skipping...')
|
|
|
|
return
|
|
|
|
|
|
|
|
print('Retrying: {0} failed tries\n\n##########\n\n'.format(try_num))
|
|
|
|
|
|
|
|
try_num += 1
|
2013-03-09 01:05:43 -08:00
|
|
|
else:
|
|
|
|
break
|
2013-01-01 10:30:29 -08:00
|
|
|
|
2014-08-21 02:52:07 -07:00
|
|
|
if is_playlist:
|
|
|
|
self.assertEqual(res_dict['_type'], 'playlist')
|
|
|
|
expect_info_dict(self, test_case.get('info_dict', {}), res_dict)
|
|
|
|
if 'playlist_mincount' in test_case:
|
|
|
|
self.assertGreaterEqual(
|
|
|
|
len(res_dict['entries']),
|
|
|
|
test_case['playlist_mincount'],
|
|
|
|
'Expected at least %d in playlist %s, but got only %d' % (
|
|
|
|
test_case['playlist_mincount'], test_case['url'],
|
|
|
|
len(res_dict['entries'])))
|
2014-08-25 08:02:52 -07:00
|
|
|
if 'playlist_count' in test_case:
|
|
|
|
self.assertEqual(
|
|
|
|
len(res_dict['entries']),
|
|
|
|
test_case['playlist_count'],
|
|
|
|
'Expected at %d in playlist %s, but got %d.')
|
2014-08-21 02:52:07 -07:00
|
|
|
|
2013-01-01 10:30:29 -08:00
|
|
|
for tc in test_cases:
|
2013-10-28 14:01:37 -07:00
|
|
|
tc_filename = get_tc_filename(tc)
|
2013-01-01 12:01:49 -08:00
|
|
|
if not test_case.get('params', {}).get('skip_download', False):
|
2013-10-28 14:01:37 -07:00
|
|
|
self.assertTrue(os.path.exists(tc_filename), msg='Missing file ' + tc_filename)
|
|
|
|
self.assertTrue(tc_filename in finished_hook_called)
|
2013-11-19 21:34:48 -08:00
|
|
|
info_json_fn = os.path.splitext(tc_filename)[0] + '.info.json'
|
|
|
|
self.assertTrue(os.path.exists(info_json_fn))
|
2013-01-01 10:30:29 -08:00
|
|
|
if 'md5' in tc:
|
2013-10-28 14:01:37 -07:00
|
|
|
md5_for_file = _file_md5(tc_filename)
|
2013-01-01 10:30:29 -08:00
|
|
|
self.assertEqual(md5_for_file, tc['md5'])
|
2013-11-19 21:34:48 -08:00
|
|
|
with io.open(info_json_fn, encoding='utf-8') as infof:
|
2013-01-01 10:30:29 -08:00
|
|
|
info_dict = json.load(infof)
|
2014-03-23 07:52:21 -07:00
|
|
|
|
|
|
|
expect_info_dict(self, tc.get('info_dict', {}), info_dict)
|
2013-01-01 10:30:29 -08:00
|
|
|
finally:
|
2013-10-28 14:01:37 -07:00
|
|
|
try_rm_tcs_files()
|
2012-12-12 05:15:21 -08:00
|
|
|
|
2012-12-11 18:55:06 -08:00
|
|
|
return test_template
|
2012-12-12 05:15:21 -08:00
|
|
|
|
2012-12-12 06:14:58 -08:00
|
|
|
### And add them to TestDownload
|
2013-06-25 05:38:00 -07:00
|
|
|
for n, test_case in enumerate(defs):
|
2012-12-12 06:14:58 -08:00
|
|
|
test_method = generator(test_case)
|
2013-06-27 10:13:11 -07:00
|
|
|
tname = 'test_' + str(test_case['name'])
|
|
|
|
i = 1
|
|
|
|
while hasattr(TestDownload, tname):
|
2013-06-27 10:43:43 -07:00
|
|
|
tname = 'test_' + str(test_case['name']) + '_' + str(i)
|
2013-06-27 10:13:11 -07:00
|
|
|
i += 1
|
|
|
|
test_method.__name__ = tname
|
2012-12-12 05:15:21 -08:00
|
|
|
setattr(TestDownload, test_method.__name__, test_method)
|
2012-12-12 06:14:58 -08:00
|
|
|
del test_method
|
2012-11-28 06:09:56 -08:00
|
|
|
|
|
|
|
|
|
|
|
if __name__ == '__main__':
|
|
|
|
unittest.main()
|