def test_Youtube(self):
filename = 'BaW_jenozKc.mp4'
params = self.parameters
fd = FileDownloader(params)
fd.add_info_extractor(youtube_dl.InfoExtractors.YoutubeIE())
fd.download(['http://www.youtube.com/watch?v=BaW_jenozKc'])
self.assertTrue(os.path.exists(filename))
def test_XVideos(self):
filename = '939581.flv'
params = self.parameters
fd = FileDownloader(params)
fd.add_info_extractor(youtube_dl.InfoExtractors.XVideosIE())
fd.download(['http://www.xvideos.com/video939581/funny_porns_by_s_-1'])
self.assertTrue(os.path.exists(filename))
md5_for_file = _file_md5(filename)
self.assertEqual(md5_for_file, '1d0c835822f0a71a7bf011855db929d0')
def test_XNXX(self):
filename = '1135332.flv'
params = self.parameters
fd = FileDownloader(params)
fd.add_info_extractor(youtube_dl.InfoExtractors.XNXXIE())
fd.download(['http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_'])
self.assertTrue(os.path.exists(filename))
md5_for_file = _file_md5(filename)
self.assertEqual(md5_for_file, '0831677e2b4761795f68d417e0b7b445')
def test_StanfordOpenClassroom(self):
filename = 'PracticalUnix_intro-environment.mp4'
params = self.parameters
fd = FileDownloader(params)
fd.add_info_extractor(youtube_dl.InfoExtractors.StanfordOpenClassroomIE())
fd.download(['http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100'])
self.assertTrue(os.path.exists(filename))
md5_for_file = _file_md5(filename)
self.assertEqual(md5_for_file, '544a9468546059d4e80d76265b0443b8')
def test_Soundcloud(self):
filename = '62986583.mp3'
params = self.parameters
fd = FileDownloader(params)
fd.add_info_extractor(youtube_dl.InfoExtractors.SoundcloudIE())
fd.download(['http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy'])
self.assertTrue(os.path.exists(filename))
md5_for_file = _file_md5(filename)
self.assertEqual(md5_for_file, 'ebef0a451b909710ed1d7787dddbf0d7')
def test_Vimeo(self):
filename = '14160053.mp4'
params = self.parameters
fd = FileDownloader(params)
fd.add_info_extractor(youtube_dl.InfoExtractors.VimeoIE())
fd.download(['http://vimeo.com/14160053'])
self.assertTrue(os.path.exists(filename))
md5_for_file = _file_md5(filename)
self.assertEqual(md5_for_file, '60540a4ec7cc378ec84b919c0aed5023')
def test_BlipTV(self):
filename = '5779306.m4v'
params = self.parameters
fd = FileDownloader(params)
fd.add_info_extractor(youtube_dl.InfoExtractors.BlipTVIE())
fd.download(['http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352'])
self.assertTrue(os.path.exists(filename))
md5_for_file = _file_md5(filename)
self.assertEqual(md5_for_file, 'b2d849efcf7ee18917e4b4d9ff37cafe')
def test_Dailymotion(self):
filename = 'x33vw9.mp4'
params = self.parameters
fd = FileDownloader(params)
fd.add_info_extractor(youtube_dl.InfoExtractors.DailymotionIE())
fd.download(['http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech'])
self.assertTrue(os.path.exists(filename))
md5_for_file = _file_md5(filename)
self.assertEqual(md5_for_file, '392c4b85a60a90dc4792da41ce3144eb')
def test_Youku(self):
filename = 'XNDgyMDQ2NTQw_part00.flv'
params = self.parameters
params["test"] = False
fd = FileDownloader(params)
fd.add_info_extractor(youtube_dl.InfoExtractors.YoukuIE())
fd.download(['http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html'])
self.assertTrue(os.path.exists(filename))
md5_for_file = _file_md5(filename)
self.assertEqual(md5_for_file, 'ffe3f2e435663dc2d1eea34faeff5b5b')
def test_template(self):
ie = getattr(youtube_dl.InfoExtractors, test_case['name'] + 'IE')
if not ie._WORKING:
print('Skipping: IE marked as not _WORKING')
return
if 'playlist' not in test_case and not test_case['file']:
print('Skipping: No output file specified')
return
if 'skip' in test_case:
print('Skipping: {0}'.format(test_case['skip']))
return
params = self.parameters.copy()
params.update(test_case.get('params', {}))
fd = FileDownloader(params)
fd.add_info_extractor(ie())
for ien in test_case.get('add_ie', []):
fd.add_info_extractor(getattr(youtube_dl.InfoExtractors, ien + 'IE')())
finished_hook_called = set()
def _hook(status):
if status['status'] == 'finished':
finished_hook_called.add(status['filename'])
fd.add_progress_hook(_hook)
test_cases = test_case.get('playlist', [test_case])
for tc in test_cases:
_try_rm(tc['file'])
_try_rm(tc['file'] + '.part')
_try_rm(tc['file'] + '.info.json')
try:
fd.download([test_case['url']])
for tc in test_cases:
if not test_case.get('params', {}).get('skip_download', False):
self.assertTrue(os.path.exists(tc['file']))
self.assertTrue(tc['file'] in finished_hook_called)
self.assertTrue(os.path.exists(tc['file'] + '.info.json'))
if 'md5' in tc:
md5_for_file = _file_md5(tc['file'])
self.assertEqual(md5_for_file, tc['md5'])
with io.open(tc['file'] + '.info.json', encoding='utf-8') as infof:
info_dict = json.load(infof)
for (info_field, value) in tc.get('info_dict', {}).items():
if value.startswith('md5:'):
md5_info_value = hashlib.md5(info_dict.get(info_field, '')).hexdigest()
self.assertEqual(value[3:], md5_info_value)
else:
self.assertEqual(value, info_dict.get(info_field))
finally:
for tc in test_cases:
_try_rm(tc['file'])
_try_rm(tc['file'] + '.part')
_try_rm(tc['file'] + '.info.json')
def test_template(self):
ie = getattr(youtube_dl.InfoExtractors, test_case["name"] + "IE")
if not ie._WORKING:
print("Skipping: IE marked as not _WORKING")
return
if "playlist" not in test_case and not test_case["file"]:
print("Skipping: No output file specified")
return
if "skip" in test_case:
print("Skipping: {0}".format(test_case["skip"]))
return
params = self.parameters.copy()
params.update(test_case.get("params", {}))
fd = FileDownloader(params)
fd.add_info_extractor(ie())
for ien in test_case.get("add_ie", []):
fd.add_info_extractor(getattr(youtube_dl.InfoExtractors, ien + "IE")())
finished_hook_called = set()
def _hook(status):
if status["status"] == "finished":
finished_hook_called.add(status["filename"])
fd.add_progress_hook(_hook)
test_cases = test_case.get("playlist", [test_case])
for tc in test_cases:
_try_rm(tc["file"])
_try_rm(tc["file"] + ".part")
_try_rm(tc["file"] + ".info.json")
try:
fd.download([test_case["url"]])
for tc in test_cases:
if not test_case.get("params", {}).get("skip_download", False):
self.assertTrue(os.path.exists(tc["file"]), msg="Missing file " + tc["file"])
self.assertTrue(tc["file"] in finished_hook_called)
self.assertTrue(os.path.exists(tc["file"] + ".info.json"))
if "md5" in tc:
md5_for_file = _file_md5(tc["file"])
self.assertEqual(md5_for_file, tc["md5"])
with io.open(tc["file"] + ".info.json", encoding="utf-8") as infof:
info_dict = json.load(infof)
for (info_field, value) in tc.get("info_dict", {}).items():
self.assertEqual(value, info_dict.get(info_field))
finally:
for tc in test_cases:
_try_rm(tc["file"])
_try_rm(tc["file"] + ".part")
_try_rm(tc["file"] + ".info.json")
def test_template(self):
ie = getattr(youtube_dl.InfoExtractors, test_case['name'] + 'IE')
if not ie._WORKING:
print('Skipping: IE marked as not _WORKING')
return
if not test_case['file']:
print('Skipping: No output file specified')
return
if 'skip' in test_case:
print('Skipping: {0}'.format(test_case['skip']))
return
params = dict(self.parameters) # Duplicate it locally
for p in test_case.get('params', {}):
params[p] = test_case['params'][p]
fd = FileDownloader(params)
fd.add_info_extractor(ie())
for ien in test_case.get('add_ie', []):
fd.add_info_extractor(getattr(youtube_dl.InfoExtractors, ien + 'IE')())
fd.download([test_case['url']])
self.assertTrue(os.path.exists(test_case['file']))
if 'md5' in test_case:
md5_for_file = _file_md5(test_case['file'])
self.assertEqual(md5_for_file, test_case['md5'])
info_dict = fd.processed_info_dicts[0]
for (info_field, value) in test_case.get('info_dict', {}).items():
if value.startswith('md5:'):
md5_info_value = hashlib.md5(info_dict.get(info_field, '')).hexdigest()
self.assertEqual(value[3:], md5_info_value)
else:
self.assertEqual(value, info_dict.get(info_field))
def test_Metacafe(self):
filename = '_aUehQsCQtM.flv'
params = self.parameters
fd = FileDownloader(params)
fd.add_info_extractor(youtube_dl.InfoExtractors.MetacafeIE())
fd.add_info_extractor(youtube_dl.InfoExtractors.YoutubeIE())
fd.download(['http://www.metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/'])
self.assertTrue(os.path.exists(filename))
def test_info_json(self):
ie = youtube_dl.extractor.YoutubeIE()
fd = FileDownloader(params)
fd.add_info_extractor(ie)
fd.download([TEST_ID])
self.assertTrue(os.path.exists(INFO_JSON_FILE))
with io.open(INFO_JSON_FILE, 'r', encoding='utf-8') as jsonf:
jd = json.load(jsonf)
self.assertEqual(jd['upload_date'], u'20121002')
self.assertEqual(jd['description'], EXPECTED_DESCRIPTION)
self.assertEqual(jd['id'], TEST_ID)
self.assertEqual(jd['extractor'], 'youtube')
self.assertEqual(jd['title'], u'''youtube-dl test video "'/\ä↭𝕐''')
self.assertEqual(jd['uploader'], 'Philipp Hagemeister')
self.assertTrue(os.path.exists(DESCRIPTION_FILE))
with io.open(DESCRIPTION_FILE, 'r', encoding='utf-8') as descf:
descr = descf.read()
self.assertEqual(descr, EXPECTED_DESCRIPTION)
def test_template(self):
ie = getattr(youtube_dl.InfoExtractors, test_case['name'] + 'IE')
if not ie._WORKING:
print('Skipping: IE marked as not _WORKING')
return
if not test_case['file']:
print('Skipping: No output file specified')
return
if 'skip' in test_case:
print('Skipping: {0}'.format(test_case['skip']))
return
params = dict(self.parameters) # Duplicate it locally
for p in test_case.get('params', {}):
params[p] = test_case['params'][p]
fd = FileDownloader(params)
fd.add_info_extractor(ie())
for ien in test_case.get('add_ie', []):
fd.add_info_extractor(getattr(youtube_dl.InfoExtractors, ien + 'IE')())
fd.download([test_case['url']])
self.assertTrue(os.path.exists(test_case['file']))
if 'md5' in test_case:
md5_for_file = _file_md5(test_case['file'])
self.assertEqual(md5_for_file, test_case['md5'])
def test_template(self):
ie = getattr(youtube_dl.InfoExtractors, test_case['name'] + 'IE')
if not ie._WORKING:
print('Skipping: IE marked as not _WORKING')
return
if 'playlist' not in test_case and not test_case['file']:
print('Skipping: No output file specified')
return
if 'skip' in test_case:
print('Skipping: {0}'.format(test_case['skip']))
return
params = self.parameters.copy()
params.update(test_case.get('params', {}))
fd = FileDownloader(params)
for ie in youtube_dl.InfoExtractors.gen_extractors():
fd.add_info_extractor(ie)
finished_hook_called = set()
def _hook(status):
if status['status'] == 'finished':
finished_hook_called.add(status['filename'])
fd.add_progress_hook(_hook)
test_cases = test_case.get('playlist', [test_case])
for tc in test_cases:
_try_rm(tc['file'])
_try_rm(tc['file'] + '.part')
_try_rm(tc['file'] + '.info.json')
try:
for retry in range(1, RETRIES + 1):
try:
fd.download([test_case['url']])
except (DownloadError, ExtractorError) as err:
if retry == RETRIES: raise
# Check if the exception is not a network related one
if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError):
raise
print('Retrying: {0} failed tries\n\n##########\n\n'.format(retry))
else:
break
for tc in test_cases:
if not test_case.get('params', {}).get('skip_download', False):
self.assertTrue(os.path.exists(tc['file']), msg='Missing file ' + tc['file'])
self.assertTrue(tc['file'] in finished_hook_called)
self.assertTrue(os.path.exists(tc['file'] + '.info.json'))
if 'md5' in tc:
md5_for_file = _file_md5(tc['file'])
self.assertEqual(md5_for_file, tc['md5'])
with io.open(tc['file'] + '.info.json', encoding='utf-8') as infof:
info_dict = json.load(infof)
for (info_field, value) in tc.get('info_dict', {}).items():
self.assertEqual(value, info_dict.get(info_field))
finally:
for tc in test_cases:
_try_rm(tc['file'])
_try_rm(tc['file'] + '.part')
_try_rm(tc['file'] + '.info.json')
def test_template(self):
ie = youtube_dl.InfoExtractors.get_info_extractor(test_case['name'])
if not ie._WORKING:
print('Skipping: IE marked as not _WORKING')
return
if 'playlist' not in test_case and not test_case['file']:
print('Skipping: No output file specified')
return
if 'skip' in test_case:
print('Skipping: {0}'.format(test_case['skip']))
return
params = self.parameters.copy()
params.update(test_case.get('params', {}))
fd = FileDownloader(params)
for ie in youtube_dl.InfoExtractors.gen_extractors():
fd.add_info_extractor(ie)
finished_hook_called = set()
def _hook(status):
if status['status'] == 'finished':
finished_hook_called.add(status['filename'])
fd.add_progress_hook(_hook)
test_cases = test_case.get('playlist', [test_case])
for tc in test_cases:
_try_rm(tc['file'])
_try_rm(tc['file'] + '.part')
_try_rm(tc['file'] + '.info.json')
try:
for retry in range(1, RETRIES + 1):
try:
fd.download([test_case['url']])
except (DownloadError, ExtractorError) as err:
if retry == RETRIES: raise
# Check if the exception is not a network related one
if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError):
raise
print('Retrying: {0} failed tries\n\n##########\n\n'.format(retry))
else:
break
for tc in test_cases:
if not test_case.get('params', {}).get('skip_download', False):
self.assertTrue(os.path.exists(tc['file']), msg='Missing file ' + tc['file'])
self.assertTrue(tc['file'] in finished_hook_called)
self.assertTrue(os.path.exists(tc['file'] + '.info.json'))
if 'md5' in tc:
md5_for_file = _file_md5(tc['file'])
self.assertEqual(md5_for_file, tc['md5'])
with io.open(tc['file'] + '.info.json', encoding='utf-8') as infof:
info_dict = json.load(infof)
for (info_field, value) in tc.get('info_dict', {}).items():
if isinstance(value, compat_str) and value.startswith('md5:'):
self.assertEqual(value, 'md5:' + md5(info_dict.get(info_field)))
else:
self.assertEqual(value, info_dict.get(info_field))
# If checkable fields are missing from the test case, print the info_dict
test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))
for key, value in info_dict.items()
if value and key in ('title', 'description', 'uploader', 'upload_date', 'uploader_id', 'location'))
if not all(key in tc.get('info_dict', {}).keys() for key in test_info_dict.keys()):
sys.stderr.write(u'\n"info_dict": ' + json.dumps(test_info_dict, ensure_ascii=False, indent=2) + u'\n')
# Check for the presence of mandatory fields
for key in ('id', 'url', 'title', 'ext'):
self.assertTrue(key in info_dict.keys() and info_dict[key])
finally:
for tc in test_cases:
_try_rm(tc['file'])
_try_rm(tc['file'] + '.part')
_try_rm(tc['file'] + '.info.json')
