X-Git-Url: https://jfr.im/git/yt-dlp.git/blobdiff_plain/1d3d579c2142f69831b6ae140e1d8e824e07fa0e..61edf57f8f13f6dfd81154174e647eb5fdd26089:/yt_dlp/extractor/pornhub.py diff --git a/yt_dlp/extractor/pornhub.py b/yt_dlp/extractor/pornhub.py index 999d038d4..679dc6323 100644 --- a/yt_dlp/extractor/pornhub.py +++ b/yt_dlp/extractor/pornhub.py @@ -6,7 +6,6 @@ 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 ( @@ -81,14 +80,14 @@ def _login(self, host): 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 ( - r'class=["\']signOut', - r'>Sign\s+[Oo]ut\s*<')) + r'id="profileMenuDropdown"', + r'class="ph-icon-logout"')) if is_logged(login_page): self._logged_in = True @@ -97,13 +96,13 @@ def is_logged(webpage): login_form = self._hidden_inputs(login_page) login_form.update({ - 'username': username, + 'email': username, 'password': password, }) 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', @@ -118,23 +117,23 @@ def is_logged(webpage): 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[\da-z]+) - ''' % PornHubBaseIE._PORNHUB_HOST_RE + ''' _EMBED_REGEX = [r']+?src=["\'](?P(?:https?:)?//(?:www\.)?pornhub(?:premium)?\.(?:com|net|org)/embed/[\da-z]+)'] _TESTS = [{ 'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015', @@ -196,8 +195,8 @@ class PornHubIE(PornHubBaseIE): 'categories': list, 'subtitles': { 'en': [{ - "ext": 'srt' - }] + 'ext': 'srt', + }], }, }, 'params': { @@ -266,7 +265,7 @@ class PornHubIE(PornHubBaseIE): }] 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) @@ -279,8 +278,8 @@ def _real_extract(self, 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') @@ -291,7 +290,7 @@ def dl_webpage(platform): 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 ( @@ -332,7 +331,7 @@ def dl_webpage(platform): 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 @@ -392,7 +391,7 @@ def parse_quality_items(quality_items): 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(): @@ -403,7 +402,7 @@ def parse_quality_items(quality_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( @@ -470,8 +469,8 @@ def add_format(format_url, height=None): def extract_vote_count(kind, name): return self._extract_count( - (r']+\bclass="votes%s"[^>]*>([\d,\.]+)' % kind, - r']+\bclass=["\']votes%s["\'][^>]*\bdata-rating=["\'](\d+)' % kind), + (rf']+\bclass="votes{kind}"[^>]*>([\d,\.]+)', + rf']+\bclass=["\']votes{kind}["\'][^>]*\bdata-rating=["\'](\d+)'), webpage, name) view_count = self._extract_count( @@ -483,8 +482,8 @@ def extract_vote_count(kind, name): def extract_list(meta_key): div = self._search_regex( - r'(?s)]+\bclass=["\'].*?\b%sWrapper[^>]*>(.+?)' - % meta_key, webpage, meta_key, default=None) + rf'(?s)]+\bclass=["\'].*?\b{meta_key}Wrapper[^>]*>(.+?)', + webpage, meta_key, default=None) if div: return [clean_html(x).strip() for x in re.findall(r'(?s)]+\bhref=[^>]+>.+?', div)] @@ -528,7 +527,7 @@ def _extract_entries(self, webpage, host): 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="([^"]+)"', @@ -537,7 +536,7 @@ def _extract_entries(self, webpage, host): class PornHubUserIE(PornHubPlaylistBaseIE): - _VALID_URL = r'(?Phttps?://(?:[^/]+\.)?%s/(?:(?:user|channel)s|model|pornstar)/(?P[^/?#&]+))(?:[?#&]|/(?!videos)|$)' % PornHubBaseIE._PORNHUB_HOST_RE + _VALID_URL = rf'(?Phttps?://(?:[^/]+\.)?{PornHubBaseIE._PORNHUB_HOST_RE}/(?:(?:user|channel)s|model|pornstar)/(?P[^/?#&]+))(?:[?#&]|/(?!videos)|$)' _TESTS = [{ 'url': 'https://www.pornhub.com/model/zoe_ph', 'playlist_mincount': 118, @@ -574,7 +573,7 @@ class PornHubUserIE(PornHubPlaylistBaseIE): 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: @@ -599,7 +598,7 @@ def _entries(self, url, host, item_id): 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}) @@ -646,7 +645,7 @@ def _real_extract(self, url): class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE): - _VALID_URL = r'https?://(?:[^/]+\.)?%s/(?!playlist/)(?P(?:[^/]+/)*[^/?#&]+)' % PornHubBaseIE._PORNHUB_HOST_RE + _VALID_URL = rf'https?://(?:[^/]+\.)?{PornHubBaseIE._PORNHUB_HOST_RE}/(?!playlist/)(?P(?:[^/]+/)*[^/?#&]+)' _TESTS = [{ 'url': 'https://www.pornhub.com/model/zoe_ph/videos', 'only_matching': True, @@ -748,11 +747,11 @@ class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE): 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'(?Phttps?://(?:[^/]+\.)?%s/(?:(?:user|channel)s|model|pornstar)/(?P[^/]+)/videos/upload)' % PornHubBaseIE._PORNHUB_HOST_RE + _VALID_URL = rf'(?Phttps?://(?:[^/]+\.)?{PornHubBaseIE._PORNHUB_HOST_RE}/(?:(?:user|channel)s|model|pornstar)/(?P[^/]+)/videos/upload)' _TESTS = [{ 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload', 'info_dict': { @@ -769,7 +768,7 @@ class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE): class PornHubPlaylistIE(PornHubPlaylistBaseIE): - _VALID_URL = r'(?Phttps?://(?:[^/]+\.)?%s/playlist/(?P[^/?#&]+))' % PornHubBaseIE._PORNHUB_HOST_RE + _VALID_URL = rf'(?Phttps?://(?:[^/]+\.)?{PornHubBaseIE._PORNHUB_HOST_RE}/playlist/(?P[^/?#&]+))' _TESTS = [{ 'url': 'https://www.pornhub.com/playlist/44121572', 'info_dict': { @@ -797,8 +796,8 @@ def _entries(self, url, host, item_id): 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, @@ -811,8 +810,7 @@ def download_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)