from .common import InfoExtractor
from .openload import PhantomJSwrapper
-from ..compat import compat_str
from ..networking import Request
from ..networking.exceptions import HTTPError
from ..utils import (
if username is None:
return
- login_url = 'https://www.%s/%slogin' % (host, 'premium/' if 'premium' in host else '')
+ login_url = 'https://www.{}/{}login'.format(host, 'premium/' if 'premium' in host else '')
login_page = self._download_webpage(
- login_url, None, 'Downloading %s login page' % site)
+ login_url, None, f'Downloading {site} login page')
def is_logged(webpage):
return any(re.search(p, webpage) for p in (
})
response = self._download_json(
- 'https://www.%s/front/authenticate' % host, None,
- 'Logging in to %s' % site,
+ f'https://www.{host}/front/authenticate', None,
+ f'Logging in to {site}',
data=urlencode_postdata(login_form),
headers={
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
message = response.get('message')
if message is not None:
raise ExtractorError(
- 'Unable to login: %s' % message, expected=True)
+ f'Unable to login: {message}', expected=True)
raise ExtractorError('Unable to log in')
class PornHubIE(PornHubBaseIE):
IE_DESC = 'PornHub and Thumbzilla'
- _VALID_URL = r'''(?x)
+ _VALID_URL = rf'''(?x)
https?://
(?:
(?:[^/]+\.)?
- %s
+ {PornHubBaseIE._PORNHUB_HOST_RE}
/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
(?:www\.)?thumbzilla\.com/video/
)
(?P<id>[\da-z]+)
- ''' % PornHubBaseIE._PORNHUB_HOST_RE
+ '''
_EMBED_REGEX = [r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub(?:premium)?\.(?:com|net|org)/embed/[\da-z]+)']
_TESTS = [{
'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
'categories': list,
'subtitles': {
'en': [{
- "ext": 'srt'
- }]
+ 'ext': 'srt',
+ }],
},
},
'params': {
}]
def _extract_count(self, pattern, webpage, name):
- return str_to_int(self._search_regex(pattern, webpage, '%s count' % name, default=None))
+ return str_to_int(self._search_regex(pattern, webpage, f'{name} count', default=None))
def _real_extract(self, url):
mobj = self._match_valid_url(url)
def dl_webpage(platform):
self._set_cookie(host, 'platform', platform)
return self._download_webpage(
- 'https://www.%s/view_video.php?viewkey=%s' % (host, video_id),
- video_id, 'Downloading %s webpage' % platform)
+ f'https://www.{host}/view_video.php?viewkey={video_id}',
+ video_id, f'Downloading {platform} webpage')
webpage = dl_webpage('pc')
if error_msg:
error_msg = re.sub(r'\s+', ' ', error_msg)
raise ExtractorError(
- 'PornHub said: %s' % error_msg,
+ f'PornHub said: {error_msg}',
expected=True, video_id=video_id)
if any(re.search(p, webpage) for p in (
if not isinstance(definition, dict):
continue
video_url = definition.get('videoUrl')
- if not video_url or not isinstance(video_url, compat_str):
+ if not video_url or not isinstance(video_url, str):
continue
if video_url in video_urls_set:
continue
if not video_urls:
FORMAT_PREFIXES = ('media', 'quality', 'qualityItems')
js_vars = extract_js_vars(
- webpage, r'(var\s+(?:%s)_.+)' % '|'.join(FORMAT_PREFIXES),
+ webpage, r'(var\s+(?:{})_.+)'.format('|'.join(FORMAT_PREFIXES)),
default=None)
if js_vars:
for key, format_url in js_vars.items():
if not video_urls and re.search(
r'<[^>]+\bid=["\']lockedPlayer', webpage):
raise ExtractorError(
- 'Video %s is locked' % video_id, expected=True)
+ f'Video {video_id} is locked', expected=True)
if not video_urls:
js_vars = extract_js_vars(
def extract_vote_count(kind, name):
return self._extract_count(
- (r'<span[^>]+\bclass="votes%s"[^>]*>([\d,\.]+)</span>' % kind,
- r'<span[^>]+\bclass=["\']votes%s["\'][^>]*\bdata-rating=["\'](\d+)' % kind),
+ (rf'<span[^>]+\bclass="votes{kind}"[^>]*>([\d,\.]+)</span>',
+ rf'<span[^>]+\bclass=["\']votes{kind}["\'][^>]*\bdata-rating=["\'](\d+)'),
webpage, name)
view_count = self._extract_count(
def extract_list(meta_key):
div = self._search_regex(
- r'(?s)<div[^>]+\bclass=["\'].*?\b%sWrapper[^>]*>(.+?)</div>'
- % meta_key, webpage, meta_key, default=None)
+ rf'(?s)<div[^>]+\bclass=["\'].*?\b{meta_key}Wrapper[^>]*>(.+?)</div>',
+ webpage, meta_key, default=None)
if div:
return [clean_html(x).strip() for x in re.findall(r'(?s)<a[^>]+\bhref=[^>]+>.+?</a>', div)]
return [
self.url_result(
- 'http://www.%s/%s' % (host, video_url),
+ f'http://www.{host}/{video_url}',
PornHubIE.ie_key(), video_title=title)
for video_url, title in orderedSet(re.findall(
r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"',
class PornHubUserIE(PornHubPlaylistBaseIE):
- _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)' % PornHubBaseIE._PORNHUB_HOST_RE
+ _VALID_URL = rf'(?P<url>https?://(?:[^/]+\.)?{PornHubBaseIE._PORNHUB_HOST_RE}/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)'
_TESTS = [{
'url': 'https://www.pornhub.com/model/zoe_ph',
'playlist_mincount': 118,
def _real_extract(self, url):
mobj = self._match_valid_url(url)
user_id = mobj.group('id')
- videos_url = '%s/videos' % mobj.group('url')
+ videos_url = '{}/videos'.format(mobj.group('url'))
self._set_age_cookies(mobj.group('host'))
page = self._extract_page(url)
if page:
VIDEOS = '/videos'
def download_page(base_url, num, fallback=False):
- note = 'Downloading page %d%s' % (num, ' (switch to fallback)' if fallback else '')
+ note = 'Downloading page {}{}'.format(num, ' (switch to fallback)' if fallback else '')
return self._download_webpage(
base_url, item_id, note, query={'page': num})
class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
- _VALID_URL = r'https?://(?:[^/]+\.)?%s/(?!playlist/)(?P<id>(?:[^/]+/)*[^/?#&]+)' % PornHubBaseIE._PORNHUB_HOST_RE
+ _VALID_URL = rf'https?://(?:[^/]+\.)?{PornHubBaseIE._PORNHUB_HOST_RE}/(?!playlist/)(?P<id>(?:[^/]+/)*[^/?#&]+)'
_TESTS = [{
'url': 'https://www.pornhub.com/model/zoe_ph/videos',
'only_matching': True,
def suitable(cls, url):
return (False
if PornHubIE.suitable(url) or PornHubUserIE.suitable(url) or PornHubUserVideosUploadIE.suitable(url)
- else super(PornHubPagedVideoListIE, cls).suitable(url))
+ else super().suitable(url))
class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
- _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)' % PornHubBaseIE._PORNHUB_HOST_RE
+ _VALID_URL = rf'(?P<url>https?://(?:[^/]+\.)?{PornHubBaseIE._PORNHUB_HOST_RE}/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)'
_TESTS = [{
'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
'info_dict': {
class PornHubPlaylistIE(PornHubPlaylistBaseIE):
- _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/playlist/(?P<id>[^/?#&]+))' % PornHubBaseIE._PORNHUB_HOST_RE
+ _VALID_URL = rf'(?P<url>https?://(?:[^/]+\.)?{PornHubBaseIE._PORNHUB_HOST_RE}/playlist/(?P<id>[^/?#&]+))'
_TESTS = [{
'url': 'https://www.pornhub.com/playlist/44121572',
'info_dict': {
page_entries = self._extract_entries(webpage, host)
def download_page(page_num):
- note = 'Downloading page {}'.format(page_num)
- page_url = 'https://www.{}/playlist/viewChunked'.format(host)
+ note = f'Downloading page {page_num}'
+ page_url = f'https://www.{host}/playlist/viewChunked'
return self._download_webpage(page_url, item_id, note, query={
'id': playlist_id,
'page': page_num,
page_entries = self._extract_entries(webpage, host)
if not page_entries:
break
- for e in page_entries:
- yield e
+ yield from page_entries
def _real_extract(self, url):
mobj = self._match_valid_url(url)
projects / yt-dlp.git / blobdiff