import functools
import itertools
+import math
import operator
import re
)
from .openload import PhantomJSwrapper
from ..utils import (
+ clean_html,
determine_ext,
ExtractorError,
int_or_none,
class PornHubBaseIE(InfoExtractor):
_NETRC_MACHINE = 'pornhub'
+ _PORNHUB_HOST_RE = r'(?:(?P<host>pornhub(?:premium)?\.(?:com|net|org))|pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd\.onion)'
def _download_webpage_handle(self, *args, **kwargs):
def dl(*args, **kwargs):
_VALID_URL = r'''(?x)
https?://
(?:
- (?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net|org))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
+ (?:[^/]+\.)?
+ %s
+ /(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
(?:www\.)?thumbzilla\.com/video/
)
(?P<id>[\da-z]+)
- '''
+ ''' % PornHubBaseIE._PORNHUB_HOST_RE
_TESTS = [{
'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
'md5': 'a6391306d050e4547f62b3f485dd9ba9',
'age_limit': 18,
'tags': list,
'categories': list,
+ 'cast': list,
},
}, {
# non-ASCII title
}, {
'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5f75b0f4b18e3',
'only_matching': True,
+ }, {
+ # geo restricted
+ 'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5a9813bfa7156',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd.onion/view_video.php?viewkey=ph5a9813bfa7156',
+ 'only_matching': True,
}]
@staticmethod
webpage)
def _extract_count(self, pattern, webpage, name):
- return str_to_int(self._search_regex(
- pattern, webpage, '%s count' % name, fatal=False))
+ return str_to_int(self._search_regex(pattern, webpage, '%s count' % name, default=None))
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
+ mobj = self._match_valid_url(url)
host = mobj.group('host') or 'pornhub.com'
video_id = mobj.group('id')
'PornHub said: %s' % error_msg,
expected=True, video_id=video_id)
+ if any(re.search(p, webpage) for p in (
+ r'class=["\']geoBlocked["\']',
+ r'>\s*This content is unavailable in your country')):
+ self.raise_geo_restricted()
+
# video_title from flashvars contains whitespace instead of non-ASCII (see
# http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying
# on that anymore.
formats = []
def add_format(format_url, height=None):
- tbr = None
- mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', format_url)
- if mobj:
- if not height:
- height = int(mobj.group('height'))
- tbr = int(mobj.group('tbr'))
+ ext = determine_ext(format_url)
+ if ext == 'mpd':
+ formats.extend(self._extract_mpd_formats(
+ format_url, video_id, mpd_id='dash', fatal=False))
+ return
+ if ext == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(
+ format_url, video_id, 'mp4', entry_protocol='m3u8_native',
+ m3u8_id='hls', fatal=False))
+ return
+ if not height:
+ height = int_or_none(self._search_regex(
+ r'(?P<height>\d+)[pP]?_\d+[kK]', format_url, 'height',
+ default=None))
formats.append({
'url': format_url,
'format_id': '%dp' % height if height else None,
'height': height,
- 'tbr': tbr,
})
for video_url, height in video_urls:
r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None)
if upload_date:
upload_date = upload_date.replace('/', '')
- ext = determine_ext(video_url)
- if ext == 'mpd':
- formats.extend(self._extract_mpd_formats(
- video_url, video_id, mpd_id='dash', fatal=False))
- continue
- elif ext == 'm3u8':
- formats.extend(self._extract_m3u8_formats(
- video_url, video_id, 'mp4', entry_protocol='m3u8_native',
- m3u8_id='hls', fatal=False))
- continue
if '/video/get_media' in video_url:
medias = self._download_json(video_url, video_id, fatal=False)
if isinstance(medias, list):
add_format(video_url, height)
continue
add_format(video_url)
- self._sort_formats(formats)
+
+ # field_preference is unnecessary here, but kept for code-similarity with youtube-dl
+ self._sort_formats(
+ formats, field_preference=('height', 'width', 'fps', 'format_id'))
video_uploader = self._html_search_regex(
r'(?s)From: .+?<(?:a\b[^>]+\bhref=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',
r'(?s)<div[^>]+\bclass=["\'].*?\b%sWrapper[^>]*>(.+?)</div>'
% meta_key, webpage, meta_key, default=None)
if div:
- return re.findall(r'<a[^>]+\bhref=[^>]+>([^<]+)', div)
+ return [clean_html(x).strip() for x in re.findall(r'(?s)<a[^>]+\bhref=[^>]+>.+?</a>', div)]
info = self._search_json_ld(webpage, video_id, default={})
# description provided in JSON-LD is irrelevant
'age_limit': 18,
'tags': extract_list('tags'),
'categories': extract_list('categories'),
+ 'cast': extract_list('pornstars'),
'subtitles': subtitles,
}, info)
class PornHubUserIE(PornHubPlaylistBaseIE):
- _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net|org))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)'
+ _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)' % PornHubBaseIE._PORNHUB_HOST_RE
_TESTS = [{
'url': 'https://www.pornhub.com/model/zoe_ph',
'playlist_mincount': 118,
# Same as before, multi page
'url': 'https://www.pornhubpremium.com/pornstar/lily-labeau',
'only_matching': True,
+ }, {
+ 'url': 'https://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd.onion/model/zoe_ph',
+ 'only_matching': True,
}]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
+ mobj = self._match_valid_url(url)
user_id = mobj.group('id')
videos_url = '%s/videos' % mobj.group('url')
page = self._extract_page(url)
break
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
+ mobj = self._match_valid_url(url)
host = mobj.group('host')
item_id = mobj.group('id')
class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
- _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net|org))/(?P<id>(?:[^/]+/)*[^/?#&]+)'
+ _VALID_URL = r'https?://(?:[^/]+\.)?%s/(?!playlist/)(?P<id>(?:[^/]+/)*[^/?#&]+)' % PornHubBaseIE._PORNHUB_HOST_RE
_TESTS = [{
'url': 'https://www.pornhub.com/model/zoe_ph/videos',
'only_matching': True,
'url': 'https://www.pornhub.com/video/incategories/60fps-1/hd-porn',
'only_matching': True,
}, {
- 'url': 'https://www.pornhub.com/playlist/44121572',
- 'info_dict': {
- 'id': 'playlist/44121572',
- },
- 'playlist_mincount': 132,
- }, {
- 'url': 'https://www.pornhub.com/playlist/4667351',
- 'only_matching': True,
- }, {
- 'url': 'https://de.pornhub.com/playlist/4667351',
+ 'url': 'https://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd.onion/model/zoe_ph/videos',
'only_matching': True,
}]
class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
- _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net|org))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)'
+ _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)' % PornHubBaseIE._PORNHUB_HOST_RE
_TESTS = [{
'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
'info_dict': {
}, {
'url': 'https://www.pornhub.com/model/zoe_ph/videos/upload',
'only_matching': True,
+ }, {
+ 'url': 'http://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd.onion/pornstar/jenny-blighe/videos/upload',
+ 'only_matching': True,
}]
+
+
+class PornHubPlaylistIE(PornHubPlaylistBaseIE):
+ _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/playlist/(?P<id>[^/?#&]+))' % PornHubBaseIE._PORNHUB_HOST_RE
+ _TESTS = [{
+ 'url': 'https://www.pornhub.com/playlist/44121572',
+ 'info_dict': {
+ 'id': '44121572',
+ },
+ 'playlist_count': 77,
+ }, {
+ 'url': 'https://www.pornhub.com/playlist/4667351',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://de.pornhub.com/playlist/4667351',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://de.pornhub.com/playlist/4667351?page=2',
+ 'only_matching': True,
+ }]
+
+ def _entries(self, url, host, item_id):
+ webpage = self._download_webpage(url, item_id, 'Downloading page 1')
+ playlist_id = self._search_regex(r'var\s+playlistId\s*=\s*"([^"]+)"', webpage, 'playlist_id')
+ video_count = int_or_none(
+ self._search_regex(r'var\s+itemsCount\s*=\s*([0-9]+)\s*\|\|', webpage, 'video_count'))
+ token = self._search_regex(r'var\s+token\s*=\s*"([^"]+)"', webpage, 'token')
+ page_count = math.ceil((video_count - 36) / 40.) + 1
+ 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)
+ return self._download_webpage(page_url, item_id, note, query={
+ 'id': playlist_id,
+ 'page': page_num,
+ 'token': token,
+ })
+
+ for page_num in range(1, page_count + 1):
+ if page_num > 1:
+ webpage = download_page(page_num)
+ page_entries = self._extract_entries(webpage, host)
+ if not page_entries:
+ break
+ for e in page_entries:
+ yield e
+
+ def _real_extract(self, url):
+ mobj = self._match_valid_url(url)
+ host = mobj.group('host')
+ item_id = mobj.group('id')
+
+ self._login(host)
+
+ return self.playlist_result(self._entries(mobj.group('url'), host, item_id), item_id)