RESULT = ('.' + domain + '\n' in LIST or '\n' + domain + '\n' in LIST)
- if RESULT and ('info_dict' not in test or 'age_limit' not in test['info_dict'] or
- test['info_dict']['age_limit'] != 18):
+ if RESULT and ('info_dict' not in test or 'age_limit' not in test['info_dict']
+ or test['info_dict']['age_limit'] != 18):
print('\nPotential missing age_limit check: {0}'.format(test['name']))
- elif not RESULT and ('info_dict' in test and 'age_limit' in test['info_dict'] and
- test['info_dict']['age_limit'] == 18):
+ elif not RESULT and ('info_dict' in test and 'age_limit' in test['info_dict']
+ and test['info_dict']['age_limit'] == 18):
print('\nPotential false negative: {0}'.format(test['name']))
else:
[flake8]
exclude = youtube_dl/extractor/__init__.py,devscripts/buildserver.py,devscripts/lazy_load_template.py,devscripts/make_issue_template.py,setup.py,build,.git,venv
-ignore = E402,E501,E731,E741
+ignore = E402,E501,E731,E741,W503
def test_decrypt_text(self):
password = intlist_to_bytes(self.key).decode('utf-8')
encrypted = base64.b64encode(
- intlist_to_bytes(self.iv[:8]) +
- b'\x17\x15\x93\xab\x8d\x80V\xcdV\xe0\t\xcdo\xc2\xa5\xd8ksM\r\xe27N\xae'
+ intlist_to_bytes(self.iv[:8])
+ + b'\x17\x15\x93\xab\x8d\x80V\xcdV\xe0\t\xcdo\xc2\xa5\xd8ksM\r\xe27N\xae'
).decode('utf-8')
decrypted = (aes_decrypt_text(encrypted, password, 16))
self.assertEqual(decrypted, self.secret_msg)
password = intlist_to_bytes(self.key).decode('utf-8')
encrypted = base64.b64encode(
- intlist_to_bytes(self.iv[:8]) +
- b'\x0b\xe6\xa4\xd9z\x0e\xb8\xb9\xd0\xd4i_\x85\x1d\x99\x98_\xe5\x80\xe7.\xbf\xa5\x83'
+ intlist_to_bytes(self.iv[:8])
+ + b'\x0b\xe6\xa4\xd9z\x0e\xb8\xb9\xd0\xd4i_\x85\x1d\x99\x98_\xe5\x80\xe7.\xbf\xa5\x83'
).decode('utf-8')
decrypted = (aes_decrypt_text(encrypted, password, 32))
self.assertEqual(decrypted, self.secret_msg)
def test_func(self):
as_file = os.path.join(TEST_DIR, testfile)
swf_file = os.path.join(TEST_DIR, test_id + '.swf')
- if ((not os.path.exists(swf_file)) or
- os.path.getmtime(swf_file) < os.path.getmtime(as_file)):
+ if ((not os.path.exists(swf_file))
+ or os.path.getmtime(swf_file) < os.path.getmtime(as_file)):
# Recompile
try:
subprocess.check_call([
else:
raise
- if (sys.platform != 'win32' and
- sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968'] and
- not params.get('restrictfilenames', False)):
+ if (sys.platform != 'win32'
+ and sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968']
+ and not params.get('restrictfilenames', False)):
# Unicode filesystem API will throw errors (#1474, #13027)
self.report_warning(
'Assuming --restrict-filenames since file system encoding '
if re.match(r'^-[0-9A-Za-z_-]{10}$', a)]
if idxs:
correct_argv = (
- ['youtube-dl'] +
- [a for i, a in enumerate(argv) if i not in idxs] +
- ['--'] + [argv[i] for i in idxs]
+ ['youtube-dl']
+ + [a for i, a in enumerate(argv) if i not in idxs]
+ + ['--'] + [argv[i] for i in idxs]
)
self.report_warning(
'Long argument string detected. '
if result_type in ('url', 'url_transparent'):
ie_result['url'] = sanitize_url(ie_result['url'])
extract_flat = self.params.get('extract_flat', False)
- if ((extract_flat == 'in_playlist' and 'playlist' in extra_info) or
- extract_flat is True):
+ if ((extract_flat == 'in_playlist' and 'playlist' in extra_info)
+ or extract_flat is True):
if self.params.get('forcejson', False):
self.to_stdout(json.dumps(ie_result))
return ie_result
# https://github.com/ytdl-org/youtube-dl/issues/10083).
incomplete_formats = (
# All formats are video-only or
- all(f.get('vcodec') != 'none' and f.get('acodec') == 'none' for f in formats) or
+ all(f.get('vcodec') != 'none' and f.get('acodec') == 'none' for f in formats)
# all formats are audio-only
- all(f.get('vcodec') == 'none' and f.get('acodec') != 'none' for f in formats))
+ or all(f.get('vcodec') == 'none' and f.get('acodec') != 'none' for f in formats))
ctx = {
'formats': formats,
else:
assert fixup_policy in ('ignore', 'never')
- if (info_dict.get('requested_formats') is None and
- info_dict.get('container') == 'm4a_dash'):
+ if (info_dict.get('requested_formats') is None
+ and info_dict.get('container') == 'm4a_dash'):
if fixup_policy == 'warn':
self.report_warning(
'%s: writing DASH m4a. '
else:
assert fixup_policy in ('ignore', 'never')
- if (info_dict.get('protocol') == 'm3u8_native' or
- info_dict.get('protocol') == 'm3u8' and
- self.params.get('hls_prefer_native')):
+ if (info_dict.get('protocol') == 'm3u8_native'
+ or info_dict.get('protocol') == 'm3u8'
+ and self.params.get('hls_prefer_native')):
if fixup_policy == 'warn':
self.report_warning('%s: malformed AAC bitstream detected.' % (
info_dict['id']))
def download(self, url_list):
"""Download a given list of URLs."""
outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
- if (len(url_list) > 1 and
- outtmpl != '-' and
- '%' not in outtmpl and
- self.params.get('max_downloads') != 1):
+ if (len(url_list) > 1
+ and outtmpl != '-'
+ and '%' not in outtmpl
+ and self.params.get('max_downloads') != 1):
raise SameFileError(outtmpl)
for url in url_list:
if res:
res += ', '
res += '%s container' % fdict['container']
- if (fdict.get('vcodec') is not None and
- fdict.get('vcodec') != 'none'):
+ if (fdict.get('vcodec') is not None
+ and fdict.get('vcodec') != 'none'):
if res:
res += ', '
res += fdict['vcodec']
if opts.allsubtitles and not opts.writeautomaticsub:
opts.writesubtitles = True
- outtmpl = ((opts.outtmpl is not None and opts.outtmpl) or
- (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s') or
- (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s') or
- (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s') or
- (opts.usetitle and '%(title)s-%(id)s.%(ext)s') or
- (opts.useid and '%(id)s.%(ext)s') or
- (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s') or
- DEFAULT_OUTTMPL)
+ outtmpl = ((opts.outtmpl is not None and opts.outtmpl)
+ or (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s')
+ or (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s')
+ or (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s')
+ or (opts.usetitle and '%(title)s-%(id)s.%(ext)s')
+ or (opts.useid and '%(id)s.%(ext)s')
+ or (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s')
+ or DEFAULT_OUTTMPL)
if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
parser.error('Cannot download a video and extract audio into the same'
' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
try:
args = shlex.split('中文')
- assert (isinstance(args, list) and
- isinstance(args[0], compat_str) and
- args[0] == '中文')
+ assert (isinstance(args, list)
+ and isinstance(args[0], compat_str)
+ and args[0] == '中文')
compat_shlex_split = shlex.split
except (AssertionError, UnicodeEncodeError):
# Working around shlex issue with unicode strings on some python 2
"""
nooverwrites_and_exists = (
- self.params.get('nooverwrites', False) and
- os.path.exists(encodeFilename(filename))
+ self.params.get('nooverwrites', False)
+ and os.path.exists(encodeFilename(filename))
)
if not hasattr(filename, 'write'):
continuedl_and_exists = (
- self.params.get('continuedl', True) and
- os.path.isfile(encodeFilename(filename)) and
- not self.params.get('nopart', False)
+ self.params.get('continuedl', True)
+ and os.path.isfile(encodeFilename(filename))
+ and not self.params.get('nopart', False)
)
# Check file already present
def remove_encrypted_media(media):
- return list(filter(lambda e: 'drmAdditionalHeaderId' not in e.attrib and
- 'drmAdditionalHeaderSetId' not in e.attrib,
+ return list(filter(lambda e: 'drmAdditionalHeaderId' not in e.attrib
+ and 'drmAdditionalHeaderSetId' not in e.attrib,
media))
media = doc.findall(_add_ns('media'))
if not media:
self.report_error('No media found')
- for e in (doc.findall(_add_ns('drmAdditionalHeader')) +
- doc.findall(_add_ns('drmAdditionalHeaderSet'))):
+ for e in (doc.findall(_add_ns('drmAdditionalHeader'))
+ + doc.findall(_add_ns('drmAdditionalHeaderSet'))):
# If id attribute is missing it's valid for all media nodes
# without drmAdditionalHeaderId or drmAdditionalHeaderSetId attribute
if 'id' not in e.attrib:
frag_total_bytes = s.get('total_bytes') or 0
if not ctx['live']:
estimated_size = (
- (ctx['complete_frags_downloaded_bytes'] + frag_total_bytes) /
- (state['fragment_index'] + 1) * total_frags)
+ (ctx['complete_frags_downloaded_bytes'] + frag_total_bytes)
+ / (state['fragment_index'] + 1) * total_frags)
state['total_bytes_estimate'] = estimated_size
if s['status'] == 'finished':
return fd.real_download(filename, info_dict)
def is_ad_fragment_start(s):
- return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=ad' in s or
- s.startswith('#UPLYNK-SEGMENT') and s.endswith(',ad'))
+ return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=ad' in s
+ or s.startswith('#UPLYNK-SEGMENT') and s.endswith(',ad'))
def is_ad_fragment_end(s):
- return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=master' in s or
- s.startswith('#UPLYNK-SEGMENT') and s.endswith(',segment'))
+ return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=master' in s
+ or s.startswith('#UPLYNK-SEGMENT') and s.endswith(',segment'))
media_frags = 0
ad_frags = 0
is_test = self.params.get('test', False)
chunk_size = self._TEST_FILE_SIZE if is_test else (
- info_dict.get('downloader_options', {}).get('http_chunk_size') or
- self.params.get('http_chunk_size') or 0)
+ info_dict.get('downloader_options', {}).get('http_chunk_size')
+ or self.params.get('http_chunk_size') or 0)
ctx.open_mode = 'wb'
ctx.resume_len = 0
content_len = int_or_none(content_range_m.group(3))
accept_content_len = (
# Non-chunked download
- not ctx.chunk_size or
+ not ctx.chunk_size
# Chunked download and requested piece or
# its part is promised to be served
- content_range_end == range_end or
- content_len < range_end)
+ or content_range_end == range_end
+ or content_len < range_end)
if accept_content_len:
ctx.data_len = content_len
return
raise
else:
# Examine the reported length
- if (content_length is not None and
- (ctx.resume_len - 100 < int(content_length) < ctx.resume_len + 100)):
+ if (content_length is not None
+ and (ctx.resume_len - 100 < int(content_length) < ctx.resume_len + 100)):
# The file had already been fully downloaded.
# Explanation to the above condition: in issue #175 it was revealed that
# YouTube sometimes adds or removes a few bytes from the end of the file,
parsed_url = compat_urllib_parse_urlparse(url)
av_val = av_res + len(parsed_url.netloc)
confirm_url = (
- parsed_url.scheme + '://' + parsed_url.netloc +
- action + '?' +
- compat_urllib_parse_urlencode({
+ parsed_url.scheme + '://' + parsed_url.netloc
+ + action + '?'
+ + compat_urllib_parse_urlencode({
'jschl_vc': vc, 'jschl_answer': compat_str(av_val)}))
self._download_webpage(
confirm_url, video_id,
video_id = self._match_id(url)
display_id = video_id[:8]
- api_url = ('https://apib4.blinkx.com/api.php?action=play_video&' +
- 'video=%s' % video_id)
+ api_url = ('https://apib4.blinkx.com/api.php?action=play_video&'
+ + 'video=%s' % video_id)
data_json = self._download_webpage(api_url, display_id)
data = json.loads(data_json)['api']['results'][0]
duration = None
raise ExtractorError('An extractor error has occurred.', cause=e)
def __maybe_fake_ip_and_retry(self, countries):
- if (not self._downloader.params.get('geo_bypass_country', None) and
- self._GEO_BYPASS and
- self._downloader.params.get('geo_bypass', True) and
- not self._x_forwarded_for_ip and
- countries):
+ if (not self._downloader.params.get('geo_bypass_country', None)
+ and self._GEO_BYPASS
+ and self._downloader.params.get('geo_bypass', True)
+ and not self._x_forwarded_for_ip
+ and countries):
country_code = random.choice(countries)
self._x_forwarded_for_ip = GeoUtils.random_ipv4(country_code)
if self._x_forwarded_for_ip:
def __check_blocked(self, content):
first_block = content[:512]
- if ('<title>Access to this site is blocked</title>' in content and
- 'Websense' in first_block):
+ if ('<title>Access to this site is blocked</title>' in content
+ and 'Websense' in first_block):
msg = 'Access to this webpage has been blocked by Websense filtering software in your network.'
blocked_iframe = self._html_search_regex(
r'<iframe src="([^"]+)"', content,
if block_msg:
msg += ' (Message: "%s")' % block_msg.replace('\n', ' ')
raise ExtractorError(msg, expected=True)
- if ('<title>TTK :: Доступ к ресурсу ограничен</title>' in content and
- 'blocklist.rkn.gov.ru' in content):
+ if ('<title>TTK :: Доступ к ресурсу ограничен</title>' in content
+ and 'blocklist.rkn.gov.ru' in content):
raise ExtractorError(
'Access to this webpage has been blocked by decision of the Russian government. '
'Visit http://blocklist.rkn.gov.ru/ for a block reason.',
continue
else:
tbr = float_or_none(
- last_stream_inf.get('AVERAGE-BANDWIDTH') or
- last_stream_inf.get('BANDWIDTH'), scale=1000)
+ last_stream_inf.get('AVERAGE-BANDWIDTH')
+ or last_stream_inf.get('BANDWIDTH'), scale=1000)
format_id = []
if m3u8_id:
format_id.append(m3u8_id)
if str_or_none(s_attr.get(lbl))
]
width = int_or_none(s_attr.get('width'))
- height = (int_or_none(s_attr.get('height')) or
- int_or_none(s_attr.get('res')))
+ height = (int_or_none(s_attr.get('height'))
+ or int_or_none(s_attr.get('res')))
if not width or not height:
for lbl in labels:
resolution = parse_resolution(lbl)
return not any_restricted
def extract_subtitles(self, *args, **kwargs):
- if (self._downloader.params.get('writesubtitles', False) or
- self._downloader.params.get('listsubtitles')):
+ if (self._downloader.params.get('writesubtitles', False)
+ or self._downloader.params.get('listsubtitles')):
return self._get_subtitles(*args, **kwargs)
return {}
return ret
def extract_automatic_captions(self, *args, **kwargs):
- if (self._downloader.params.get('writeautomaticsub', False) or
- self._downloader.params.get('listsubtitles')):
+ if (self._downloader.params.get('writeautomaticsub', False)
+ or self._downloader.params.get('listsubtitles')):
return self._get_automatic_captions(*args, **kwargs)
return {}
raise NotImplementedError('This method must be implemented by subclasses')
def mark_watched(self, *args, **kwargs):
- if (self._downloader.params.get('mark_watched', False) and
- (self._get_login_info()[0] is not None or
- self._downloader.params.get('cookiefile') is not None)):
+ if (self._downloader.params.get('mark_watched', False)
+ and (self._get_login_info()[0] is not None
+ or self._downloader.params.get('cookiefile') is not None)):
self._mark_watched(*args, **kwargs)
def _mark_watched(self, *args, **kwargs):
sources_url = (try_get(
video_data,
(lambda x: x['plugins']['sources']['url'],
- lambda x: x['sources']['url']), compat_str) or
- 'http://www.dailymail.co.uk/api/player/%s/video-sources.json' % video_id)
+ lambda x: x['sources']['url']), compat_str)
+ or 'http://www.dailymail.co.uk/api/player/%s/video-sources.json' % video_id)
video_sources = self._download_json(sources_url, video_id)
body = video_sources.get('body')
endpoint = next(
server['endpoint']
for server in servers
- if url_or_none(server.get('endpoint')) and
- 'cloudfront' in server['endpoint'])
+ if url_or_none(server.get('endpoint'))
+ and 'cloudfront' in server['endpoint'])
else:
endpoint = 'rtmpe://s2pqqn4u96e4j8.cloudfront.net/cfx/st/'
title = info.get('titleRaw') or data['title']
description = info.get('descriptionRaw')
thumbnail = info.get('socialMediaImage') or data.get('image')
- duration = int_or_none(info.get('videoTotalSecondsDuration') or
- data.get('totalSecondsDuration'))
+ duration = int_or_none(info.get('videoTotalSecondsDuration')
+ or data.get('totalSecondsDuration'))
timestamp = unified_timestamp(info.get('publishDate'))
return {
chapter_number = None
index = lesson.get('index')
element_index = lesson.get('elementIndex')
- if (isinstance(index, int) and isinstance(element_index, int) and
- index < element_index):
+ if (isinstance(index, int) and isinstance(element_index, int)
+ and index < element_index):
chapter_number = element_index - index
chapter = (chapters[chapter_number - 1]
if chapter_number - 1 < len(chapters) else None)
return self.url_result(mobj.group('url'))
# Look for Ooyala videos
- mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
- re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
- re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
- re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
- re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
+ mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
+ or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
+ or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
+ or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
+ or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
if mobj is not None:
embed_token = self._search_regex(
r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
else:
formats.append({
'url': src,
- 'ext': (mimetype2ext(src_type) or
- ext if ext in KNOWN_EXTENSIONS else 'mp4'),
+ 'ext': (mimetype2ext(src_type)
+ or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
})
if formats:
self._sort_formats(formats)
'id': video_id,
'title': title,
'description': description,
- 'thumbnail': (xpath_text(doc, './/{http://rss.jwpcdn.com/}image') or
- self._og_search_thumbnail(webpage)),
+ 'thumbnail': (xpath_text(doc, './/{http://rss.jwpcdn.com/}image')
+ or self._og_search_thumbnail(webpage)),
'timestamp': parse_iso8601(
self._html_search_meta('date', webpage)),
'formats': formats,
title = video_meta.get('media_status')
alt_title = video_meta.get('media_title')
description = clean_html(
- video_meta.get('media_description') or
- video_meta.get('media_description_md'))
+ video_meta.get('media_description')
+ or video_meta.get('media_description_md'))
duration = float_or_none(video_meta.get('media_duration'))
uploader = video_meta.get('media_user_name')
views = int_or_none(video_meta.get('media_views'))
tags = [
t['text']
for t in tags_list
- if isinstance(t, dict) and t.get('text') and
- isinstance(t['text'], compat_str)]
+ if isinstance(t, dict) and t.get('text')
+ and isinstance(t['text'], compat_str)]
return {
'id': video_id,
title = (
self._html_search_meta(
- ('ed_title', 'search.ed_title'), webpage, default=None) or
- self._search_regex(
+ ('ed_title', 'search.ed_title'), webpage, default=None)
+ or self._search_regex(
r'data-favorite_title_(?:eng|chi)=(["\'])(?P<id>(?:(?!\1).)+)\1',
- webpage, 'title', default=None, group='url') or
- self._html_search_regex(
- r'<h1>([^<]+)</h1>', webpage, 'title', default=None) or
- self._og_search_title(webpage)
+ webpage, 'title', default=None, group='url')
+ or self._html_search_regex(
+ r'<h1>([^<]+)</h1>', webpage, 'title', default=None)
+ or self._og_search_title(webpage)
)
file_id = self._search_regex(
language=self._APP_LANGUAGE,
application_id=self._APP_PUBLICATION_ID)
- self._login_url = (modules['user']['resources']['login']['uri'] +
- '/format/json').format(session_id=self._session_id)
+ self._login_url = (modules['user']['resources']['login']['uri']
+ + '/format/json').format(session_id=self._session_id)
self._logout_url = modules['user']['resources']['logout']['uri']
formats = self._extract_bokecc_formats(webpage, video_id)
else:
formats = (
- self._extract_rtmp_video(webpage) +
- self._extract_http_video(webpage) +
- self._extract_http_audio(webpage, video_id))
+ self._extract_rtmp_video(webpage)
+ + self._extract_http_video(webpage)
+ + self._extract_http_audio(webpage, video_id))
self._sort_formats(formats)
self._sleep(5, video_id)
self._sort_formats(formats)
- title = (get_element_by_id('widget-videotitle', webpage) or
- clean_html(get_element_by_attribute('class', 'mod-play-tit', webpage)) or
- self._html_search_regex(r'<span[^>]+data-videochanged-title="word"[^>]*>([^<]+)</span>', webpage, 'title'))
+ title = (get_element_by_id('widget-videotitle', webpage)
+ or clean_html(get_element_by_attribute('class', 'mod-play-tit', webpage))
+ or self._html_search_regex(r'<span[^>]+data-videochanged-title="word"[^>]*>([^<]+)</span>', webpage, 'title'))
return {
'id': video_id,
return etree.SubElement(element, _add_ns(name))
production_id = (
- params.get('data-video-autoplay-id') or
- '%s#001' % (
- params.get('data-video-episode-id') or
- video_id.replace('a', '/')))
+ params.get('data-video-autoplay-id')
+ or '%s#001' % (
+ params.get('data-video-episode-id')
+ or video_id.replace('a', '/')))
req_env = etree.Element(_add_ns('soapenv:Envelope'))
_add_sub_element(req_env, 'soapenv:Header')
(?P<q2>['"])_?(?P<partner_id>(?:(?!(?P=q2)).)+)(?P=q2),.*?
(?P<q3>['"])entry_?[Ii]d(?P=q3)\s*:\s*
(?P<q4>['"])(?P<id>(?:(?!(?P=q4)).)+)(?P=q4)(?:,|\s*\})
- """, webpage) or
- re.search(
+ """, webpage)
+ or re.search(
r'''(?xs)
(?P<q1>["'])
(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com(?::\d+)?/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)(?:(?!(?P=q1)).)*
\[\s*(?P<q2_1>["'])entry_?[Ii]d(?P=q2_1)\s*\]\s*=\s*
)
(?P<q3>["'])(?P<id>(?:(?!(?P=q3)).)+)(?P=q3)
- ''', webpage) or
- re.search(
+ ''', webpage)
+ or re.search(
r'''(?xs)
<(?:iframe[^>]+src|meta[^>]+\bcontent)=(?P<q1>["'])
(?:https?:)?//(?:(?:www|cdnapi(?:sec)?)\.)?kaltura\.com/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)
webpage = self._download_webpage(url, video_id)
- title = (self._html_search_meta('title', webpage, default=None) or
- self._search_regex(r'<h1 class="title">([^<]+)</h1>', webpage, 'video title'))
+ title = (self._html_search_meta('title', webpage, default=None)
+ or self._search_regex(r'<h1 class="title">([^<]+)</h1>', webpage, 'video title'))
video_id = self._search_regex(
r'/config/video/(.+?)\.xml', webpage, 'video id')
video_url = (self._html_search_regex(
(r'setup\(\{\s*["\']file["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
r'fileurl\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1'),
- webpage, 'video URL', default=None, group='url') or
- 'http://cdn4.videos.motherlessmedia.com/videos/%s.mp4?fs=opencloud' % video_id)
+ webpage, 'video URL', default=None, group='url')
+ or 'http://cdn4.videos.motherlessmedia.com/videos/%s.mp4?fs=opencloud' % video_id)
age_limit = self._rta_search(webpage)
view_count = str_to_int(self._html_search_regex(
r'<strong>Views</strong>\s+([^<]+)<',
# '__title' does not contain extra words such as sub-site name, "Video" etc.
title = compat_urllib_parse_unquote_plus(
- self._search_regex(r"__title\s*=\s*'([^']+)'", webpage, 'title', default=None) or
- self._og_search_title(webpage))
+ self._search_regex(r"__title\s*=\s*'([^']+)'", webpage, 'title', default=None)
+ or self._og_search_title(webpage))
filename = self._search_regex(
r"(?:__)?filename\s*[:=]\s*'([^']+)'", webpage, 'video filename')
_URL_PATTERN = r'\{url: \'(.+)\'\}'
def _fetch_title(self, page):
- return (self._html_search_regex(r'<h1 id="h1">([^<>]+)</h1>', page, 'news title', default=None) or
- self._html_search_meta('description', page, 'news title'))
+ return (self._html_search_regex(r'<h1 id="h1">([^<>]+)</h1>', page, 'news title', default=None)
+ or self._html_search_meta('description', page, 'news title'))
def _fetch_thumbnail(self, page):
return self._html_search_regex(r"setInitialImage\(\'([^']+)'\)", page, 'video thumbnail', fatal=False)
video_detail = watch_api_data.get('videoDetail', {})
thumbnail = (
- get_video_info(['thumbnail_url', 'thumbnailURL']) or
- self._html_search_meta('image', webpage, 'thumbnail', default=None) or
- video_detail.get('thumbnail'))
+ get_video_info(['thumbnail_url', 'thumbnailURL'])
+ or self._html_search_meta('image', webpage, 'thumbnail', default=None)
+ or video_detail.get('thumbnail'))
description = get_video_info('description')
- timestamp = (parse_iso8601(get_video_info('first_retrieve')) or
- unified_timestamp(get_video_info('postedDateTime')))
+ timestamp = (parse_iso8601(get_video_info('first_retrieve'))
+ or unified_timestamp(get_video_info('postedDateTime')))
if not timestamp:
match = self._html_search_meta('datePublished', webpage, 'date published', default=None)
if match:
view_count = int_or_none(match.replace(',', ''))
view_count = view_count or video_detail.get('viewCount')
- comment_count = (int_or_none(get_video_info('comment_num')) or
- video_detail.get('commentCount') or
- try_get(api_data, lambda x: x['thread']['commentCount']))
+ comment_count = (int_or_none(get_video_info('comment_num'))
+ or video_detail.get('commentCount')
+ or try_get(api_data, lambda x: x['thread']['commentCount']))
if not comment_count:
match = self._html_search_regex(
r'>Comments: <strong[^>]*>([^<]+)</strong>',
comment_count = int_or_none(match.replace(',', ''))
duration = (parse_duration(
- get_video_info('length') or
- self._html_search_meta(
- 'video:duration', webpage, 'video duration', default=None)) or
- video_detail.get('length') or
- get_video_info('duration'))
+ get_video_info('length')
+ or self._html_search_meta(
+ 'video:duration', webpage, 'video duration', default=None))
+ or video_detail.get('length')
+ or get_video_info('duration'))
webpage_url = get_video_info('watch_url') or url
entries = []
conviva = data.get('convivaStatistics') or {}
- live = (data.get('mediaElementType') == 'Live' or
- data.get('isLive') is True or conviva.get('isLive'))
+ live = (data.get('mediaElementType') == 'Live'
+ or data.get('isLive') is True or conviva.get('isLive'))
def make_title(t):
return self._live_title(t) if live else t
title = metadata['title']
auth_data = self._download_json(
- self._AUTHORIZATION_URL_TEMPLATE % (pcode, embed_code) +
- compat_urllib_parse_urlencode({
+ self._AUTHORIZATION_URL_TEMPLATE % (pcode, embed_code)
+ + compat_urllib_parse_urlencode({
'domain': domain,
'supportedFormats': supportedformats or 'mp4,rtmp,m3u8,hds,dash,smooth',
'embedToken': embed_token,
if cookie.discard is not None:
cookie_dict['discard'] = cookie.discard
try:
- if (cookie.has_nonstandard_attr('httpOnly') or
- cookie.has_nonstandard_attr('httponly') or
- cookie.has_nonstandard_attr('HttpOnly')):
+ if (cookie.has_nonstandard_attr('httpOnly')
+ or cookie.has_nonstandard_attr('httponly')
+ or cookie.has_nonstandard_attr('HttpOnly')):
cookie_dict['httponly'] = True
except TypeError:
pass
video_id = mobj.group('id')
channel = mobj.group('channel') or mobj.group('channel_2')
- json_url = (('%s://%s.podomatic.com/entry/embed_params/%s' +
- '?permalink=true&rtmp=0') %
+ json_url = (('%s://%s.podomatic.com/entry/embed_params/%s'
+ + '?permalink=true&rtmp=0') %
(mobj.group('proto'), channel, video_id))
data_json = self._download_webpage(
json_url, video_id, 'Downloading video info')
extract_formats(child)
elif child.tag.endswith('File'):
video_url = child.text
- if (not video_url or video_url in processed_urls or
- any(p in video_url for p in ('NOT_USED', 'NOT-USED'))):
+ if (not video_url or video_url in processed_urls
+ or any(p in video_url for p in ('NOT_USED', 'NOT-USED'))):
continue
processed_urls.append(video_url)
ext = determine_ext(video_url)
raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True)
urls = player_params['releaseUrls']
- theplatform_url = (urls.get('progressive') or urls.get('html') or
- urls.get('standard') or player_params['relatedItemsURL'])
+ theplatform_url = (urls.get('progressive') or urls.get('html')
+ or urls.get('standard') or player_params['relatedItemsURL'])
return {
'_type': 'url_transparent',
genres = video_info.get('genres')
genre = (
- genres[0] if genres and isinstance(genres, list) and
- isinstance(genres[0], compat_str) else None)
+ genres[0] if genres and isinstance(genres, list)
+ and isinstance(genres[0], compat_str) else None)
is_explicit = video_info.get('isExplicit')
if is_explicit is True:
format_url = url_or_none(format_url)
if not format_url or not format_url.startswith(('http', '//', 'rtmp')):
continue
- if (format_id.startswith(('url', 'cache')) or
- format_id in ('extra_data', 'live_mp4', 'postlive_mp4')):
+ if (format_id.startswith(('url', 'cache'))
+ or format_id in ('extra_data', 'live_mp4', 'postlive_mp4')):
height = int_or_none(self._search_regex(
r'^(?:url|cache)(\d+)', format_id, 'height', default=None))
formats.append({
description = content.get('description')
thumbnail = content.get('thumbnail')
- timestamp = (int_or_none(content.get('release_date')) or
- int_or_none(content.get('release_date_ut')) or
- int_or_none(content.get('start_time')))
+ timestamp = (int_or_none(content.get('release_date'))
+ or int_or_none(content.get('release_date_ut'))
+ or int_or_none(content.get('start_time')))
duration = int_or_none(content.get('duration'))
series = content.get('program_title')
age_limit = int_or_none(content.get('restriction_age'))
transform_source=lambda s: js_to_json(strip_jsonp(s))).get('html')
if playlist_data is None:
return [None, None]
- drama_list = (get_element_by_class('p-drama-grid', playlist_data) or
- get_element_by_class('p-drama-half-row', playlist_data))
+ drama_list = (get_element_by_class('p-drama-grid', playlist_data)
+ or get_element_by_class('p-drama-half-row', playlist_data))
if drama_list is None:
raise ExtractorError('No episodes found')
video_urls = re.findall(r'<a[^>]+href="([^"]+)"', drama_list)
url_or_none(try_get(
player_response,
lambda x: x['streamingData']['hlsManifestUrl'],
- compat_str)) or
- url_or_none(try_get(
+ compat_str))
+ or url_or_none(try_get(
video_info, lambda x: x['hlsvp'][0], compat_str)))
if manifest_url:
formats = []
self._downloader.report_warning('unable to extract uploader nickname')
channel_id = (
- str_or_none(video_details.get('channelId')) or
- self._html_search_meta(
- 'channelId', video_webpage, 'channel id', default=None) or
- self._search_regex(
+ str_or_none(video_details.get('channelId'))
+ or self._html_search_meta(
+ 'channelId', video_webpage, 'channel id', default=None)
+ or self._search_regex(
r'data-channel-external-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
video_webpage, 'channel id', default=None, group='id'))
channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None
search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
title_span = (
- search_title('playlist-title') or
- search_title('title long-title') or
- search_title('title'))
+ search_title('playlist-title')
+ or search_title('title long-title')
+ or search_title('title'))
title = clean_html(title_span)
return self.playlist_result(url_results, playlist_id, title)
return next(
chan['cid'] for chan in channel_list
if chan.get('cid') and (
- chan.get('display_alias') == channel_name or
- chan.get('cid') == channel_name))
+ chan.get('display_alias') == channel_name
+ or chan.get('cid') == channel_name))
except StopIteration:
raise ExtractorError('Could not extract channel id')
# avconv does not have repeat option
if self.basename == 'ffmpeg':
cmd += [encodeArgument('-loglevel'), encodeArgument('repeat+info')]
- cmd += (files_cmd +
- [encodeArgument(o) for o in opts] +
- [encodeFilename(self._ffmpeg_filename_argument(out_path), True)])
+ cmd += (files_cmd
+ + [encodeArgument(o) for o in opts]
+ + [encodeFilename(self._ffmpeg_filename_argument(out_path), True)])
if self._downloader.params.get('verbose', False):
self._downloader.to_screen('[debug] ffmpeg command line: %s' % shell_quote(cmd))
information['ext'] = extension
# If we download foo.mp3 and convert it to... foo.mp3, then don't delete foo.mp3, silly.
- if (new_path == path or
- (self._nopostoverwrites and os.path.exists(encodeFilename(new_path)))):
+ if (new_path == path
+ or (self._nopostoverwrites and os.path.exists(encodeFilename(new_path)))):
self._downloader.to_screen('[ffmpeg] Post-process file %s exists, skipping' % new_path)
return [], information
except XAttrMetadataError as e:
if e.reason == 'NO_SPACE':
self._downloader.report_warning(
- 'There\'s no disk space left, disk quota exceeded or filesystem xattr limit exceeded. ' +
- (('Some ' if num_written else '') + 'extended attributes are not written.').capitalize())
+ 'There\'s no disk space left, disk quota exceeded or filesystem xattr limit exceeded. '
+ + (('Some ' if num_written else '') + 'extended attributes are not written.').capitalize())
elif e.reason == 'VALUE_TOO_LONG':
self._downloader.report_warning(
'Unable to write extended attributes due to too long values.')
self.msg = msg
# Parsing code and msg
- if (self.code in (errno.ENOSPC, errno.EDQUOT) or
- 'No space left' in self.msg or 'Disk quota excedded' in self.msg):
+ if (self.code in (errno.ENOSPC, errno.EDQUOT)
+ or 'No space left' in self.msg or 'Disk quota excedded' in self.msg):
self.reason = 'NO_SPACE'
elif self.code == errno.E2BIG or 'Argument list too long' in self.msg:
self.reason = 'VALUE_TOO_LONG'
def not_a_console(handle):
if handle == INVALID_HANDLE_VALUE or handle is None:
return True
- return ((GetFileType(handle) & ~FILE_TYPE_REMOTE) != FILE_TYPE_CHAR or
- GetConsoleMode(handle, ctypes.byref(ctypes.wintypes.DWORD())) == 0)
+ return ((GetFileType(handle) & ~FILE_TYPE_REMOTE) != FILE_TYPE_CHAR
+ or GetConsoleMode(handle, ctypes.byref(ctypes.wintypes.DWORD())) == 0)
if not_a_console(h):
return False
if _windows_write_string(s, out):
return
- if ('b' in getattr(out, 'mode', '') or
- sys.version_info[0] < 3): # Python 2 lies about mode of sys.stderr
+ if ('b' in getattr(out, 'mode', '')
+ or sys.version_info[0] < 3): # Python 2 lies about mode of sys.stderr
byt = s.encode(encoding or preferredencoding(), 'ignore')
out.write(byt)
elif hasattr(out, 'buffer'):
for k, v in a_dict.items():
if v is None:
continue
- if (k not in merged or
- (isinstance(v, compat_str) and v and
- isinstance(merged[k], compat_str) and
- not merged[k])):
+ if (k not in merged
+ or (isinstance(v, compat_str) and v
+ and isinstance(merged[k], compat_str)
+ and not merged[k])):
merged[k] = v
return merged
if m:
op = COMPARISON_OPERATORS[m.group('op')]
actual_value = dct.get(m.group('key'))
- if (m.group('quotedstrval') is not None or
- m.group('strval') is not None or
+ if (m.group('quotedstrval') is not None
+ or m.group('strval') is not None
# If the original field is a string and matching comparisonvalue is
# a number we should respect the origin of the original field
# and process comparison value as a string (see
# https://github.com/ytdl-org/youtube-dl/issues/11082).
- actual_value is not None and m.group('intval') is not None and
- isinstance(actual_value, compat_str)):
+ or actual_value is not None and m.group('intval') is not None
+ and isinstance(actual_value, compat_str)):
if m.group('op') not in ('=', '!='):
raise ValueError(
'Operator %s does not support string values!' % m.group('op'))
executable = 'xattr'
opts = ['-w', key, value]
- cmd = ([encodeFilename(executable, True)] +
- [encodeArgument(o) for o in opts] +
- [encodeFilename(path, True)])
+ cmd = ([encodeFilename(executable, True)]
+ + [encodeArgument(o) for o in opts]
+ + [encodeFilename(path, True)])
try:
p = subprocess.Popen(
projects / youtube-dl.git / commitdiff